ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning | Paper Citation Record

Observation 71316cb8-5dfe-4eca-aeb6-84068d6591a4 · outbound

This paper cites an unresolved cited work.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-05T04:53:14.524151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a6cd4b45-4225-435a-9331-cba37575e76f · outbound

This paper cites DAPO: An open-source LLM reinforcement learning system at scale.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning DAPO: An open-source LLM reinforcement learning system at scale

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:53:14.503525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8dd9ea9a-6b98-4d28-9433-78731f14513b · outbound

This paper cites CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Process.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Process

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T04:53:12.942968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9f173e5-5435-4412-8d60-8680b15edc49 · outbound

This paper cites Loong: Synthesize long chain-of-thoughts at scale through verifiers, 2025.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Loong: Synthesize long chain-of-thoughts at scale through verifiers, 2025

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:53:14.484558Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 676f668a-52ec-46bb-8205-8d92a83901b9 · outbound

This paper cites Reinforcement mid-training, 2025.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Reinforcement mid-training, 2025

Reference 5

Resolution: verified exact; raw_fallback, observed 2026-08-05T04:53:13.931848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 44f0d7fa-e63b-4d3f-95ab-b22290f112a8 · outbound

This paper cites Self-evolving multi-agent systems via textual backpropagation.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Self-evolving multi-agent systems via textual backpropagation

Reference 6

Resolution: verified exact; doi, observed 2026-08-05T04:53:13.269181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 67a31706-7647-441c-8dc1-7555dd841db5 · outbound

This paper cites On-policy distillation.Thinking Machines Lab: Connectionism,.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning On-policy distillation.Thinking Machines Lab: Connectionism,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T04:53:12.967025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08623710-4d5f-4471-9ed1-b85223d145b3 · outbound

This paper cites EchoRL: Reinforcement learning via rollout echoing.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning EchoRL: Reinforcement learning via rollout echoing

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:53:14.431786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 52a20fe1-d4db-4942-bd10-d5997539c958 · outbound

This paper cites Learning to reason under off-policy guidance.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Learning to reason under off-policy guidance

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:53:14.403651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b0ef0794-26c1-4934-9d36-ef04fc58c1de · outbound

This paper cites Ozdaglar.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Ozdaglar

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:53:14.384926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b85e76e7-0456-4d29-bc9a-c56812d5dcb0 · outbound

This paper cites Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T04:53:12.991139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e10b2e6-8c8f-44a6-aa55-41da810147f7 · outbound

This paper cites The Lessons of Developing Process Reward Models in Mathematical Reasoning.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning The Lessons of Developing Process Reward Models in Mathematical Reasoning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T04:53:12.995759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed2e493a-78a5-41cf-b3d3-c6115491da56 · outbound

This paper cites Measuring mathematical problem solving with the MATH dataset.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Measuring mathematical problem solving with the MATH dataset

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-05T04:53:13.000441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3f5af37-516a-4256-a71d-ad4ed9033892 · outbound

This paper cites Solving quantitative reasoning problems with lan- guagemodels.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Solving quantitative reasoning problems with lan- guagemodels

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:53:14.356660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9a4ab40e-1c4d-42b2-abc4-82df9bd4935a · outbound

This paper cites OlympiadBench: A challenging benchmark for promoting AGI with olympiad-level bilingual multimodal scientific problems.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning OlympiadBench: A challenging benchmark for promoting AGI with olympiad-level bilingual multimodal scientific problems

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T04:53:13.009142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 459ab9fd-1d12-4713-a675-b2c08aa7424b · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-05T04:53:13.014357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1112e77e-80b2-45ad-b511-b36b7e5fab67 · outbound

This paper cites an unresolved cited work.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-05T04:53:13.019460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efe2d354-b221-4331-b963-3c3aa75c560c · outbound

This paper cites MMLU-pro: A more robust and challenging multi-task language understanding 12 benchmark.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning MMLU-pro: A more robust and challenging multi-task language understanding 12 benchmark

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:53:14.319942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8f65f649-835a-4863-9ab0-ad4026eaee28 · outbound

This paper cites SimpleRL-zoo: Investigating and taming zero reinforcement learning for open base models in the wild.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning SimpleRL-zoo: Investigating and taming zero reinforcement learning for open base models in the wild

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:53:14.303448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6ebc4b3a-56c6-45b5-84ad-3dcc8aa093ca · outbound

This paper cites Open- reasoner-zero: An open source approach to scaling up reinforcement learning on the base model.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Open- reasoner-zero: An open source approach to scaling up reinforcement learning on the base model

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:53:14.286659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b6cf11d9-1ffb-4e6d-b7ca-4fd5826cd031 · outbound

This paper cites Process reinforcement through implicit rewards.Transactions on Machine Learning Research,.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Process reinforcement through implicit rewards.Transactions on Machine Learning Research,

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:53:14.268959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation db9f4ef3-9ecd-428d-9fed-a5df98748910 · outbound

This paper cites Qwen2.5 Technical Report.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Qwen2.5 Technical Report

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T04:53:13.046874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e59e571-48aa-4a9a-8545-fbb844e7488b · outbound

This paper cites The Llama 3 Herd of Models.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning The Llama 3 Herd of Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T04:53:13.051552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c97db0fe-842d-4390-928a-c1a0eee4a97a · outbound

This paper cites Think outside the policy: In-context steered policy optimization.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Think outside the policy: In-context steered policy optimization

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:53:14.237674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f4754bd8-ebb5-4826-81cc-08f8df5b9e12 · outbound

This paper cites SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T04:53:13.062069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6f71012-67b5-4f5f-8950-493008b635b8 · outbound

