Paper Citation Record · LEDGER

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

As of 20 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 31 inbound Pith citation observations for arXiv:2506.03106.

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

pith.paper-citation-record.v1
2506.03106 v7

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T11:15:35.267794Z

measured 63 of 63 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 31 of 31 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-11T23:11:38.110587Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-04T00:29:15.119817Z

Reference resolution

32 of 32 outbound references displayed

verified exact0
verified fuzzy19
unresolved11
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a579f800-b35c-4935-90c5-4a76dec37ed3 · outbound

This paper cites needle in a haystack.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback needle in a haystack

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:15:35.779353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8f534efd-4ea8-42f6-8d0b-09cda7837070 · outbound

This paper cites While the worst-case complexity remains dimT E(H, ℓ, ϵ)≈O(|S|L), the critique acts as a pruning signal.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback While the worst-case complexity remains dimT E(H, ℓ, ϵ)≈O(|S|L), the critique acts as a pruning signal

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:15:35.769972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b7ad4a6d-2136-4acf-a79a-1b4869b9c1c7 · outbound

This paper cites an unresolved cited work.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:15:35.690194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 90b9b898-9e89-4f9c-ac0c-dbff6c9078c9 · outbound

This paper cites Wang, Y ., Yue, X., and Chen, W.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback Wang, Y ., Yue, X., and Chen, W

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T11:15:35.170943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad29d770-e3e6-4bc6-877a-0c21c185e548 · outbound

This paper cites The correct maximum value, as derived from a proper analysis, should be 10 3.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback The correct maximum value, as derived from a proper analysis, should be 10 3

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:15:35.556971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ef39f899-e63f-45a1-b692-4364d4fae2ea · outbound

This paper cites Qwen3 Technical Report.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback Qwen3 Technical Report

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T11:15:35.178558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39b23d80-f7f2-4675-ad68-235586a58802 · outbound

This paper cites Zhang, X., Peng, B., Li, K., Zhou, J., and Meng, H.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback Zhang, X., Peng, B., Li, K., Zhou, J., and Meng, H

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T11:15:35.181921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d54d17d-9fa2-43c1-bf9a-a3de9d99d77a · outbound

This paper cites correct” and “incorrect.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback correct” and “incorrect

Reference 8

Resolution: malformed identifier; no resolver link, observed 2026-08-07T11:15:35.185214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f77a2b8-0532-498f-aa9c-3d95e421f3f1 · outbound

This paper cites As illustrated in Figure 8, this function is bounded between (0,1) , where x represents the token probability of the policy.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback As illustrated in Figure 8, this function is bounded between (0,1) , where x represents the token probability of the policy

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:15:35.789361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7ffef02b-96c2-48ce-a18e-b35fb89a5553 · outbound

This paper cites In this setting, the feedback function is simply the reward itself, fη(a) =r(a).

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback In this setting, the feedback function is simply the reward itself, fη(a) =r(a)

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:15:35.760582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f008ba4f-474c-4083-8873-e2fee8bd2e6d · outbound

This paper cites The probability of finding the unique optimal solution a∗ is equivalent to sampling the correct element from a set of sizedwithout replacement.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback The probability of finding the unique optimal solution a∗ is equivalent to sampling the correct element from a set of sizedwithout replacement

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:15:35.750597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1b7aa275-33cb-445b-9173-d95966e02ccb · outbound

This paper cites Since γ≪1 , the gradient magnitude is significantly dampened.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback Since γ≪1 , the gradient magnitude is significantly dampened

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:15:35.739780Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9f3ca082-9d4f-44c2-8694-c307e8481ab4 · outbound

This paper cites weaker refinement,.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback weaker refinement,

Reference 15

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T11:15:35.729061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 119a2374-8a19-4e5b-94a6-3c2f71405470 · outbound

This paper cites an unresolved cited work.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:15:35.708975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c9c10e5b-01ee-4e8c-9b10-4407e713a172 · outbound

