Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T11:33:58.345391Z
Paper Citation Record · LEDGER
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
As of 17 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 30 inbound Pith citation observations for arXiv:2506.02177.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-15T17:19:46.719051Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-07-03T09:47:59.849796Z
Reference resolution
38 of 38 outbound references displayed
- verified exact0
- verified fuzzy8
- unresolved30
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation d9831c0c-05e7-4a31-a01c-0fbc8f226c97 · outbound
This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:53.422853Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0d8a338a-89e1-47db-ba73-d11448e44cda · outbound
This paper cites Training.Our method is implemented based on verl (Sheng et al.,.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts Training.Our method is implemented based on verl (Sheng et al.,
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:34:00.133936Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 23c8d49a-973f-49ee-95cc-884995a9bb2d · outbound
This paper cites On Designing Effective RL Reward at Training Time for LLM Reasoning.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts On Designing Effective RL Reward at Training Time for LLM Reasoning
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:54.037842Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f9c3030d-ccd9-4bcc-bafd-d5082f7d4ebe · outbound
This paper cites OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:54.160410Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1513ae04-df18-4551-b3b0-5004701717db · outbound
This paper cites Data-efficient finetuning using cross-task nearest neighbors.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts Data-efficient finetuning using cross-task nearest neighbors
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:34:01.140721Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 9b82e5ce-5627-4432-acbb-de0cc0225403 · outbound
This paper cites Large-Scale Data Selection for Instruction Tuning.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts Large-Scale Data Selection for Instruction Tuning
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:54.560575Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation aedd8de2-cdae-4679-b01c-fc73610148f5 · outbound
This paper cites VinePPO: Refining Credit Assignment in RL Training of LLMs.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts VinePPO: Refining Credit Assignment in RL Training of LLMs
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:54.702600Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 04d656e2-c62d-4612-92f6-7b1e770b01bd · outbound
This paper cites Let's Verify Step by Step.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts Let's Verify Step by Step
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:55.000411Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c30c30e7-a2a5-40f5-aa80-9eade33d7799 · outbound
This paper cites Understanding R1-Zero-Like Training: A Critical Perspective.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts Understanding R1-Zero-Like Training: A Critical Perspective
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:55.145743Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0f96e0ce-7823-441d-bc85-09fc21a62170 · outbound
This paper cites Enabling Weak LLMs to Judge Response Reliability via Meta Ranking.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts Enabling Weak LLMs to Judge Response Reliability via Meta Ranking
Reference 15
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:55.280113Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 281fdffb-7daf-4088-a06d-b603cad1e1f9 · outbound
This paper cites s1: Simple test-time scaling.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts s1: Simple test-time scaling
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:55.416178Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6d8283ee-dc53-42bc-bf0b-7e40a6c8fb88 · outbound
This paper cites Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:55.521985Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8325e58a-b228-4603-8f90-fa9d1df8c754 · outbound
This paper cites OpenAI o1 System Card.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts OpenAI o1 System Card
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:55.643161Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 58fd25b9-d2f3-4476-98de-d4e90c16c08c · outbound
This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:55.813166Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 10a3f3e9-9bb3-4dc5-aaa8-8ef6b83ed13e · outbound
This paper cites HybridFlow: A Flexible and Efficient RLHF Framework.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts HybridFlow: A Flexible and Efficient RLHF Framework
Reference 20
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:55.929448Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8bb4b8c2-2e6a-4fec-8a11-2d49ab3cd961 · outbound
This paper cites Kimi k1.5: Scaling Reinforcement Learning with LLMs.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts Kimi k1.5: Scaling Reinforcement Learning with LLMs
Reference 21
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:56.042626Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b7f103ad-20e3-4ede-b2fb-bba1a62b64ea · outbound
This paper cites A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce
Reference 23
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:56.370913Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f678aa86-9893-4cd6-8d94-f0914b3a7036 · outbound
This paper cites Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:56.534466Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 87883627-e99d-41f5-b282-cc9822319cae · outbound
This paper cites Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:56.659506Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 40fb4ab4-d45f-4e03-adc9-c5a196ab3651 · outbound
This paper cites LIMO: Less is More for Reasoning.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts LIMO: Less is More for Reasoning
Reference 26
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:56.783335Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 209e468b-62bb-4f5a-b75b-ea1eb0702bd0 · outbound
