Paper Citation Record · LEDGER

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

As of 6 August 2026, this Paper Citation Record lists 50 of 50 outbound references and 73 inbound Pith citation observations for arXiv:2505.24298.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2505.24298 v5

Coverage vector

measured 50 of 50 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-11T11:50:26.030339Z

measured 123 of 123 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 73 of 73 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T04:17:54.142833Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

50 of 50 outbound references displayed

verified exact15
verified fuzzy15
unresolved14
parse uncertain0
malformed identifier2
metadata mismatch4

External citation measurements

0
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation f1b5f65d-5401-46eb-a59d-e09f50458e72 · outbound

This paper cites Dota 2 with Large Scale Deep Reinforcement Learning.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Dota 2 with Large Scale Deep Reinforcement Learning

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-15T14:24:22.034522Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 04c98360-1a8c-4d4b-9851-275de73d2520 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Evaluating Large Language Models Trained on Code

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-15T14:24:22.024153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c68c561a-5cbb-46c8-b5b1-78b1f6320f9f · outbound

This paper cites an unresolved cited work.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-05-15T14:24:22.092893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f6726aac-2bc3-4aa1-867d-592e16976e21 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Training Verifiers to Solve Math Word Problems

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-15T14:24:22.061360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 907e8104-ed56-4057-aa42-6ef156b66393 · outbound

This paper cites Espeholt, H.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Espeholt, H

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T14:24:22.095148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 09668f0b-c48b-454b-8315-75fc0a8cb846 · outbound

This paper cites Espeholt, R.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Espeholt, R

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T14:24:22.097530Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 65c5e111-101c-433e-b470-277b310c206f · outbound

This paper cites Hendrycks, C.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Hendrycks, C

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T14:24:22.099511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 50b91d8b-0a5f-45b3-913e-904d135b37b4 · outbound

This paper cites Hilton, K.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Hilton, K

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T14:24:22.102020Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ddd1dcba-6b8a-4ca0-9e75-122efaeeb268 · outbound

This paper cites Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-15T14:24:22.069097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1a8ba6c0-7b7e-4f1c-a6ae-8e5caf4218e9 · outbound

This paper cites an unresolved cited work.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-05-15T14:24:22.104566Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d379ce49-8768-4e9f-824c-cb32e3bfe0d9 · outbound

This paper cites an unresolved cited work.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-05-15T14:24:22.107087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 842f1a27-327f-4e04-9398-54f70b48c754 · outbound

This paper cites an unresolved cited work.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-05-15T14:24:22.109287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 006a0879-9795-4d9f-a0a4-1c4ed76a61c7 · outbound

This paper cites Kapturowski, G.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Kapturowski, G

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T14:24:22.111431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2bcfd707-7ecc-45ae-9639-e65d83ae8a57 · outbound

This paper cites Efficient Memory Management for Large Language Model Serving with PagedAttention , booktitle =.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Efficient Memory Management for Large Language Model Serving with PagedAttention , booktitle =

Reference 20

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T14:24:21.973774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3afe3235-b742-4fdf-9ba2-163c2ef1226f · outbound

This paper cites an unresolved cited work.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-05-15T14:24:22.113383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a83167a8-ffea-4f7c-80bb-72c2b906a51b · outbound

This paper cites an unresolved cited work.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-05-15T14:24:22.115514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cd3d6ccb-9aac-4db8-8979-46e7f573bb14 · outbound

This paper cites Liang, R.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Liang, R

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T14:24:22.118256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 00c3bd1a-c9f2-4983-9911-f4b4947d08cd · outbound

This paper cites ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning ZebraLogic: On the Scaling Limits of LLMs for Logical Reasoning

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:24:22.051843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4c66119e-5d22-4e30-b656-2bc41e0ceaef · outbound

This paper cites an unresolved cited work.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-05-15T14:24:22.120199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5b2a3e38-cc70-4796-8b56-a8489d7d4d67 · outbound

