Paper Citation Record · LEDGER

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning

As of 10 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2608.05080.

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

pith.paper-citation-record.v1
2608.05080 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T05:53:52.797095Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

33 of 33 outbound references displayed

verified exact4
verified fuzzy11
unresolved18
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a1297d76-745d-4ed0-b42b-eb4cdfa6d4eb · outbound

This paper cites Assumption C.6 is the stability condition connecting the controller analysis to policy optimization.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning Assumption C.6 is the stability condition connecting the controller analysis to policy optimization

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:53:54.435100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c5f83f90-9fa2-41f6-820a-a27d5847c104 · outbound

This paper cites EvolveRouter: Co-Evolving Routing and Prompt for Multi-Agent Question Answering.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning EvolveRouter: Co-Evolving Routing and Prompt for Multi-Agent Question Answering

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T05:53:52.726238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1ee55ea-e882-4ff7-b926-c5183599e476 · outbound

This paper cites Tree search for llm agent reinforcement learning.arXiv preprint arXiv:2509.21240,.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning Tree search for llm agent reinforcement learning.arXiv preprint arXiv:2509.21240,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T05:53:52.729206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b314d96-44a0-40c2-aeb1-33fb9af16d44 · outbound

This paper cites Understanding R1-Zero-Like Training: A Critical Perspective.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning Understanding R1-Zero-Like Training: A Critical Perspective

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T05:53:52.736354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b770c64f-c6f7-468a-9cce-d88cb13e5802 · outbound

This paper cites Adaptive rollout allocation for online reinforcement learning with verifiable rewards.arXiv preprint arXiv:2602.01601,.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning Adaptive rollout allocation for online reinforcement learning with verifiable rewards.arXiv preprint arXiv:2602.01601,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T05:53:52.739218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 824626db-cf8b-4f7e-b9ee-082df4fc9507 · outbound

This paper cites Group distribu- tionally robust optimization-driven reinforcement learning for llm reasoning.arXiv preprint arXiv:2601.19280,.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning Group distribu- tionally robust optimization-driven reinforcement learning for llm reasoning.arXiv preprint arXiv:2601.19280,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T05:53:52.741571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae3eb28e-29f0-4e35-8350-1a307876aa15 · outbound

This paper cites SAGE: Answer-Conditioned Uncertainty Targets for Verbal Uncertainty Alignment.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning SAGE: Answer-Conditioned Uncertainty Targets for Verbal Uncertainty Alignment

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-08-06T05:53:53.759426Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation edbb19bf-4184-4a46-a168-220e7f27a0d8 · outbound

This paper cites RAGEN-2: Reasoning Collapse in Agentic RL.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning RAGEN-2: Reasoning Collapse in Agentic RL

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T05:53:52.749306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc6ba695-5295-4b4a-98c2-932ca0d4c436 · outbound

This paper cites Entropy-tree: Tree-based decoding with entropy-guided exploration.arXiv preprint arXiv:2601.15296,.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning Entropy-tree: Tree-based decoding with entropy-guided exploration.arXiv preprint arXiv:2601.15296,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T05:53:52.751646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51a9fe03-06bf-4c44-97a5-a18e719450d7 · outbound

This paper cites Scaling search-augmented llm reasoning via adaptive information control.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning Scaling search-augmented llm reasoning via adaptive information control

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T05:53:52.753963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f92a6c1b-c9bd-48bf-adf1-9cb27978882d · outbound

This paper cites Wei Xiong, Chenlu Ye, Baohao Liao, Hanze Dong, Xinxing Xu, Christof Monz, Jiang Bian, Nan Jiang, and Tong Zhang.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning Wei Xiong, Chenlu Ye, Baohao Liao, Hanze Dong, Xinxing Xu, Christof Monz, Jiang Bian, Nan Jiang, and Tong Zhang

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T05:53:52.756198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ce64937-e1b1-4807-9fe5-06d152e115f9 · outbound

This paper cites Llms4all: A review of large language models across academic disciplines.arXiv preprint arXiv:2509.19580,.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning Llms4all: A review of large language models across academic disciplines.arXiv preprint arXiv:2509.19580,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T05:53:52.760835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 454f7f37-0091-4243-aba9-34b22322ce7d · outbound

This paper cites Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agents.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning Information Gain-based Rollout Policy Optimization: An Adaptive Tree-Structured Rollout Approach for Multi-Turn LLM Agents

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-08-06T05:53:52.858284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ae2f86d9-a61b-4345-84a8-11d2420ec17a · outbound

This paper cites Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T05:53:52.766149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8114cd00-53cd-4efb-baa9-9557b6121c75 · outbound

This paper cites First Return, Entropy-Eliciting Explore.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning First Return, Entropy-Eliciting Explore

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T05:53:52.768850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c837d4d8-8b63-4426-836d-dc3c6a75e150 · outbound

This paper cites TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-08-06T05:53:52.828977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6285bcc4-50ff-498e-ba5a-b8f4509aca7d · outbound

