Paper Citation Record · LEDGER

Agent Learning via Early Experience

As of 6 August 2026, this Paper Citation Record lists 90 of 90 outbound references and 34 inbound Pith citation observations for arXiv:2510.08558.

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

pith.paper-citation-record.v1
2510.08558 v3

Coverage vector

measured 90 of 90 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T10:48:06.310505Z

measured 124 of 124 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 34 of 34 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T20:51:46.531155Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-04T20:00:07.735443Z

Reference resolution

90 of 90 outbound references displayed

verified exact0
verified fuzzy0
unresolved90
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 98353674-d12e-4a05-9b5b-93480057539a · outbound

This paper cites write newline.

Agent Learning via Early Experience write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:56.506509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2957aec-e8bb-450f-b12c-e803e3d3c071 · outbound

This paper cites Hindsight experience replay.

Agent Learning via Early Experience Hindsight experience replay

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:56.584040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b25a9a5-87af-4259-8d5e-f356859708ed · outbound

This paper cites Bellemare, Yavar Naddaf, Joel Veness, and Michael Bowling.

Agent Learning via Early Experience Bellemare, Yavar Naddaf, Joel Veness, and Michael Bowling

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:56.723578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c5c6e16-f8aa-480a-8b1f-0177606aa294 · outbound

This paper cites A markovian decision process.

Agent Learning via Early Experience A markovian decision process

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:56.900269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4175b265-f9d7-46db-8d4c-520439f915c2 · outbound

This paper cites OpenAI Gym.

Agent Learning via Early Experience OpenAI Gym

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:57.125475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d74d271c-b12c-48de-8669-261eca641cb8 · outbound

This paper cites Web agents with world models: Learning and leveraging environment dynamics in web navigation.

Agent Learning via Early Experience Web agents with world models: Learning and leveraging environment dynamics in web navigation

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:57.297587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfdb7304-bb93-4667-b3a7-0c6d70eae062 · outbound

This paper cites Baker, Benjamin Burns, Daniel Adu-Ampratwum, Xuhui Huang, Xia Ning, Song Gao, Yu Su, and Huan Sun.

Agent Learning via Early Experience Baker, Benjamin Burns, Daniel Adu-Ampratwum, Xuhui Huang, Xia Ning, Song Gao, Yu Su, and Huan Sun

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:57.473817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12a48378-77dd-455d-a24a-6354db69e839 · outbound

This paper cites SFT memorizes, RL generalizes: A comparative study of foundation model post-training.

Agent Learning via Early Experience SFT memorizes, RL generalizes: A comparative study of foundation model post-training

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:57.646059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad1297fe-b9f7-4f4f-ba0b-5501da60cfaa · outbound

This paper cites TextWorld: A Learning Environment for Text-based Games.

Agent Learning via Early Experience TextWorld: A Learning Environment for Text-based Games

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:57.846696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2653aaf-fc4b-43a2-b890-73a02237e909 · outbound

This paper cites Mind2web: Towards a generalist agent for the web.

Agent Learning via Early Experience Mind2web: Towards a generalist agent for the web

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:58.076593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cf5a722-79ac-4f9f-8ef8-669cb43f5b89 · outbound

This paper cites Group-in-Group Policy Optimization for LLM Agent Training.

Agent Learning via Early Experience Group-in-Group Policy Optimization for LLM Agent Training

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:58.288029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eff87050-7876-4b69-8fe2-c579e4538ae1 · outbound

This paper cites o rg P. M \.

Agent Learning via Early Experience o rg P. M \

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:58.389893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8eee5330-96f6-42e4-ae48-9245f0c587ee · outbound

This paper cites Multimodal web navigation with instruction-finetuned foundation models.

Agent Learning via Early Experience Multimodal web navigation with instruction-finetuned foundation models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:58.507889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9989590c-175f-49ea-992e-207d1eca1144 · outbound

This paper cites Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Use.