This paper cites an unresolved cited work.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-05-15T14:24:22.122299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bc842cf3-3971-4022-b753-e1754b602810 · outbound

This paper cites an unresolved cited work.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-05-15T14:24:22.124185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5187a572-3c6a-49dc-b575-ee6e3fe22140 · outbound

This paper cites an unresolved cited work.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-05-15T14:24:22.126219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2fe33030-686b-40dd-a9d0-a8732103d5fa · outbound

This paper cites Specinfer: Accelerating large language model serving with tree-based speculative inference and verification.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Specinfer: Accelerating large language model serving with tree-based speculative inference and verification

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:24:22.009165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9ac1dd7b-70c8-4f58-a4b3-041e34200782 · outbound

This paper cites URL https://openai.com/index/ learning-to-reason-with-llms/.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning URL https://openai.com/index/ learning-to-reason-with-llms/

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T14:24:22.128959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 22c0fc43-2c26-490e-8a5c-a489cb6e1b09 · outbound

This paper cites URL https://openai.com/index/ introducing-o3-and-o4-mini/.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning URL https://openai.com/index/ introducing-o3-and-o4-mini/

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T14:24:22.131543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 17be9c91-965d-422f-85f3-be94cfbb6859 · outbound

This paper cites Ouyang, J.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Ouyang, J

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T14:24:22.134269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 746cce49-6e19-44ed-a3ce-a0c2003f75ea · outbound

This paper cites an unresolved cited work.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-05-15T14:24:22.136472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ec081b8d-129c-43c1-8ab9-c91d41defadf · outbound

This paper cites Paszke, S.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Paszke, S

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T14:24:22.071955Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b34c7e4e-1a27-448a-892a-0bbd00897967 · outbound

This paper cites Wiley Series in Probability and Statistics, Wiley (1994).

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Wiley Series in Probability and Statistics, Wiley (1994)

Reference 39

Resolution: verified exact; doi, observed 2026-05-15T14:24:22.012386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4cfce521-ebf0-4a16-bfe9-efb03efa7f1c · outbound

This paper cites Generalized Slow Roll for Tensors.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Generalized Slow Roll for Tensors

Reference 40

Resolution: metadata mismatch; local_arxiv, observed 2026-05-15T14:24:22.016165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 75a53cec-ed67-4faf-a111-953e497e4cbf · outbound

This paper cites Schulman, P.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Schulman, P

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T14:24:22.074665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1df6b9ad-1039-4be0-b252-ddcca0f8182d · outbound

This paper cites Proximal Policy Optimization Algorithms.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Proximal Policy Optimization Algorithms

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-05-15T14:24:22.038379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 80570ad7-d6ed-406a-8833-791c6d4c419a · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 45

Resolution: verified exact; local_arxiv, observed 2026-05-15T14:24:22.042354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 55dbd829-c259-4871-b28d-53e033abd762 · outbound

This paper cites Hybridflow: A flexible and efficient rlhf framework.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Hybridflow: A flexible and efficient rlhf framework

Reference 48

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T14:24:22.003970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9b490396-40b7-48ba-8703-c5eb8ac69ba5 · outbound

This paper cites Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-05-15T14:24:22.046981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bf02d8bd-d30e-42e4-80c0-b9cd86e0f88e · outbound

This paper cites an unresolved cited work.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Unresolved cited work

Reference 51

Resolution: unresolved; raw_fallback, observed 2026-05-15T14:24:22.077208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a9bb1a91-530b-4c64-91dc-330177927b5a · outbound

This paper cites INTELLECT-2: A Reasoning Model Trained Through Globally Decentralized Reinforcement Learning.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning INTELLECT-2: A Reasoning Model Trained Through Globally Decentralized Reinforcement Learning

Reference 53

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:24:22.057134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ac46e50e-a781-4a67-b569-1d9158477b2e · outbound

This paper cites Vaswani, N.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Vaswani, N

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T14:24:22.079530Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bb8f25bb-19ec-4261-b3a5-29ee5836815c · outbound

