Paper Citation Record · LEDGER

Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse

As of 6 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 1 inbound Pith citation observation for arXiv:2511.00413.

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

pith.paper-citation-record.v1
2511.00413 v5

Coverage vector

measured 20 of 20 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-18T02:04:46.559881Z

measured 21 of 21 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-28T16:43:39.796020Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-01T21:36:15.121485Z

Reference resolution

20 of 20 outbound references displayed

verified exact9
verified fuzzy0
unresolved1
parse uncertain0
malformed identifier0
metadata mismatch10

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 69ee9101-85a7-41ec-b5e9-ab6db935dfb8 · outbound

This paper cites an unresolved cited work.

Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-05-18T02:05:39.952946Z

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 3254e4a1-adac-4f35-867b-62da1df701c3 · outbound

This paper cites Knowledge-Centric Hallucination Detection.

Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse Knowledge-Centric Hallucination Detection

Reference 2

Resolution: metadata mismatch; doi, observed 2026-05-18T02:05:38.261554Z

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 4ad770f5-a54f-44a6-bebc-9e2d3413a7b8 · outbound

This paper cites One-Pass to Reason: Token Duplication and Block-Sparse Mask for Efficient Fine-Tuning on Multi-Turn Reasoning.

Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse One-Pass to Reason: Token Duplication and Block-Sparse Mask for Efficient Fine-Tuning on Multi-Turn Reasoning

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-18T02:05:39.082347Z

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 bc205017-7caf-4ec6-b1fc-0c19b7228b78 · outbound

This paper cites TreeRL: LLM Reinforcement Learning with On-Policy Tree Search.

Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse TreeRL: LLM Reinforcement Learning with On-Policy Tree Search

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-18T02:05:39.076738Z

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 f0f9bd3e-326e-4dfe-b339-97e330d529f3 · outbound

This paper cites Tree search for llm agent reinforcement learning.

Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse Tree search for llm agent reinforcement learning

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T02:05:39.126535Z

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 04f94907-8158-499b-bcb5-7729b579e4ff · outbound

This paper cites An LLM Compiler for Parallel Function Calling.

Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse An LLM Compiler for Parallel Function Calling

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-18T02:05:39.068282Z

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 f8880798-37da-44a6-9a62-48596e83e9bc · outbound

This paper cites TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling.

Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T02:05:39.041530Z

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 fb41e146-eb65-40a0-8374-c4c5404bf209 · outbound

This paper cites Prefix Grouper: Efficient GRPO Training through Shared-Prefix Forward.

Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse Prefix Grouper: Efficient GRPO Training through Shared-Prefix Forward

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-18T02:05:39.090776Z

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 4aa540f4-64bf-464e-bd6b-1700fed9f2f3 · outbound

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

Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse Agent Lightning: Train ANY AI Agents with Reinforcement Learning

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T02:05:39.048068Z

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 7cfdf13c-8ccb-4d51-8f88-f9f0ca7b2f26 · outbound

This paper cites MemGPT: Towards LLMs as Operating Systems.

Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse MemGPT: Towards LLMs as Operating Systems

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-18T02:05:39.139982Z

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 5b5bebc3-06fd-4ab5-a9f6-29afd0d72509 · outbound

This paper cites Efficiently Scaling Transformer Inference.

Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse Efficiently Scaling Transformer Inference

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T02:05:39.116323Z

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 358e0bb5-b56f-4ab7-91df-b8ce2596b5a0 · outbound

This paper cites Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving.

Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T02:05:39.054797Z

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 0e058099-7786-4f8e-b4b8-2b10601c829e · outbound

This paper cites FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision.

Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T19:45:36.571697Z

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 f88e571c-fdf6-42be-b873-dee90322ab84 · outbound

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

Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-18T02:05:39.096468Z

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 9559dbdd-1d70-426a-a7da-524ef6d051f1 · outbound

This paper cites Accelerating Direct Preference Optimization with Prefix Sharing.

Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse Accelerating Direct Preference Optimization with Prefix Sharing

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-18T02:05:39.028340Z

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 ce2a2c98-9b30-45ef-96ea-4f32e7e548aa · outbound

This paper cites FlashMask: Efficient and Rich Mask Extension of FlashAttention.

Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse FlashMask: Efficient and Rich Mask Extension of FlashAttention

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-18T02:05:39.102728Z

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 64625755-c28e-424f-a05a-bf8e743100f3 · outbound

This paper cites Qwen3 Technical Report.

Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse Qwen3 Technical Report

Reference 17

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T02:05:39.135299Z

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 a98a6fea-2b30-4400-bf46-14255b6516a9 · outbound

This paper cites Agentrl: Scaling agentic reinforcement learning with a multi-turn, multi-task framework.

Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse Agentrl: Scaling agentic reinforcement learning with a multi-turn, multi-task framework

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T02:05:39.110820Z

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 f8a5ece9-5208-426b-8cd1-e6cd58f46e49 · outbound

This paper cites MemoryBank: Enhancing Large Language Models with Long-Term Memory.

Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse MemoryBank: Enhancing Large Language Models with Long-Term Memory

Reference 19

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T02:05:39.121171Z

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 43c7aad6-49c0-49e6-906c-976e2360c91e · outbound

This paper cites SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks.

Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-18T02:05:39.034862Z

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 cd32c189-b334-4e74-9ba4-e89aa8e2a6ed · inbound

Schedule-Level Shared-Prefix Reuse for LLM RL Training cites this paper.

Schedule-Level Shared-Prefix Reuse for LLM RL Training Tree Training: Accelerating Agentic LLMs Training via Shared Prefix Reuse

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-07-01T21:36:15.122972Z

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.