Agent Learning via Early Experience Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Use

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:58.616326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba0c974f-6795-42e0-9cf5-2c226c5b8d20 · outbound

This paper cites Middleware for LLM s: Tools are instrumental for language agents in complex environments.

Agent Learning via Early Experience Middleware for LLM s: Tools are instrumental for language agents in complex environments

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:58.722164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc9ee8f5-43f0-4df3-b64b-4bbfb3ffbc5c · outbound

This paper cites Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents.

Agent Learning via Early Experience Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:58.803710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b71b2ef9-9321-4376-b30e-ba1d1a25f069 · outbound

This paper cites World modelling improves language model agents.

Agent Learning via Early Experience World modelling improves language model agents

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:58.908791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a0b34ad-cecb-4482-bde0-5e88ceebf935 · outbound

This paper cites Recurrent world models facilitate policy evolution.

Agent Learning via Early Experience Recurrent world models facilitate policy evolution

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:58.984749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af8199f1-020f-49a0-ad5c-a33eefcbce67 · outbound

This paper cites Dream to control: Learning behaviors by latent imagination.

Agent Learning via Early Experience Dream to control: Learning behaviors by latent imagination

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:59.064163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7771a86-7a17-41d6-b73d-c51000c17f49 · outbound

This paper cites Mastering atari with discrete world models.

Agent Learning via Early Experience Mastering atari with discrete world models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:59.153672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 697bf0e5-d2e2-4a84-9146-783fa9004246 · outbound

This paper cites Reasoning with language model is planning with world model.

Agent Learning via Early Experience Reasoning with language model is planning with world model

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:59.271600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8ccb03b-ca18-49d7-bd77-0c5a77f7c3b7 · outbound

This paper cites Constructing a multi-hop QA dataset for comprehensive evaluation of reasoning steps.

Agent Learning via Early Experience Constructing a multi-hop QA dataset for comprehensive evaluation of reasoning steps

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:59.356603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d738211a-229d-4dfd-89f8-ebc7e9b917bf · outbound

This paper cites Cogagent: A visual language model for gui agents.

Agent Learning via Early Experience Cogagent: A visual language model for gui agents

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:59.442881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e532730-8555-4857-adb8-7336787ffabb · outbound

This paper cites Lo RA : Low-rank adaptation of large language models.

Agent Learning via Early Experience Lo RA : Low-rank adaptation of large language models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:59.563349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a12b6eaf-3eaa-4498-85a3-211e024ce892 · outbound

This paper cites Large language models can self-improve.

Agent Learning via Early Experience Large language models can self-improve

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:59.628208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9fb40ad-a4c7-4db0-abcc-c85d8e6f6176 · outbound

This paper cites Large language models cannot self-correct reasoning yet.

Agent Learning via Early Experience Large language models cannot self-correct reasoning yet

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:59.739590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f9831e9-31c0-498d-9d39-748193f910c1 · outbound

This paper cites Imitation learning: A survey of learning methods.

Agent Learning via Early Experience Imitation learning: A survey of learning methods

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:59.850231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2230664e-8cdf-4292-b0e9-c4a75ac757bd · outbound

This paper cites Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning.

Agent Learning via Early Experience Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T10:47:59.970459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f383fb3-7639-41c5-a13b-9219a6a0639c · outbound

This paper cites Tree search for language model agents.

Agent Learning via Early Experience Tree search for language model agents

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:00.093999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e75f23f8-27ca-4f8e-ada5-ee995680f6ac · outbound

This paper cites VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents.

Agent Learning via Early Experience VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:00.216972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89bcbb31-2d78-4396-96d9-c9a9784ab24e · outbound

This paper cites Visualagentbench: Towards large multimodal models as visual foundation agents.

Agent Learning via Early Experience Visualagentbench: Towards large multimodal models as visual foundation agents

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:00.302101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ccca055-feba-4e1c-b71a-0bcc5d883f46 · outbound

This paper cites AAAR-1.0 : Assessing ai's potential to assist research.

