Paper Citation Record · LEDGER

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents

As of 7 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 2 inbound Pith citation observations for arXiv:2607.05378.

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

pith.paper-citation-record.v1
2607.05378 v1

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

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

measured 26 of 26 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T04:48:26.776852Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

24 of 24 outbound references displayed

verified exact11
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch13

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3e0b7f1f-21c6-4f78-b210-85ce19c6a25e · outbound

This paper cites Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs.

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-07-07T14:03:48.710553Z

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 a7927d0d-817a-4c0d-8243-53ec0a377332 · outbound

This paper cites LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding.

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-07T14:03:48.676493Z

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 2a288b75-3e56-455b-8f45-c710aa0c68be · outbound

This paper cites Longformer: The Long-Document Transformer.

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents Longformer: The Long-Document Transformer

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-07-07T14:03:48.664487Z

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 023bb951-e804-417d-9340-f44cace5c373 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-07-07T14:03:48.678559Z

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 045d7020-f785-4f0e-91f0-16c2aaa76866 · outbound

This paper cites GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models.

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-07-07T14:03:48.713654Z

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 e6123da0-4012-48b2-8d19-fb1ac55d7222 · outbound

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

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents TreeRL: LLM Reinforcement Learning with On-Policy Tree Search

Reference 6

Resolution: metadata mismatch; local_arxiv, observed 2026-07-07T14:03:48.459093Z

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 2aa56711-e4d4-46a5-8abe-be2e62d0cd56 · outbound

This paper cites LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression.

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-07-07T14:03:48.697410Z

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 55055d7b-fee2-4555-b94a-908aaff47fc9 · outbound

This paper cites Scaling llm multi-turn rl with end-to-end summarization-based context management.

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents Scaling llm multi-turn rl with end-to-end summarization-based context management

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-07-07T14:03:48.682914Z

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 c7ff7ccf-8645-4c87-8cde-57fa11fcedee · outbound

This paper cites Scaling llm multi-turn rl with end-to-end summarization-based context management.

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents Scaling llm multi-turn rl with end-to-end summarization-based context management

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-07-07T14:03:48.458893Z

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 df19cf28-7086-41d6-9002-eb6addeb02d7 · outbound

This paper cites Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces.

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

Reference 10

Resolution: metadata mismatch; local_arxiv, observed 2026-07-07T14:03:48.685877Z

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 2b84c590-9e9f-48f7-825e-ef3cd51ff423 · outbound

This paper cites MemGPT: Towards LLMs as Operating Systems.

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents MemGPT: Towards LLMs as Operating Systems

Reference 11

Resolution: metadata mismatch; local_arxiv, observed 2026-07-07T14:03:48.693835Z

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 e5c6f8f2-8623-4812-901f-ae9ee5edc6ad · outbound

This paper cites High-Dimensional Continuous Control Using Generalized Advantage Estimation.

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents High-Dimensional Continuous Control Using Generalized Advantage Estimation

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-07-07T14:03:48.693952Z

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 c193882f-a41e-4693-97d3-6eb68216b44c · outbound

This paper cites Proximal Policy Optimization Algorithms.

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents Proximal Policy Optimization Algorithms

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-07-07T14:03:48.700310Z

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 7b5a9f53-0e91-4fac-b2f2-5eeb8d8377a4 · outbound

This paper cites Proximal Policy Optimization Algorithms.

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents Proximal Policy Optimization Algorithms

Reference 14

Resolution: metadata mismatch; local_arxiv, observed 2026-07-07T14:03:48.455187Z

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 0cb92ccc-8750-4222-8b7b-396eba6f9d8e · outbound

This paper cites Scaling long-horizon llm agent via context-folding.

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents Scaling long-horizon llm agent via context-folding

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-07-07T14:03:48.700572Z

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 a8af86be-f3c9-4f83-8bdb-e65689f503f3 · outbound

This paper cites Solving math word problems with process- and outcome-based feedback.

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents Solving math word problems with process- and outcome-based feedback

Reference 16

Resolution: metadata mismatch; local_arxiv, observed 2026-07-07T14:03:48.666214Z

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 ac13f391-c494-4674-8ae9-2517d8748159 · outbound

This paper cites Resum: Unlocking long-horizon search intelligence via context summarization.

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents Resum: Unlocking long-horizon search intelligence via context summarization

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-07-07T14:03:48.707305Z

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 874c9524-eb42-4c89-a0bf-5b3db07e460b · outbound

This paper cites Resum: Unlocking long-horizon search intelligence via context summarization.

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents Resum: Unlocking long-horizon search intelligence via context summarization

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-07-07T14:03:48.448402Z

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 799b7099-f76b-4e41-8096-63bf8c3c7a98 · outbound

This paper cites Mobilerl: Online agentic reinforcement learning for mobile gui agents, 2025 a.

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents Mobilerl: Online agentic reinforcement learning for mobile gui agents, 2025 a

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-07-07T14:03:48.661263Z

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 9204ddb4-64b8-4377-918b-0875d07f1c33 · outbound

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

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 20

Resolution: metadata mismatch; local_arxiv, observed 2026-07-07T14:03:48.703852Z

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 6bbf5e80-5a18-4823-a0c3-2e3b10152ac7 · outbound

This paper cites What's Behind PPO's Collapse in Long-CoT? Value Optimization Holds the Secret.

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents What's Behind PPO's Collapse in Long-CoT? Value Optimization Holds the Secret

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-07-07T14:03:48.691291Z

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 b0504468-7755-4dd9-a45f-4f2ae2ccb475 · outbound

This paper cites What's Behind PPO's Collapse in Long-CoT? Value Optimization Holds the Secret.

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents What's Behind PPO's Collapse in Long-CoT? Value Optimization Holds the Secret

Reference 22

Resolution: metadata mismatch; local_arxiv, observed 2026-07-07T14:03:48.463323Z

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 fc0fbd2b-181a-47c9-86f7-6ca5775ab26b · outbound

This paper cites Group Sequence Policy Optimization.

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents Group Sequence Policy Optimization

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-07-07T14:03:48.705471Z

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 0a88d4ce-846d-43ce-9970-23ab6f4a0469 · outbound

This paper cites MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents.

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents

Reference 24

Resolution: metadata mismatch; local_arxiv, observed 2026-07-07T14:03:48.688465Z

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 881ff980-e98d-4b97-a9c8-8046ec27c3da · inbound

Where Facts Go Missing: A Layerwise Taxonomy and Per-Layer Attribution of Information Omission in Air-Gapped LLMAgent Pipelines cites this paper.

Where Facts Go Missing: A Layerwise Taxonomy and Per-Layer Attribution of Information Omission in Air-Gapped LLMAgent Pipelines CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T04:48:26.776852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50e24622-8465-421c-ac21-ea8a57905800 · inbound

AgentOmnia: Scaling Agentic Models for Full-Scenario Applications cites this paper.

AgentOmnia: Scaling Agentic Models for Full-Scenario Applications CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents

Reference 107

Resolution: unresolved; no resolver link, observed 2026-08-01T03:38:25.594637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.