This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts DAPO: An Open-Source LLM Reinforcement Learning System at Scale
Reference 27
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:56.907899Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1871f2f7-c535-4ef7-9dcc-a2ad22c02ed6 · outbound
This paper cites VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks
Reference 28
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:57.031251Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0550c118-947f-459e-bfbe-4a6c265c01e0 · outbound
This paper cites SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM
Reference 29
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:57.154091Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation af96af09-a3de-4845-a58d-785ada5276b4 · outbound
This paper cites PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel
Reference 30
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:57.305024Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 39da3963-895b-4fa0-9746-a8b686108307 · outbound
This paper cites Coverage-centric coreset selection for high pruning rates.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts Coverage-centric coreset selection for high pruning rates
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:34:00.880737Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation b4b7d512-6da2-4e00-a08b-ae0adce931fb · outbound
This paper cites LLNL-affiliated authors were supported under Contract DE-AC52-07NA27344 and supported by the LLNL-LDRD Program under Project Nos.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts LLNL-affiliated authors were supported under Contract DE-AC52-07NA27344 and supported by the LLNL-LDRD Program under Project Nos
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:34:00.655878Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 9d4a53b0-6123-428b-ad5b-49517ad0fe3a · outbound
This paper cites We find that training on DAPO alone can degrade performance on LaTeX-based benchmarks, so we augment it with MATH to preserve formatting diversity and improve generalization.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts We find that training on DAPO alone can degrade performance on LaTeX-based benchmarks, so we augment it with MATH to preserve formatting diversity and improve generalization
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:34:00.370119Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 97e561c9-9c20-4a84-abea-f46fe94f1050 · outbound
This paper cites We use 4xH100 for Qwen2.5-Math-1.5B training and 8xH100 for Qwen2.5-Math-7B and DeepSeek-R1-Distill-Qwen-1.5B.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts We use 4xH100 for Qwen2.5-Math-1.5B training and 8xH100 for Qwen2.5-Math-7B and DeepSeek-R1-Distill-Qwen-1.5B
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:33:59.873088Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 7eafab92-670f-4b36-bd34-28395fb1569c · outbound
This paper cites an unresolved cited work.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts Unresolved cited work
Reference 37
- Resolution
- unresolved
- raw_fallback, observed 2026-08-07T11:33:59.357792Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 64209bf2-bcdd-4765-acb2-35b1ea20ce8e · outbound
This paper cites Safe RLHF: Safe Reinforcement Learning from Human Feedback.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts Safe RLHF: Safe Reinforcement Learning from Human Feedback
Reference 2017
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:53.510451Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8efec914-804d-416f-bbd1-df6fdc0ad840 · outbound
This paper cites We use β1 = 0.9, β2 = 0.999, and apply a weight decay of 0.01.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts We use β1 = 0.9, β2 = 0.999, and apply a weight decay of 0.01
Reference 2019
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:33:59.602692Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 2a05e5e0-9c29-4444-89dd-426e927ce2b7 · outbound
This paper cites Reinforcement Learning for Reasoning in Large Language Models with One Training Example.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts Reinforcement Learning for Reasoning in Large Language Models with One Training Example
Reference 2020
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:56.204875Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 078a963e-511f-47f7-90a5-90629883b038 · outbound
This paper cites REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization
Reference 2021
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:54.297876Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5c790190-4f4c-4b4f-a4a2-43d7f28d5c46 · outbound
This paper cites LIMR: Less is More for RL Scaling.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts LIMR: Less is More for RL Scaling
Reference 2022
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:54.876617Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5182579f-4527-4fea-820f-fafc04ade777 · outbound
This paper cites Active Preference Optimization for Sample Efficient RLHF.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts Active Preference Optimization for Sample Efficient RLHF
Reference 2023
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:53.628034Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation de08b487-e30d-48b1-90f0-2e748fca46e8 · outbound
This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Reference 2024
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:53.786117Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d5eb21f6-e440-4230-a022-5f7f5ebe07d1 · outbound
This paper cites Open r1: A fully open reproduction of deepseek-r1, January 2025.https://github.com/huggingface/open-r1.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts Open r1: A fully open reproduction of deepseek-r1, January 2025.https://github.com/huggingface/open-r1
Reference 2025
- Resolution
- unresolved
- no resolver link, observed 2026-08-07T11:33:53.916913Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9d935f1b-5438-49e7-a02b-8e5183d840bb · outbound
This paper cites We evaluate all models with temperature = 1 and repeat the test set 4 times for evaluation stability, i.e.,pass@1(avg@4), for all benchmarks.
Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts We evaluate all models with temperature = 1 and repeat the test set 4 times for evaluation stability, i.e.,pass@1(avg@4), for all benchmarks
Reference 8196
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-07T11:33:59.131928Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Pith citing papers
Observation d084dc3c-910a-4cbc-9535-8d8786694e82 · inbound
G$^2$RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance cites this paper.
G$^2$RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 51
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T17:19:46.719051Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b4d40336-1471-4269-b24f-77da40690d0f · inbound
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey cites this paper.
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 57
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T19:21:48.638499Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation db8baea6-a880-4384-a29e-9fd1060a96ae · inbound
LASER: A Data-Centric Method for Low-Cost and Efficient SQL Rewriting based on SQL-GRPO cites this paper.
LASER: A Data-Centric Method for Low-Cost and Efficient SQL Rewriting based on SQL-GRPO Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 49
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T07:16:02.195880Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 332989d2-bc58-4d9e-b58b-55c974b8e2be · inbound
MCPO: Mastery-Consolidated Policy Optimization for Large Reasoning Models cites this paper.
MCPO: Mastery-Consolidated Policy Optimization for Large Reasoning Models Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 33
- Resolution
- verified exact
- arxiv_id, observed 2026-05-10T07:06:52.840498Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 3644689d-62f7-4cea-8a5c-5ec10e9c720c · inbound
Cost-Aware Learning cites this paper.
Cost-Aware Learning Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 23
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T10:36:30.855968Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 920e3085-d9e2-44c6-a90f-4243e10ddbe6 · inbound
Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning cites this paper.
Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 184
- Resolution
- verified exact
- arxiv_id, observed 2026-05-10T23:15:49.463309Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation cb3b60b6-8cee-4536-9fa1-7a060ba2fb04 · inbound
Selective Rollout: Mid-Trajectory Termination for Multi-Sample Agent RL cites this paper.
Selective Rollout: Mid-Trajectory Termination for Multi-Sample Agent RL Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 9
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T16:41:09.059414Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 1bd91141-483c-4119-97cc-f75940b57616 · inbound
ROSE: Rollout On Serving GPUs via Cooperative Elasticity for Agentic RL cites this paper.
ROSE: Rollout On Serving GPUs via Cooperative Elasticity for Agentic RL Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 95
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T21:31:15.988767Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 99e4c427-1350-4aaa-bef3-db35fa1bc34b · inbound
ROSE: Rollout On Serving GPUs via Cooperative Elasticity for Agentic RL cites this paper.
ROSE: Rollout On Serving GPUs via Cooperative Elasticity for Agentic RL Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 94
- Resolution
- verified exact
- arxiv_id, observed 2026-05-21T08:39:53.200705Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation e8dfdb1f-37e0-4527-abcc-0816e3b30fcd · inbound
Gradient Extrapolation-Based Policy Optimization cites this paper.
Gradient Extrapolation-Based Policy Optimization Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 45
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T03:55:56.733368Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 56fe42d0-5d57-4e03-8d3e-2fa1432befd8 · inbound
Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States cites this paper.
Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 43
- Resolution
- verified exact
- arxiv_id, observed 2026-05-11T03:55:54.882249Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 1bb2620f-65b2-4965-a974-ffd22c58c6b1 · inbound
Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States cites this paper.
Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 43
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T06:41:45.835310Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation f86cb607-eed8-4ff2-a252-14fb94b01f17 · inbound
DUET: Optimize Token-Budget Allocation for Reinforcement Learning with Verifiable Rewards cites this paper.
DUET: Optimize Token-Budget Allocation for Reinforcement Learning with Verifiable Rewards Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 43
- Resolution
- malformed identifier
- arxiv_id, observed 2026-05-12T07:46:28.647091Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 12169cac-4b43-40bd-ae4d-62099273376f · inbound
DARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty Estimation cites this paper.
DARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty Estimation Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 61
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T03:16:19.327965Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 117727e2-7d6b-4893-9a70-1b6ea6b10b7a · inbound
Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning cites this paper.
Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 16
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T02:22:06.806520Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 39a0d34e-3e63-4bc3-b2c7-ecb5096dfb5c · inbound
AIS: Adaptive Importance Sampling for Quantized RL cites this paper.
AIS: Adaptive Importance Sampling for Quantized RL Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 26
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-15T03:14:52.595524Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 2bd94e0d-39a0-4977-a38e-91ea45ade716 · inbound
Learning from Language Feedback via Variational Policy Distillation cites this paper.
Learning from Language Feedback via Variational Policy Distillation Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 51
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-20T20:39:00.348750Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 72467af6-8d03-4f29-8f8f-1424b2767578 · inbound
AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs cites this paper.
AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 47
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-20T20:13:43.788110Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 942d9897-902c-48e5-9eb4-31e12c4ae2cd · inbound
Spend Your Rollouts Where It Counts: Rollout Allocation for Group-Based RL Post-Training cites this paper.
Spend Your Rollouts Where It Counts: Rollout Allocation for Group-Based RL Post-Training Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 22
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-06-29T19:53:55.782288Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 24f670bc-ea5d-4b7e-a474-bd4cdf87ed2c · inbound
On Effectiveness and Efficiency of Agentic Tool-calling and RL Training cites this paper.
On Effectiveness and Efficiency of Agentic Tool-calling and RL Training Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 32
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-06-29T08:43:15.361248Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation ba73a442-9db2-4e22-ab0a-1a24cbdae46a · inbound
RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning cites this paper.
RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 70
- Resolution
- malformed identifier
- arxiv_id, observed 2026-07-01T21:16:13.345991Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 4c242cd4-ec7c-43f0-901d-3edb7e28c52e · inbound
On Advantage Estimates for Max@K Policy Gradients cites this paper.
On Advantage Estimates for Max@K Policy Gradients Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 69
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-02T12:06:56.403920Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 9fe1ca1e-f844-438f-8466-60f0a59ecddc · inbound
AdaGRPO: A Capability-Aware Adaptive Enhancement for Flow-based GRPO cites this paper.
AdaGRPO: A Capability-Aware Adaptive Enhancement for Flow-based GRPO Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 30
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-02T16:17:08.917602Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 342d495b-9320-40ba-adb9-58a2db117d97 · inbound
CATPO: Critique-Augmented Tree Policy Optimization cites this paper.
CATPO: Critique-Augmented Tree Policy Optimization Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 16
- Resolution
- verified exact
- arxiv_id, observed 2026-07-02T21:47:28.013303Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 125b38d1-05be-4ade-bf2d-03ff4f6c5ced · inbound
N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization cites this paper.
N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 8
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-03T04:17:37.386022Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 1e5be0ca-5cbb-4df1-9a9e-4cb4ed65cca2 · inbound
Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning cites this paper.
Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 51
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-03T09:47:59.851250Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.
Observation 3ea09dec-71d9-4b2d-9af3-1544d52c4ef9 · inbound
Early Verdicts, Better Budgets: Sequential Adaptive Rollout Allocation for Compute-Efficient RLVR cites this paper.
Early Verdicts, Better Budgets: Sequential Adaptive Rollout Allocation for Compute-Efficient RLVR Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T00:29:00.908981Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 90c868fa-b460-46cc-b1cf-3190f1bd4b4e · inbound
Kalman Meets Curriculum: Efficient Dynamic Prompt Selection for Adaptive RL Finetuning cites this paper.
Kalman Meets Curriculum: Efficient Dynamic Prompt Selection for Adaptive RL Finetuning Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 82
- Resolution
- unresolved
- no resolver link, observed 2026-07-31T01:31:13.934392Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 79f0a914-cc9b-46b6-bf4d-f8132541aa86 · inbound
Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance cites this paper.
Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T00:22:11.829438Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2ac7fa79-d18f-4e95-83b3-d54f63cf1327 · inbound
PAIR: Pairwise-Aware Inclusion Reweighting for Adaptive Rollout Allocation in RLVR cites this paper.
PAIR: Pairwise-Aware Inclusion Reweighting for Adaptive Rollout Allocation in RLVR Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T14:22:55.603592Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.