Agent Learning via Early Experience AAAR-1.0 : Assessing ai's potential to assist research

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:00.416385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d809de26-f766-442d-8de4-5857bee8b53f · outbound

This paper cites Self-refine: Iterative refinement with self-feedback.

Agent Learning via Early Experience Self-refine: Iterative refinement with self-feedback

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:00.516077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc199b04-a244-4f96-aef2-b47fa26b334d · outbound

This paper cites Towards Enterprise-Ready Computer Using Generalist Agent.

Agent Learning via Early Experience Towards Enterprise-Ready Computer Using Generalist Agent

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:00.611698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ec18984-96b6-4bdd-8252-bc3c999efc12 · outbound

This paper cites Playing Atari with Deep Reinforcement Learning.

Agent Learning via Early Experience Playing Atari with Deep Reinforcement Learning

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:00.750900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9962b77-3bb7-4c3d-9324-d2f28e76cdfd · outbound

This paper cites Manning, Peter Shaw, Mandar Joshi, and Kenton Lee.

Agent Learning via Early Experience Manning, Peter Shaw, Mandar Joshi, and Kenton Lee

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:00.830638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0c7cdd5-2e0c-4548-a7bd-bfd721a933a8 · outbound

This paper cites Hello GPT-4o.

Agent Learning via Early Experience Hello GPT-4o

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:00.863967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 530fde74-325c-4b96-aa89-1e6bf4132b76 · outbound

This paper cites Explorer: Scaling exploration-driven web trajectory synthesis for multimodal web agents.

Agent Learning via Early Experience Explorer: Scaling exploration-driven web trajectory synthesis for multimodal web agents

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:00.989334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d7bfe75-1935-495c-8311-1e34cdf4b344 · outbound

This paper cites Gonzalez.

Agent Learning via Early Experience Gonzalez

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:01.121050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97e52afc-0f4c-4ddc-8fa1-f1cc9882ef00 · outbound

This paper cites Efficient training of artificial neural networks for autonomous navigation.

Agent Learning via Early Experience Efficient training of artificial neural networks for autonomous navigation

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:01.145663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c077b242-53db-460c-8a05-1ae325f6f53d · outbound

This paper cites APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay.

Agent Learning via Early Experience APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:01.215310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ad3072c-a31c-4410-a97a-a3b66aca7efe · outbound

This paper cites Measuring and narrowing the compositionality gap in language models.

Agent Learning via Early Experience Measuring and narrowing the compositionality gap in language models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:01.373304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 456f2f7e-ae95-44e5-9e90-486f0853b895 · outbound

This paper cites WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning.

Agent Learning via Early Experience WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:01.456515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccdb5895-460e-49b8-86f4-161f28e4bca2 · outbound

This paper cites Web RL : Training LLM web agents via self-evolving online curriculum reinforcement learning.

Agent Learning via Early Experience Web RL : Training LLM web agents via self-evolving online curriculum reinforcement learning

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:01.572095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c148590-0c74-4097-b064-dd4f7bd01825 · outbound

This paper cites ToolRL: Reward is All Tool Learning Needs.

Agent Learning via Early Experience ToolRL: Reward is All Tool Learning Needs

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:01.703082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ed98744-c594-4e95-a3ef-e39120147ab7 · outbound

This paper cites Efficient reductions for imitation learning.

Agent Learning via Early Experience Efficient reductions for imitation learning

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:01.808110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 757c5d10-939a-4b0f-a774-c3ba3b52b523 · outbound

This paper cites A reduction of imitation learning and structured prediction to no-regret online learning.

Agent Learning via Early Experience A reduction of imitation learning and structured prediction to no-regret online learning

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:01.923890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6213fdc4-694b-4f78-a163-f97a66536212 · outbound

This paper cites Russell and Peter Norvig.

Agent Learning via Early Experience Russell and Peter Norvig

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:02.019600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1508f2a-73e9-4c01-a470-a63425e73673 · outbound

This paper cites Learning from demonstration.