This paper cites Liar” ends the game, then both players reveal their dice. If the last bid is not satisﬁed, then the player who called “Liar.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Liar” ends the game, then both players reveal their dice. If the last bid is not satisﬁed, then the player who called “Liar

Reference 55

Resolution: verified exact; doi, observed 2026-05-15T14:24:21.993334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 776aaf06-5ed0-4e76-b9fe-01a51c09984b · outbound

This paper cites an unresolved cited work.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Unresolved cited work

Reference 56

Resolution: unresolved; raw_fallback, observed 2026-05-15T14:24:22.081758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b991c518-178b-426d-a6ca-76576e505494 · outbound

This paper cites DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:24:22.065868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3628c109-2250-48f9-95a8-63f07031ee6a · outbound

This paper cites an unresolved cited work.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Unresolved cited work

Reference 64

Resolution: unresolved; raw_fallback, observed 2026-05-15T14:24:22.083916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ed6d1c0e-4631-41c4-aa10-076c7defaa9f · outbound

This paper cites Job Scheduling Strategies for Parallel Processing pp 44–60.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Job Scheduling Strategies for Parallel Processing pp 44–60

Reference 65

Resolution: metadata mismatch; doi, observed 2026-05-15T14:24:21.978165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 79e61d0b-a2c8-4729-9c60-20162a21aa35 · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 66

Resolution: malformed identifier; local_arxiv, observed 2026-05-15T14:24:21.986322Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4fd6d89d-55ff-46da-b1b7-fae958d9c605 · outbound

This paper cites VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks

Reference 67

Resolution: verified exact; local_arxiv, observed 2026-05-15T14:24:22.020162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e28f579a-43c0-4b89-bbaf-fd5e5bc8e433 · outbound

This paper cites I am EdgeRunner AI.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning I am EdgeRunner AI

Reference 68

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:24:21.999394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 52324d64-6c04-4d1f-801f-61360ca221ce · outbound

This paper cites Zheng, L.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Zheng, L

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T14:24:22.086140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 59953177-8abe-4da9-bdfe-30c73e0f5279 · outbound

This paper cites StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation

Reference 70

Resolution: malformed identifier; arxiv_id, observed 2026-05-15T14:24:22.029099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ef40b99f-46ba-4556-bd29-cd07bb5f073d · outbound

This paper cites Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning Guidelines: • The answer NA means that the paper does not involve crowdsourcing nor research with human subjects

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T14:24:22.088384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d73722ed-f188-4954-af71-82d1754581e9 · outbound

This paper cites For most of the results, we use SGLang [63] v0.4.6 as generation backend and pytorch FSDP [ 62] as training backend.

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning For most of the results, we use SGLang [63] v0.4.6 as generation backend and pytorch FSDP [ 62] as training backend

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T14:24:22.090551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Pith citing papers

Observation 82ad9e0a-fd61-4bad-ad06-681f30b30f8b · inbound

Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models cites this paper.

Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 191

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:24:22.137431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 87c5e038-0a6d-4e4b-b4a3-bd42cce82f05 · inbound

Reinforcement Learning from Human Feedback cites this paper.

Reinforcement Learning from Human Feedback AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 134

Resolution: verified exact; local_arxiv, observed 2026-05-22T19:32:01.288940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c27dc36d-5ebe-46fa-ab14-4e34213b8488 · inbound

Agent Lightning: Train ANY AI Agents with Reinforcement Learning cites this paper.

Agent Lightning: Train ANY AI Agents with Reinforcement Learning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-06T04:17:54.142833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0525c134-88c7-4d1a-a5e2-4c201a03f947 · inbound

AWorld: Orchestrating the Training Recipe for Agentic AI cites this paper.

AWorld: Orchestrating the Training Recipe for Agentic AI AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T15:10:17.779979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8011cfc6-c1fd-46e9-a2f6-a47513364950 · inbound

A Survey of Reinforcement Learning for Large Reasoning Models cites this paper.