This paper cites APPENDIXCONTENTTABLE A Related Work 14 B Implementation Details and Additional Experiments 14 B.1 Benchmarks.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning APPENDIXCONTENTTABLE A Related Work 14 B Implementation Details and Additional Experiments 14 B.1 Benchmarks

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:53:54.495684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 98c29281-dc7e-47d9-bd71-bd471f03e792 · outbound

This paper cites While effective, these methods rely on final outcomes and thus overlook where uncertainty arises within multi-step reasoning.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning While effective, these methods rely on final outcomes and thus overlook where uncertainty arises within multi-step reasoning

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:53:54.486208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 179f783e-53a7-48e4-a01b-05041af08e16 · outbound

This paper cites IGRPO (Zhang et al., 2026a) instead expands trajectory trees according to information gain and derives an induced teacher distribution for policy optimization.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning IGRPO (Zhang et al., 2026a) instead expands trajectory trees according to information gain and derives an induced teacher distribution for policy optimization

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:53:54.476587Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5579dc2f-5b03-407a-aa6f-6c999df98cb7 · outbound

This paper cites The agent interacts with the environment through search, page navigation, item inspection, and purchase decisions.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning The agent interacts with the environment through search, page navigation, item inspection, and purchase decisions

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:53:54.466251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f2e637b2-b2c6-4298-b857-8367df30363e · outbound

This paper cites 1 n nX i=1 Acent i 2 # = n−1 n σ2 R,E.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning 1 n nX i=1 Acent i 2 # = n−1 n σ2 R,E

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:53:54.455291Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7821f00e-40cf-4b90-87a1-756e48fedc62 · outbound

This paper cites VIP provides a complementary gradient-level justification: under standard conditional i.i.d.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning VIP provides a complementary gradient-level justification: under standard conditional i.i.d

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:53:54.444522Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a362d1fe-9974-4424-9999-0d0a8dc5fddb · outbound

This paper cites The variation-budget literature motivates modeling policy-induced non-stationarity through the drift term DT (Besbes et al., 2014; 2015).

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning The variation-budget literature motivates modeling policy-induced non-stationarity through the drift term DT (Besbes et al., 2014; 2015)

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:53:54.426106Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bfbe4bae-8ba9-4e69-84e3-2c9c2da9f545 · outbound

This paper cites 42" rather than.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning 42" rather than

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:53:54.416795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b3529ecf-c5f6-4dd1-9817-c09442526626 · outbound

This paper cites name":"sql_query.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning name":"sql_query

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:53:54.405902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ed38e50f-78f7-4050-ac0c-0ba23b2eb645 · outbound

This paper cites Xiao Liu, Hao Yu, Hanchen Zhang, Yifan Xu, Xuanyu Lei, Hanyu Lai, Yu Gu, Hangliang Ding, Kaiwen Men, Kejuan Yang, et al.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning Xiao Liu, Hao Yu, Hanchen Zhang, Yifan Xu, Xuanyu Lei, Hanyu Lai, Yu Gu, Hangliang Ding, Kaiwen Men, Kejuan Yang, et al

Reference 2007

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T05:53:54.505043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b4b3596d-a445-4a55-a7dc-1030a185020b · outbound

This paper cites 3SPO: State-Score-Supervised Policy Optimization for LLM Agents.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning 3SPO: State-Score-Supervised Policy Optimization for LLM Agents

Reference 2011

Resolution: unresolved; no resolver link, observed 2026-08-06T05:53:52.723284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5835ec8-5613-4908-abb1-6a43d8d84e55 · outbound

This paper cites Temperature as a meta-policy: Adaptive temperature in llm reinforcement learning.arXiv preprint arXiv:2602.11779,.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning Temperature as a meta-policy: Adaptive temperature in llm reinforcement learning.arXiv preprint arXiv:2602.11779,

Reference 2015

Resolution: verified exact; raw_fallback, observed 2026-08-06T05:53:54.335868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 36e3614f-6bda-4940-aed6-f89bc3d6f519 · outbound

This paper cites Coba-rl: Capability-oriented budget allocation for reinforcement learning in llms.arXiv preprint arXiv:2602.03048,.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning Coba-rl: Capability-oriented budget allocation for reinforcement learning in llms.arXiv preprint arXiv:2602.03048,

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-06T05:53:52.758401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edb736c8-4c8a-407f-a756-b069625ef69e · outbound

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

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-06T05:53:52.744072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6b3308e-4fc6-48d8-8f73-733b20fd7814 · outbound

This paper cites Finite-time analysis of the multiarmed bandit problem.Machine learning, 47(2):235–256, 2002a.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning Finite-time analysis of the multiarmed bandit problem.Machine learning, 47(2):235–256, 2002a

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-06T05:53:52.711539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ef582f9-9263-4486-b582-b33393401d0b · outbound

This paper cites How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-06T05:53:52.720367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a96c60cf-83ce-48c8-a059-c68faa26629b · outbound

This paper cites Agentic entropy-balanced policy optimization.

Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning Agentic entropy-balanced policy optimization

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-06T05:53:52.717527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.