Agent Learning via Early Experience Learning from demonstration

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:02.138239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e94de37-0c24-4429-b499-ea7b959930a3 · outbound

This paper cites Mastering atari, go, chess and shogi by planning with a learned model.

Agent Learning via Early Experience Mastering atari, go, chess and shogi by planning with a learned model

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:02.267088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fbde27e-d5d1-45cc-9636-d31c2353c480 · outbound

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

Agent Learning via Early Experience DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:02.362478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdca6f21-046e-45d8-8633-062648eea9ac · outbound

This paper cites ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data.

Agent Learning via Early Experience ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:02.524137Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f42aa539-7284-44f0-a554-901f7a2cda1b · outbound

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

Agent Learning via Early Experience Hybridflow: A flexible and efficient RLHF framework

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:02.675594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1812c5e6-9304-4766-bd46-1c4853408aa5 · outbound

This paper cites Reflexion: language agents with verbal reinforcement learning.

Agent Learning via Early Experience Reflexion: language agents with verbal reinforcement learning

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:02.837901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fd6c576-536d-4126-bd9e-f9283fa589e1 · outbound

This paper cites \ ALFW \ orld: Aligning text and embodied environments for interactive learning.

Agent Learning via Early Experience \ ALFW \ orld: Aligning text and embodied environments for interactive learning

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:03.004397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1feac97-edcc-46e2-a979-39fd7f69520f · outbound

This paper cites Welcome to the era of experience.

Agent Learning via Early Experience Welcome to the era of experience

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:03.172498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b8fd965-3dc7-4c6b-ba68-64252683cef4 · outbound

This paper cites an unresolved cited work.

Agent Learning via Early Experience Unresolved cited work

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:03.334789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ba1141b-7b50-48ad-9600-db220049afaf · outbound

This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.

Agent Learning via Early Experience Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:03.340432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b04eb56-2391-4aa3-92c1-7eb63fc7a2cd · outbound

This paper cites Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments.

Agent Learning via Early Experience Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:03.400830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 151b51f2-7274-44eb-913e-345770543c78 · outbound

This paper cites Language agents: Foundations, prospects, and risks.

Agent Learning via Early Experience Language agents: Foundations, prospects, and risks

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:03.503938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e7712b4-add6-48df-bfec-d7f4a1c4338f · outbound

This paper cites Cognitive architectures for language agents.

Agent Learning via Early Experience Cognitive architectures for language agents

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:03.585571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24bfd7eb-7037-4ff1-beed-2e826f039d07 · outbound

This paper cites Dyna, an integrated architecture for learning, planning, and reacting.

Agent Learning via Early Experience Dyna, an integrated architecture for learning, planning, and reacting

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:03.678603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef3492e9-62a0-465f-bfc6-a83d847becb6 · outbound

This paper cites Reinforcement learning: An introduction, volume 1.

Agent Learning via Early Experience Reinforcement learning: An introduction, volume 1

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:03.815177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 569dcd57-83c3-4d2f-9560-8be2130be822 · outbound

This paper cites Efficient exploration in reinforcement learning.

Agent Learning via Early Experience Efficient exploration in reinforcement learning

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:03.913957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85ecd5f2-fb70-4812-b4f8-a81b1a283db2 · outbound

This paper cites Musique: Multihop questions via single-hop question composition.

Agent Learning via Early Experience Musique: Multihop questions via single-hop question composition

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:03.994776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e850cbe3-f015-4836-9abd-168ba02a1440 · outbound

This paper cites A pp W orld: A controllable world of apps and people for benchmarking interactive coding agents.

Agent Learning via Early Experience A pp W orld: A controllable world of apps and people for benchmarking interactive coding agents

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:04.039176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43b25c1d-9ebd-4f3c-92f7-3917f6a07cb9 · outbound

This paper cites Investigating the effectiveness of self-critiquing in LLM s solving planning tasks.

Agent Learning via Early Experience Investigating the effectiveness of self-critiquing in LLM s solving planning tasks

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:04.124786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a676dd61-4aa2-448b-a334-fd7efb8acd68 · outbound

This paper cites S cience W orld: Is your agent smarter than a 5th grader? In EMNLP, 2022.