This paper cites an unresolved cited work.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:15:35.699270Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7b28c74e-0063-4c28-baa5-b1582b90f90b · outbound

This paper cites Conclusion:.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback Conclusion:

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:15:35.680966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 459c337b-f614-44a2-b336-4b4a4742ad76 · outbound

This paper cites Calculate the cosine of the angle of the axial section of the cone at the vertex which is also the apex of the cone.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback Calculate the cosine of the angle of the axial section of the cone at the vertex which is also the apex of the cone

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:15:35.671451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b3b5fbd5-10bb-4732-bb84-ca5c18c21d16 · outbound

This paper cites Wait, let me check that again.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback Wait, let me check that again

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:15:35.661156Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 28757a41-8f8a-4084-a7b3-6f5e700fdf57 · outbound

This paper cites an unresolved cited work.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-07T11:15:35.651769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 13b69af0-af44-488c-b3ad-25abf3a3b693 · outbound

This paper cites Therefore, the exact value is − 9 100, and the approximate decimal is −0.09.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback Therefore, the exact value is − 9 100, and the approximate decimal is −0.09

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:15:35.632214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f59290c6-e1c1-4789-ab3b-44eb96d8ac3c · outbound

This paper cites Alternatively, if I think about angles: A is arcsin(0.4), which is in the first quadrant, B is arcsin(0.5) which is π/6, also first quadrant.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback Alternatively, if I think about angles: A is arcsin(0.4), which is in the first quadrant, B is arcsin(0.5) which is π/6, also first quadrant

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:15:35.621418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 93a02610-6565-4c74-b972-b2944de36dba · outbound

This paper cites Alternatively, using complex numbers or other methods? Maybe not necessary.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback Alternatively, using complex numbers or other methods? Maybe not necessary

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:15:35.610767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f43a9e87-3503-4e60-8d7d-88999f07724e · outbound

This paper cites The trigonometric substitution should be used more carefully, ensuring that the constraint is satisfied throughout.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback The trigonometric substitution should be used more carefully, ensuring that the constraint is satisfied throughout

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:15:35.600273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 38bb0bc3-ed9d-43a2-a587-2e083088dddc · outbound

This paper cites The identities used do not lead to a valid simplification of the expression.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback The identities used do not lead to a valid simplification of the expression

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:15:35.589374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1857b7b4-4f3e-4372-939d-e47bc3240fc5 · outbound

This paper cites The derivative should be taken with respect to the correct variables, and the critical points should be found accurately.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback The derivative should be taken with respect to the correct variables, and the critical points should be found accurately

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:15:35.579589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 47df313b-3674-4c95-a2a8-6db297b6c724 · outbound

This paper cites The values chosen fora,b, andcdo not satisfy the constraintabc+a+c=b.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback The values chosen fora,b, andcdo not satisfy the constraintabc+a+c=b

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:15:35.568539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fe9f3e00-79b7-48ae-8afb-028fe77f3064 · outbound

This paper cites Therefore, the value of the original expression is −9 100.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback Therefore, the value of the original expression is −9 100

Reference 100

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:15:35.641688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9a8caf7d-b4f7-4f1e-96d6-2abf3d3b9665 · outbound

This paper cites Wait,.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback Wait,

Reference 150

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T11:15:35.718737Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 25931b4a-6bc6-4e11-96a3-e127664f2d9a · outbound

This paper cites Training language models to follow instructions with human feedback.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback Training language models to follow instructions with human feedback

Reference 155

Resolution: unresolved; no resolver link, observed 2026-08-07T11:15:35.163327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ffcab6a-b67c-4d0d-9558-9ec2d5b83103 · outbound

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

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-07T11:15:35.167088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d350a58a-8bf7-4c42-8595-7e3dbfa237f4 · outbound

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

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback Understanding R1-Zero-Like Training: A Critical Perspective

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-07T11:15:35.158495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45364875-fb18-435c-8de7-197aa7aacc8a · outbound

This paper cites Learning to Reason under Off-Policy Guidance.

Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback Learning to Reason under Off-Policy Guidance

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T11:15:35.175237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation ef08bf37-6769-454f-b0b7-bcb326090e57 · inbound

Video-R1: Reinforcing Video Reasoning in MLLMs cites this paper.

Video-R1: Reinforcing Video Reasoning in MLLMs Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-06-09T02:06:03.715193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 890f6533-5d3c-4937-8e75-fd63a407581d · inbound

MoL-RL: Distilling Multi-Step Environmental Feedback into LLMs for Feedback-Independent Reasoning cites this paper.

MoL-RL: Distilling Multi-Step Environmental Feedback into LLMs for Feedback-Independent Reasoning Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T13:47:19.009023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5df3f36-6a6e-4d02-a269-d7f95777e969 · inbound

CLPO: Curriculum Learning meets Policy Optimization for LLM Reasoning cites this paper.

CLPO: Curriculum Learning meets Policy Optimization for LLM Reasoning Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T13:53:36.062617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a04af6ba-5ecc-4578-9d72-008d996753aa · inbound

XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation cites this paper.

XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T11:11:12.915233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27f1b512-88a9-4cbb-929a-98e9068fa0ce · inbound

TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance cites this paper.

TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-04T10:53:10.877236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83044b5c-6cf1-4702-a64e-c12687fbd697 · inbound

OneThinker: All-in-one Reasoning Model for Image and Video cites this paper.

OneThinker: All-in-one Reasoning Model for Image and Video Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-06-09T02:06:03.715193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9af02442-d983-4e7b-b991-45aa307c7da0 · inbound

AdaTooler-V: Adaptive Tool-Use for Images and Videos cites this paper.

AdaTooler-V: Adaptive Tool-Use for Images and Videos Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 80

Resolution: verified exact; arxiv_id, observed 2026-06-09T02:06:03.715193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3baccb9b-70e2-4b70-be63-a0c3d0af0ffd · inbound

AdvJudge-Zero: Binary Decision Flips in LLM-as-a-Judge via Adversarial Control Tokens cites this paper.

AdvJudge-Zero: Binary Decision Flips in LLM-as-a-Judge via Adversarial Control Tokens Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-03T15:21:55.984824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fcaacfb-fa23-4a17-aee4-351c5a09750b · inbound

CPMobius: Iterative Coach-Player Reasoning for Data-Free Reinforcement Learning cites this paper.

CPMobius: Iterative Coach-Player Reasoning for Data-Free Reinforcement Learning Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-03T05:14:22.180784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00596522-fd42-4123-951a-941771bc4d7c · inbound

Gen-Searcher: Reinforcing Agentic Search for Image Generation cites this paper.

Gen-Searcher: Reinforcing Agentic Search for Image Generation Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-06-09T02:06:03.715193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 61bce089-f9ff-404c-b03d-b31eef3ffdeb · inbound

Gen-Searcher: Reinforcing Agentic Search for Image Generation cites this paper.

Gen-Searcher: Reinforcing Agentic Search for Image Generation Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-06-09T02:06:03.715193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 266e7451-b303-4c0b-a695-4a57d85bcf95 · inbound

Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning cites this paper.

Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 106

Resolution: verified exact; arxiv_id, observed 2026-06-09T02:06:03.715193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 11c880c2-cb3d-4c40-8b8a-947b0597696c · inbound

Hidden States Know Where Reasoning Diverges: Credit Assignment via Span-Level Wasserstein Distance cites this paper.

Hidden States Know Where Reasoning Diverges: Credit Assignment via Span-Level Wasserstein Distance Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-06-09T02:06:03.715193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0be93c8b-7545-4a9b-938e-05314ec92922 · inbound

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning cites this paper.

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 92

Resolution: metadata mismatch; arxiv_id, observed 2026-06-09T02:06:03.715193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 48110f5b-b2ff-4350-abed-0302f3f83bdf · inbound

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning cites this paper.

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 92

Resolution: metadata mismatch; arxiv_id, observed 2026-06-09T02:06:03.715193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 49fb552d-fa19-4b23-9a97-b8ac7eeb583e · inbound

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning cites this paper.

Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 92

Resolution: metadata mismatch; arxiv_id, observed 2026-06-09T02:06:03.715193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c92ccc7a-cd02-4fe1-bf07-cb4b694efa8a · inbound

The Cancellation Hypothesis in Critic-Free RL: From Outcome Rewards to Token Credits cites this paper.

The Cancellation Hypothesis in Critic-Free RL: From Outcome Rewards to Token Credits Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-06-09T02:06:03.715193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 88a1d0f1-93d7-4601-875a-9bc7a2fa9e35 · inbound

Multi-Rollout On-Policy Distillation via Peer Successes and Failures cites this paper.

Multi-Rollout On-Policy Distillation via Peer Successes and Failures Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 38

Resolution: metadata mismatch; arxiv_id, observed 2026-06-09T02:06:03.715193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1079fdf3-9892-4d3b-833e-04649fba1d4d · inbound

ICRL: Learning to Internalize Self-Critique with Reinforcement Learning cites this paper.

ICRL: Learning to Internalize Self-Critique with Reinforcement Learning Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 22

Resolution: metadata mismatch; arxiv_id, observed 2026-06-09T02:06:03.715193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 655f3118-46d8-4a0a-bbeb-1c7b7de284f2 · inbound

PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization cites this paper.

PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-06-09T02:06:03.715193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 257ced7d-efc5-48ce-92a7-13ba8301d3d2 · inbound

PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization cites this paper.

PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T02:23:32.244687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 903fc1e0-9e56-49c6-8d49-e5453ff4554e · inbound

ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning cites this paper.

ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-06-09T02:06:03.715193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0b8c0dfe-6fa1-4a06-81dd-689eda059d4e · inbound

STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning cites this paper.

STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-06-09T02:06:03.715193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 83749c53-f9af-400e-8a4e-5f7b7a0b53fd · inbound

Reinforcing Human Behavior Simulation via Verbal Feedback cites this paper.

Reinforcing Human Behavior Simulation via Verbal Feedback Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 79

Resolution: metadata mismatch; arxiv_id, observed 2026-06-09T02:06:03.715193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2c37c286-2716-4642-a16e-14e9f9a86d98 · inbound

RL with Learnable Textual Feedback: A Bilevel Approach cites this paper.

RL with Learnable Textual Feedback: A Bilevel Approach Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-06-30T14:44:45.361285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 48d2b711-066b-41b2-9cc9-1acf83b95f91 · inbound

Credit Assignment with Resets in Language Model Reasoning cites this paper.

Credit Assignment with Resets in Language Model Reasoning Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-06-29T21:53:59.255224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 660eefdb-b031-4778-b04d-c84b18bac9e8 · inbound

Trust Region On-Policy Distillation cites this paper.

Trust Region On-Policy Distillation Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 189

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T20:56:13.705760Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5fe53e6d-5bfa-441c-8a6d-0c93514215e6 · inbound

REVES: REvision and VErification--Augmented Training for Test-Time Scaling cites this paper.

REVES: REvision and VErification--Augmented Training for Test-Time Scaling Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 76

Resolution: verified exact; local_arxiv, observed 2026-07-04T00:29:15.122126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c34e7e5f-a8a7-40f4-b444-3fab060e95ae · inbound

Agent Reinforcement Learning via Pivotal-Aware Self-Feedback Retry cites this paper.

Agent Reinforcement Learning via Pivotal-Aware Self-Feedback Retry Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-12T00:33:06.488657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 483e6977-b08e-4d13-b184-6573aeae10e3 · inbound

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

LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T16:07:59.623378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe2f8e82-8e4d-4241-9d0c-09b7c8812357 · inbound

RISE-RL: Rubric-Informed Selective Exploration for Open-Ended Reinforcement Learning cites this paper.

RISE-RL: Rubric-Informed Selective Exploration for Open-Ended Reinforcement Learning Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T23:11:38.110587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.