A Survey of Reinforcement Learning for Large Reasoning Models AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 147

Resolution: verified exact; local_arxiv, observed 2026-05-18T00:02:25.401254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d8d6583d-a411-4896-ac62-6ef44ab2e356 · inbound

Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle cites this paper.

Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-04T16:07:29.199481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 413d2afd-76e0-4a29-bcf6-2e2cd3ca6ef8 · inbound

Which Heads Matter for Reasoning? RL-Guided KV Cache Compression cites this paper.

Which Heads Matter for Reasoning? RL-Guided KV Cache Compression AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-04T10:50:09.254400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f02a984-a9be-4d4e-a564-8ec48c2572e0 · inbound

Don't Tell the Answer, Truly Guide the Reasoning During RL Rollouts cites this paper.

Don't Tell the Answer, Truly Guide the Reasoning During RL Rollouts AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T10:39:26.538300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfc8bfee-2973-4ef5-ac6b-aeaf4c5df871 · inbound

RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMs cites this paper.

RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMs AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-18T05:30:55.176765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4bee1411-9875-4874-9e6f-8841b42ac7a5 · inbound

Seer: Online Context Learning for Fast Synchronous LLM Reinforcement Learning cites this paper.

Seer: Online Context Learning for Fast Synchronous LLM Reinforcement Learning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-17T20:40:14.640754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation aacc2d48-dda8-4a96-a6ab-3f900befb151 · inbound

HetRL: Efficient Reinforcement Learning for LLMs in Heterogeneous Environments cites this paper.

HetRL: Efficient Reinforcement Learning for LLMs in Heterogeneous Environments AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-16T22:23:36.646232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 70d7ed3e-a225-46ab-9638-255e8247c743 · inbound

OpenTinker: Separating Concerns in Agentic Reinforcement Learning cites this paper.

OpenTinker: Separating Concerns in Agentic Reinforcement Learning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T11:08:09.185820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d2d5ef5-381b-41af-b18b-44f0ae5fc23f · inbound

StaleFlow: Staleness-Aware Data Management for Mitigating Data Skewness in Fully Disaggregated RL Post-Training cites this paper.

StaleFlow: Staleness-Aware Data Management for Mitigating Data Skewness in Fully Disaggregated RL Post-Training AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T06:25:47.347729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbaf49e3-f50a-4ba9-8bc2-a838fd1b49c6 · inbound

CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning cites this paper.

CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T09:01:48.820681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26e97cb3-bbe2-4ffc-aa2d-49d925b892c4 · inbound

FP8-RL: A Practical and Stable Low-Precision Stack for LLM Reinforcement Learning cites this paper.

FP8-RL: A Practical and Stable Low-Precision Stack for LLM Reinforcement Learning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-16T11:07:47.092261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation eee55e6b-5056-48fa-a879-7ed6a6f470ef · inbound

Thinking Seeds: Leveraging Historical Diversity for Position-Aware RL in LLMs cites this paper.

Thinking Seeds: Leveraging Historical Diversity for Position-Aware RL in LLMs AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-03T07:01:12.356383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c0d5b6e-5517-449d-bb89-e4a7f943ed09 · inbound

ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment cites this paper.

ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-16T09:40:49.102585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4c092ba1-561c-46a3-a115-ae396192aaa4 · inbound

ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment cites this paper.

ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-21T14:10:13.456057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation af19c22a-1aa9-4c5b-87fb-42df5799b123 · inbound

ECHO-2: A Large-Scale Distributed Rollout Framework for Cost-Efficient Reinforcement Learning cites this paper.

ECHO-2: A Large-Scale Distributed Rollout Framework for Cost-Efficient Reinforcement Learning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T05:32:40.837833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 084fafff-b067-49f9-a8bc-5ba0b9385e35 · inbound

RL-VLA$^3$: A Flexible and Asynchronous Reinforcement Learning Framework for VLA Training cites this paper.