Agent Learning via Early Experience S cience W orld: Is your agent smarter than a 5th grader? In EMNLP, 2022

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:04.197435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f2a474c-08e4-4498-84cb-d20a478138f9 · outbound

This paper cites RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning.

Agent Learning via Early Experience RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:04.269782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98925eb0-8367-487a-b990-c9f09c17d489 · outbound

This paper cites Chi, Quoc V.

Agent Learning via Early Experience Chi, Quoc V

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:04.282352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38eac46c-db24-4a9b-94de-e82e5d182901 · outbound

This paper cites Webagent-r1: Training web agents via end-to-end multi-turn reinforcement learning.

Agent Learning via Early Experience Webagent-r1: Training web agents via end-to-end multi-turn reinforcement learning

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:04.593498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6023e19f-39bf-4353-abe6-2e6596f65974 · outbound

This paper cites Simple statistical gradient-following algorithms for connectionist reinforcement learning.

Agent Learning via Early Experience Simple statistical gradient-following algorithms for connectionist reinforcement learning

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:04.792221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1411b88a-6749-4946-88a9-3403e3ec155d · outbound

This paper cites Cofca: A Step-Wise Counterfactual Multi-hop QA benchmark.

Agent Learning via Early Experience Cofca: A Step-Wise Counterfactual Multi-hop QA benchmark

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:04.961013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4db8f092-61da-40b1-9c5f-7c418823dd20 · outbound

This paper cites Agentgym: Evolving large language model-based agents across diverse environments, 2024.

Agent Learning via Early Experience Agentgym: Evolving large language model-based agents across diverse environments, 2024

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:05.133243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65b0b769-6f38-4193-ac6c-0f190fa8606b · outbound

This paper cites Travelplanner: A benchmark for real-world planning with language agents.

Agent Learning via Early Experience Travelplanner: A benchmark for real-world planning with language agents

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:05.227412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48915cd1-c204-4e3b-bbfe-a79248f6fab4 · outbound

This paper cites Revealing the barriers of language agents in planning.

Agent Learning via Early Experience Revealing the barriers of language agents in planning

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:05.371114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a79b1651-c840-418d-b89d-cf525982f3da · outbound

This paper cites Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments.

Agent Learning via Early Experience Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:05.486278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f3e55cf-1a28-4600-a8f1-b968b8a367fb · outbound

This paper cites An illusion of progress? assessing the current state of web agents.

Agent Learning via Early Experience An illusion of progress? assessing the current state of web agents

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:05.562175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c2919eb-8c15-4b23-84f5-4da8e101284e · outbound

This paper cites AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents.

Agent Learning via Early Experience AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:05.644648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e34bb7ec-7172-48f6-adf3-1207db33ba34 · outbound

This paper cites an unresolved cited work.

Agent Learning via Early Experience Unresolved cited work

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:05.700685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4409272e-f614-4508-b19e-fa60dc60919a · outbound

This paper cites Webshop: Towards scalable real-world web interaction with grounded language agents.

Agent Learning via Early Experience Webshop: Towards scalable real-world web interaction with grounded language agents

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:05.785257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73b3c26e-60a2-46f3-9889-5aaa862fcbe9 · outbound

This paper cites -bench: A benchmark for tool-agent-user interaction in real-world domains.

Agent Learning via Early Experience -bench: A benchmark for tool-agent-user interaction in real-world domains

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:05.865689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f266dc3d-a1f2-4fef-b678-82b3a8e7af4b · outbound

This paper cites Dyna-think: Synergizing reasoning, acting, and world model simulation in ai agents.

Agent Learning via Early Experience Dyna-think: Synergizing reasoning, acting, and world model simulation in ai agents

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:05.921855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d83ac179-c6d7-4aed-87f2-4fab3e267c79 · outbound

This paper cites an unresolved cited work.

Agent Learning via Early Experience Unresolved cited work

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:05.984194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3104a2ea-9b8c-4d5b-8d7b-ff0b2b0dfbba · outbound

This paper cites Breaking the Data Barrier -- Building GUI Agents Through Task Generalization.

Agent Learning via Early Experience Breaking the Data Barrier -- Building GUI Agents Through Task Generalization

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:06.046348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d831caac-22ec-405f-923d-a32db62dc671 · outbound

This paper cites Gpt-4v(ision) is a generalist web agent, if grounded.

Agent Learning via Early Experience Gpt-4v(ision) is a generalist web agent, if grounded

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:06.102772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a7caab8-8afd-4fbe-a471-f65565a268cb · outbound

This paper cites Llamafactory: Unified efficient fine-tuning of 100+ language models.

Agent Learning via Early Experience Llamafactory: Unified efficient fine-tuning of 100+ language models

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:06.154764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 351629a1-78ce-472e-8892-59e6e30e08f8 · outbound

This paper cites Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Tianyue Ou, Yonatan Bisk, Daniel Fried, Uri Alon, and Graham Neubig.

Agent Learning via Early Experience Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Tianyue Ou, Yonatan Bisk, Daniel Fried, Uri Alon, and Graham Neubig

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:06.206487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76755336-f839-4dc1-9ff6-32b58057e22b · outbound

This paper cites Self-Challenging Language Model Agents.

Agent Learning via Early Experience Self-Challenging Language Model Agents

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:06.257869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d1bf8f6-3fff-470c-890c-9c7287944595 · outbound

This paper cites Proposer-agent-evaluator ( PAE ): Autonomous skill discovery for foundation model internet agents.

Agent Learning via Early Experience Proposer-agent-evaluator ( PAE ): Autonomous skill discovery for foundation model internet agents

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-04T10:48:06.310505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 005f710f-f0b7-4ba8-93d4-6d9b46aacbdb · inbound

Agentic Learner with Grow-and-Refine Multimodal Semantic Memory cites this paper.

Agentic Learner with Grow-and-Refine Multimodal Semantic Memory Agent Learning via Early Experience

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-05-26T03:04:06.268577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation cd77b6ba-29ef-4761-a3df-410a882af35c · inbound

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL cites this paper.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Agent Learning via Early Experience

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-02T20:51:46.531155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f2e425a-fe2c-442f-885e-df90f2f18237 · inbound

UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics cites this paper.

UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics Agent Learning via Early Experience

Reference 55

Resolution: metadata mismatch; arxiv_id, observed 2026-05-26T03:04:06.268577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 444a7421-5b68-40d7-9059-f279b1d7d0b0 · inbound

Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering cites this paper.

Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering Agent Learning via Early Experience

Reference 187

Resolution: verified exact; arxiv_id, observed 2026-05-26T03:04:06.268577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fe2d8dea-1f92-4ae4-85f9-a56a5df9830a · inbound

Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memory cites this paper.

Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memory Agent Learning via Early Experience

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-26T03:04:06.268577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3f1b556f-f2c0-43a1-a866-0f3241e284fe · inbound

HEALing Entropy Collapse: Enhancing Exploration in Few-Shot RLVR via Hybrid-Domain Entropy Dynamics Alignment cites this paper.

HEALing Entropy Collapse: Enhancing Exploration in Few-Shot RLVR via Hybrid-Domain Entropy Dynamics Alignment Agent Learning via Early Experience

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-26T03:04:06.268577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0dd1f92d-876a-4411-bec9-2be34833247e · inbound

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration cites this paper.

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration Agent Learning via Early Experience

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-26T03:04:06.268577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 153fe713-d22d-4d3e-ac86-39b708db7566 · inbound

Meta-Tool: Efficient Few-Shot Tool Adaptation for Small Language Models cites this paper.