RL-VLA$^3$: A Flexible and Asynchronous Reinforcement Learning Framework for VLA Training AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-16T07:02:28.930758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 996aeed6-6acc-4490-8760-039426f88fec · inbound

When RL Meets Adaptive Speculative Training: A Unified Training-Serving System cites this paper.

When RL Meets Adaptive Speculative Training: A Unified Training-Serving System AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-16T06:37:28.921689Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 082f7f1c-3122-49c3-9626-0c5d3de20b55 · inbound

ThunderAgent: A Simple, Fast and Program-Aware Agentic Inference System cites this paper.

ThunderAgent: A Simple, Fast and Program-Aware Agentic Inference System AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T23:32:11.710514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0167d83b-c497-4164-8fce-0954ae9341c9 · inbound

WebChain: A Large-Scale Human-Annotated Dataset of Real-World Web Interaction Traces cites this paper.

WebChain: A Large-Scale Human-Annotated Dataset of Real-World Web Interaction Traces AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-15T16:36:17.548558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c0f8730c-77fb-48c0-ac05-e358dc8b2efb · inbound

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments cites this paper.

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T18:45:20.779259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e196520-b2b4-49e4-9d2b-1e01e7157541 · inbound

OpenClaw-RL: Train Any Agent Simply by Talking cites this paper.

OpenClaw-RL: Train Any Agent Simply by Talking AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:24:22.137431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9799de75-3d03-40f4-8300-dda427b53027 · inbound

TensorHub: Scalable and Elastic Weight Transfer for LLM RL Training cites this paper.

TensorHub: Scalable and Elastic Weight Transfer for LLM RL Training AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:24:22.137431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a80d0625-6c83-4771-ae17-5c4bf08115af · inbound

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale cites this paper.

Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:24:22.137431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ec567ed1-d217-4fe4-b075-28002f1fae0f · inbound

Freshness-Aware Prioritized Experience Replay for LLM/VLM Reinforcement Learning cites this paper.

Freshness-Aware Prioritized Experience Replay for LLM/VLM Reinforcement Learning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:24:22.137431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 15ec06f5-f9ea-4654-b1b6-b027fb62a2e5 · inbound

StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning cites this paper.

StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:24:22.137431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 28d5ebe2-0bb1-4463-abb6-4feedf122d17 · inbound

JigsawRL: Assembling RL Pipelines for Efficient LLM Post-Training cites this paper.

JigsawRL: Assembling RL Pipelines for Efficient LLM Post-Training AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:24:22.137431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3348572b-979b-420c-814a-95fb44087120 · inbound

AMMA: A Multi-Chiplet Memory-Centric Architecture for Low-Latency 1M Context Attention Serving cites this paper.

AMMA: A Multi-Chiplet Memory-Centric Architecture for Low-Latency 1M Context Attention Serving AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:24:22.137431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8795d9fb-7462-4608-9133-2903e6a01b50 · inbound

DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training cites this paper.

DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:24:22.137431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6de70064-9924-4c14-83f4-7eebe1b6b2aa · inbound

Co-Evolving Policy Distillation cites this paper.

Co-Evolving Policy Distillation AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:24:22.137431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bb3aa539-f7b4-4b52-b501-bf34ab776043 · inbound

T$^2$PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning cites this paper.

T$^2$PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:24:22.137431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0172fdfd-c0ec-48e9-b8f6-0b3c487c0e46 · inbound

Safactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence cites this paper.

Safactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:24:22.137431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 60736719-82c0-4c9d-8720-03d335fe16cd · inbound

Safactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence cites this paper.

Safactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:24:22.137431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 09e56093-512c-44af-9d7f-df841e883179 · inbound

Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models cites this paper.

Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:24:22.137431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 25b28170-02ac-4885-9097-078af6c18838 · inbound

FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration cites this paper.

FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:24:22.137431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8d917e05-0452-4a23-8e23-8177d57a79de · inbound

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning cites this paper.

BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:24:22.137431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b8030e71-5ff6-48c6-a20b-9ad790b99e42 · inbound

Beyond Thinking: Imagining in 360$^\circ$ for Humanoid Visual Search cites this paper.

Beyond Thinking: Imagining in 360$^\circ$ for Humanoid Visual Search AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 45

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T14:24:22.137431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a2b86f5d-4b1c-425b-aac8-ef90ab2e10b3 · inbound

Position: Agentic AI System Is a Foreseeable Pathway to AGI cites this paper.

Position: Agentic AI System Is a Foreseeable Pathway to AGI AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 38

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T14:24:22.137431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 61174cbe-8304-48f5-95bc-82e7afc8816d · inbound

AIS: Adaptive Importance Sampling for Quantized RL cites this paper.

AIS: Adaptive Importance Sampling for Quantized RL AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:24:22.137431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f2ca8497-d292-4e85-b552-d7a97237461b · inbound

Diagnosing Training Inference Mismatch in LLM Reinforcement Learning cites this paper.

Diagnosing Training Inference Mismatch in LLM Reinforcement Learning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 48

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T14:24:22.137431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation da7d6f53-7e64-490d-be84-ca520310e3bc · inbound

ICRL: Learning to Internalize Self-Critique with Reinforcement Learning cites this paper.

ICRL: Learning to Internalize Self-Critique with Reinforcement Learning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 43

Resolution: metadata mismatch; local_arxiv, observed 2026-05-19T18:02:42.448329Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 83b5152c-cd27-45c1-90b1-7541046ec6ff · inbound

AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs cites this paper.

AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-20T20:13:43.758614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4f0699d7-5473-4da1-8a3b-44716b2409f2 · inbound

DynaTrain: Fast Online Parallelism Switching for Elastic LLM Training cites this paper.

DynaTrain: Fast Online Parallelism Switching for Elastic LLM Training AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:09:12.222518Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fe810c69-4791-45df-a5f5-e6c151d4e47a · inbound

ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning cites this paper.

ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-21T07:34:02.628850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 15a3adf2-8211-4f33-84b2-6124d127428b · inbound

ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning cites this paper.

ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-22T09:01:19.399223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation dd84ebee-5311-410b-a8cd-666e49a72249 · inbound

Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor cites this paper.

Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-21T07:59:50.046588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f6faf070-eb05-4ad1-8e18-b5aed790f443 · inbound

Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor cites this paper.

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-25T05:50:23.726282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 63abdda3-635c-4f93-b652-925b21489d17 · inbound

Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor cites this paper.

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-06-30T18:04:57.966303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 21bb12d9-3fbd-4aec-a1a0-8f5b899e1174 · inbound

Trust Region On-Policy Distillation cites this paper.

Trust Region On-Policy Distillation AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 237

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T20:56:13.542325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4c3d9624-528c-4dba-ba31-706b18038b2a · inbound

RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning cites this paper.

RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-07-01T21:16:13.397428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 912f1d9e-9ba2-49c2-a818-18da27152940 · inbound

AgentJet: A Distributed Swarm Training Framework for Agentic Reinforcement Learning cites this paper.

AgentJet: A Distributed Swarm Training Framework for Agentic Reinforcement Learning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-07-02T07:56:47.919524Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 00baaa07-cffa-4126-be70-b01ac06ab3a3 · inbound

AgentJet: A Distributed Swarm Training Framework for Agentic Reinforcement Learning cites this paper.

AgentJet: A Distributed Swarm Training Framework for Agentic Reinforcement Learning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-02T12:27:08.279842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 475c3c1b-5bec-4d66-b206-66aed008a67a · inbound

Rollout-Level Advantage-Prioritized Experience Replay for GRPO cites this paper.

Rollout-Level Advantage-Prioritized Experience Replay for GRPO AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-02T06:06:41.093107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 43f1bb11-1658-4ba3-8889-5204cecca945 · inbound

When RL Fails after SFT: Rejuvenating Model Plasticity for Robust SFT-to-RL Handoff cites this paper.