Meta-Tool: Efficient Few-Shot Tool Adaptation for Small Language Models Agent Learning via Early Experience

Reference 56

Resolution: verified exact; arxiv_id, observed 2026-05-26T03:04:06.268577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3d057f68-acd6-47f9-8821-ce5edd187112 · inbound

Reference-Sampled Boltzmann Projection for KL-Regularized RLVR: Target-Matched Weighted SFT, Finite One-Shot Gaps, and Policy Mirror Descent cites this paper.

Reference-Sampled Boltzmann Projection for KL-Regularized RLVR: Target-Matched Weighted SFT, Finite One-Shot Gaps, and Policy Mirror Descent Agent Learning via Early Experience

Reference 56

Resolution: metadata mismatch; arxiv_id, observed 2026-05-26T03:04:06.268577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8a99a819-e3fb-4fea-b322-17548c5d8b1e · inbound

Revisiting the Travel Planning Capabilities of Large Language Models cites this paper.

Revisiting the Travel Planning Capabilities of Large Language Models Agent Learning via Early Experience

Reference 20

Resolution: metadata mismatch; arxiv_id, observed 2026-05-26T03:04:06.268577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a2ffa417-7f58-4024-b852-e1740b3d2a91 · inbound

From History to State: Constant-Context Skill Learning for LLM Agents cites this paper.

From History to State: Constant-Context Skill Learning for LLM Agents Agent Learning via Early Experience

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-26T03:04:06.268577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 259159bf-eb49-4132-ae5e-a86900fc5214 · inbound

CASCADE: Case-Based Continual Adaptation for Large Language Models During Deployment cites this paper.

CASCADE: Case-Based Continual Adaptation for Large Language Models During Deployment Agent Learning via Early Experience

Reference 58

Resolution: metadata mismatch; arxiv_id, observed 2026-05-26T03:04:06.268577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 506667a1-1d5b-42e5-b27c-4c823f3c70ae · inbound

Learning Agent Routing From Early Experience cites this paper.

Learning Agent Routing From Early Experience Agent Learning via Early Experience

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-26T03:04:06.268577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b1e37e50-7213-4dcf-bc7e-a48be15f5573 · inbound

MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning cites this paper.

MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning Agent Learning via Early Experience

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-05-26T03:04:06.268577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5824f0ba-200a-4502-b3a7-fb0853273a85 · inbound

Differentiable Mixture-of-Agents Incentivizes Swarm Intelligence of Large Language Models cites this paper.

Differentiable Mixture-of-Agents Incentivizes Swarm Intelligence of Large Language Models Agent Learning via Early Experience

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-05-26T03:04:06.268577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 75a8d3bf-63a4-43c3-94b3-4b219e00150e · inbound

EXG: Self-Evolving Agents with Experience Graphs cites this paper.

EXG: Self-Evolving Agents with Experience Graphs Agent Learning via Early Experience

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-05-26T03:04:06.268577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 75cae065-4852-417b-95a3-afbc0306ca12 · inbound

ECHO: Terminal Agents Learn World Models for Free cites this paper.

ECHO: Terminal Agents Learn World Models for Free Agent Learning via Early Experience

Reference 22

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T15:04:46.503768Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6bdf2e05-4eb1-4d78-b2cd-0c719b5ca6bc · inbound

Enhancing LLM Metacognition via Cognitive Pairwise Training cites this paper.

Enhancing LLM Metacognition via Cognitive Pairwise Training Agent Learning via Early Experience

Reference 26

Resolution: metadata mismatch; local_arxiv, observed 2026-06-28T19:02:33.901234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 37c3835c-7587-45f3-b4da-08b33bfee284 · inbound

COMAP: Co-Evolving World Models and Agent Policies for LLM Agents cites this paper.

COMAP: Co-Evolving World Models and Agent Policies for LLM Agents Agent Learning via Early Experience

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-07-01T23:16:24.862123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2b94da71-ec1b-4c20-a2f3-7e81eab16ea4 · inbound

Policy and World Modeling Co-Training for Language Agents cites this paper.