When RL Fails after SFT: Rejuvenating Model Plasticity for Robust SFT-to-RL Handoff AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 131

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T22:27:26.415608Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bf90f729-bc4c-4830-bad0-4c32d4ac6787 · inbound

Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning cites this paper.

Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 53

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T09:47:59.826024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e5c4347e-bbdf-42ec-b2c4-c64d284cef51 · inbound

Harnessing Routing Foresight for Micro-step-level MoE load balancing in RL Post-training cites this paper.

Harnessing Routing Foresight for Micro-step-level MoE load balancing in RL Post-training AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-07-03T13:08:07.825297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation aa490fe4-6ae8-453c-b334-d1b6aa5aa84f · inbound

Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale cites this paper.

Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 27

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T22:17:25.513987Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2dbde3c1-555d-477d-a89b-deda0b49132d · inbound

Spotlight: Synergizing Seed Exploration and Spot GPUs for DiT RL Post-Training cites this paper.

Spotlight: Synergizing Seed Exploration and Spot GPUs for DiT RL Post-Training AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-07-04T02:49:24.703409Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7b89e743-e38f-407b-b510-32c2ae4d4f9c · inbound

RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning cites this paper.

RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T14:39:58.209992Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5149cbf7-dd78-4fc9-8aef-3cc9b5dbac56 · inbound

RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning cites this paper.

RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-12T11:52:35.159984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1d0c60b-fe75-4399-b3b0-a1d287f2b334 · inbound

Retroactive Advantage Correction: Closed-Form V-Trace Bias Correction for Delay-Aware RLHF cites this paper.

Retroactive Advantage Correction: Closed-Form V-Trace Bias Correction for Delay-Aware RLHF AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 7

Resolution: malformed identifier; local_arxiv, observed 2026-06-29T05:43:07.654879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 32bec269-cf7f-47ad-a24a-e0b2e9c40ea8 · inbound

Trees from Marginals: Autoregressive drafting with factorized priors cites this paper.

Trees from Marginals: Autoregressive drafting with factorized priors AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-07-10T21:57:39.209960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d5e0de3a-0c46-403c-b27a-60b45309e067 · inbound

Trees from Marginals: Autoregressive drafting with factorized priors cites this paper.

Trees from Marginals: Autoregressive drafting with factorized priors AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-14T15:58:05.356765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92f02aa6-2291-45cd-95a5-382a9e360cfa · inbound

Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning cites this paper.

Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-07-09T08:56:06.428422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 55ea7ddb-1643-47ed-84ce-597ab67dd347 · inbound

Bidirectional Resource Scheduling for Disaggregated and Asynchronous RL Post-Training cites this paper.

Bidirectional Resource Scheduling for Disaggregated and Asynchronous RL Post-Training AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 5

Resolution: malformed identifier; no resolver link, observed 2026-07-13T04:42:35.589143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0bd608c-2077-4856-a6e6-5c3f70d9e353 · inbound

Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning cites this paper.

Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-02T06:37:37.177652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14b69ad0-a0c3-473e-83bb-8a8b6deaf7cf · inbound

WAR: Workload-Aware Rollouts for Synchronous Agentic Reinforcement Learning cites this paper.

WAR: Workload-Aware Rollouts for Synchronous Agentic Reinforcement Learning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T18:29:31.579850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f2db113-7f86-4a24-8845-7519a8acf1ce · inbound

Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning cites this paper.

Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T09:49:28.853734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cd5dede-04e4-47e8-a00a-115009c85765 · inbound

QLPO: Quadrant-weighted Sampling for Length-aware Policy Optimization cites this paper.

QLPO: Quadrant-weighted Sampling for Length-aware Policy Optimization AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T06:48:17.311342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a1c46ae-723a-478a-990e-bf9e9890cca4 · inbound

DynaResize: Runtime GPU Reallocation for Disaggregated LLM Post-Training cites this paper.

DynaResize: Runtime GPU Reallocation for Disaggregated LLM Post-Training AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T11:13:59.560465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.