Policy and World Modeling Co-Training for Language Agents Agent Learning via Early Experience

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-07-01T22:06:17.190939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a50be362-d665-487c-97ff-bf9f22e4c9cb · inbound

Demo2Tutorial: From Human Experience to Multimodal Software Tutorials cites this paper.

Demo2Tutorial: From Human Experience to Multimodal Software Tutorials Agent Learning via Early Experience

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:56:28.748387Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3a71f265-0b05-4144-be95-d1611ff72898 · inbound

Co-Evolving Skill Generation and Policy Optimization cites this paper.

Co-Evolving Skill Generation and Policy Optimization Agent Learning via Early Experience

Reference 54

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:57:25.878799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9768ab59-e63f-4f93-960e-6e66d8a2b11a · inbound

Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning cites this paper.

Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning Agent Learning via Early Experience

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-07-04T17:19:59.997876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b2d13abf-35c5-4890-858b-8701e787e150 · inbound

Qwen-AgentWorld: Language World Models for General Agents cites this paper.

Qwen-AgentWorld: Language World Models for General Agents Agent Learning via Early Experience

Reference 64

Resolution: verified exact; local_arxiv, observed 2026-07-04T17:09:59.206662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d66174e5-e55e-441c-b5d9-068dc173bb2d · inbound

Beyond Next-Observation Prediction: Agent-Authored World Modeling for Sequential Decision Making cites this paper.

Beyond Next-Observation Prediction: Agent-Authored World Modeling for Sequential Decision Making Agent Learning via Early Experience

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-07-04T19:40:06.177688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3290972a-195c-4a15-99e8-51fff462aead · inbound

The Interplay of Harness Design and Post-Training in LLM Agents cites this paper.

The Interplay of Harness Design and Post-Training in LLM Agents Agent Learning via Early Experience

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-07-04T20:00:07.736814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ae2fb3c1-9a00-4b39-8be2-a1a8dcfbdcba · inbound

Where Do CoT Training Gains Land in LLM based Agents? cites this paper.

Where Do CoT Training Gains Land in LLM based Agents? Agent Learning via Early Experience

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-07-04T13:49:51.529478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 197dc697-0f81-465f-92a4-03757ec2c530 · inbound

Internalizing the Future: A Unified Agentic Training Paradigm for World Model Planning cites this paper.

Internalizing the Future: A Unified Agentic Training Paradigm for World Model Planning Agent Learning via Early Experience

Reference 16

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T18:35:58.497615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 89fe5cae-e6f8-4568-bc91-c097dc38e617 · inbound

Self-Evolving World Models for LLM Agent Planning cites this paper.

Self-Evolving World Models for LLM Agent Planning Agent Learning via Early Experience

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-06-30T13:44:41.504930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 183b1700-f357-449a-a6ee-def7c82df27d · inbound

RSPO: Reward-Swap Policy Optimization for Multi-Turn LLM Agents cites this paper.

RSPO: Reward-Swap Policy Optimization for Multi-Turn LLM Agents Agent Learning via Early Experience

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-11T14:43:39.668059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f65c47cb-620b-48dc-b740-9488350328e6 · inbound

LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks cites this paper.

LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks Agent Learning via Early Experience

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T16:07:59.640364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6154c06e-df20-472c-a8ed-76a6620735ef · inbound

Scaling GUI Agents with Visual State Transitions cites this paper.

Scaling GUI Agents with Visual State Transitions Agent Learning via Early Experience

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-31T23:04:34.096442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae9ad3dd-80de-4d02-a865-45dbeccee357 · inbound

Bridging Compute- and Data-Optimal Pretraining cites this paper.

Bridging Compute- and Data-Optimal Pretraining Agent Learning via Early Experience

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-01T03:02:07.103981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d95d0b2-43f3-403f-98bf-6a6ec15cb62e · inbound

TAPO: Transition-Aware Policy Optimization for LLM Agents cites this paper.

TAPO: Transition-Aware Policy Optimization for LLM Agents Agent Learning via Early Experience

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-31T21:44:39.634912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.