This paper cites When More is Less: Understanding Chain-of-Thought Length in LLMs.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning When More is Less: Understanding Chain-of-Thought Length in LLMs

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T04:53:13.066820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4113cf82-1aa0-4f83-a1e1-30163a41d3b3 · outbound

This paper cites Don’t overthink it.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Don’t overthink it

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:53:14.220813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation aa62ebab-5ecd-4e67-913b-e590d9786438 · outbound

This paper cites LLaVA steering: Visual instruction tuning with 500x fewer parameters through modality linear representation- steering.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning LLaVA steering: Visual instruction tuning with 500x fewer parameters through modality linear representation- steering

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:53:14.199622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 00d862b3-3b99-465b-8966-3f520b032d86 · outbound

This paper cites PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-05T04:53:13.081608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11290c47-93f1-4ba8-a121-b8c902397195 · outbound

This paper cites Beyond nl2code: A structured survey of multimodal code intelligence,.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Beyond nl2code: A structured survey of multimodal code intelligence,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:53:14.169785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3cf0b7a4-e5fd-4080-a050-efd75a89652f · outbound

This paper cites SPOT! Revisiting Video-Language Models for Event Understanding.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning SPOT! Revisiting Video-Language Models for Event Understanding

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-05T04:53:13.101410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d02da753-95da-47eb-86c2-22a74beb1c38 · outbound

This paper cites Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsing.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsing

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-08-05T04:53:13.646604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 614957f0-49a5-4284-9ca1-8e36fb0678d9 · outbound

This paper cites an unresolved cited work.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-05T04:53:13.086535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation caefa43e-66b5-448b-9654-1b652cf39833 · outbound

This paper cites KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-05T04:53:13.116166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 641dc76e-2364-4908-a5ea-84cbcf94c2f3 · outbound

This paper cites Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-08-05T04:53:13.690777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f9a3aeed-c64c-4e64-a40c-744ce16e7669 · outbound

This paper cites Aditya Prakash, Yizhou Sun, and Wei Wang.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Aditya Prakash, Yizhou Sun, and Wei Wang

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-05T04:53:13.125098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd29fcac-7c1b-45c6-bf24-4b2c68e8208f · outbound

This paper cites HYPERION: Fine-grained hypersphere alignment for robust federated graph learning.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning HYPERION: Fine-grained hypersphere alignment for robust federated graph learning

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:53:14.154663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 86e77089-5ef2-4b20-ad58-6bfb328ad5cc · outbound

This paper cites Alignsae: Concept-aligned sparse autoencoders, 2026.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Alignsae: Concept-aligned sparse autoencoders, 2026

Reference 38

Resolution: verified exact; raw_fallback, observed 2026-08-05T04:53:13.621870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bf1166f2-560f-4ee7-86c6-b287bfd71e1e · outbound

This paper cites Can visual input be compressed? a visual token compression benchmark for large multimodal models, 2025.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Can visual input be compressed? a visual token compression benchmark for large multimodal models, 2025

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-05T04:53:13.138245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33ee0171-b0d2-45d6-a8c8-35bc4f89def1 · outbound

This paper cites Ascd: Attention-steerable contrastive decoding for reducing hallucination in mllm.Proceedings of the AAAI Conference on Artificial Intelligence, 40(12): 10306–10314, Mar.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Ascd: Attention-steerable contrastive decoding for reducing hallucination in mllm.Proceedings of the AAAI Conference on Artificial Intelligence, 40(12): 10306–10314, Mar

Reference 40

Resolution: verified exact; doi, observed 2026-08-05T04:53:13.238886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9f59fc7c-c5ff-4cb9-9a09-f4498dc40694 · outbound

This paper cites Let’s verify step by step.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Let’s verify step by step

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:53:14.121834Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7480c158-ceb8-4a12-b726-2534a5dde6e2 · outbound

This paper cites Star: Bootstrapping reasoning with reasoning.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Star: Bootstrapping reasoning with reasoning

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-05T04:53:13.152614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f23d5009-9e53-4424-922c-c96b54579004 · outbound

This paper cites Backdoor cleaning without external guidance in MLLM fine-tuning.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Backdoor cleaning without external guidance in MLLM fine-tuning

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:53:14.138677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d32c9b7a-0a3b-45a1-8917-2b78a3643fa0 · outbound

This paper cites Minillm: Knowledge distillation of large language models.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Minillm: Knowledge distillation of large language models

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:53:14.074366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a51bb7c4-78cd-4b2f-99bc-40b975e53ee3 · outbound

This paper cites MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Models.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning MINED: Probing and Updating with Multimodal Time-Sensitive Knowledge for Large Multimodal Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-05T04:53:13.142470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74b080b8-944d-4d8a-a72b-534a39c68219 · outbound

This paper cites Mathcoder: Seamless code integration in llms for enhanced mathematical reasoning.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Mathcoder: Seamless code integration in llms for enhanced mathematical reasoning

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:53:14.092400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 76c6f394-d6e1-4557-8a99-8089f7dcf0cb · outbound

This paper cites Generating Sequences by Learning to Self-Correct.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Generating Sequences by Learning to Self-Correct

Reference 50

Resolution: malformed identifier; no resolver link, observed 2026-08-05T04:53:13.165423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a368c62-a29d-4e6e-9f93-ecdb5d9c6a58 · outbound

This paper cites an unresolved cited work.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Unresolved cited work

Reference 51

Resolution: unresolved; raw_fallback, observed 2026-08-05T04:53:14.057496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation cc02cac2-914a-4afa-830f-3f0e1a453564 · outbound

This paper cites an unresolved cited work.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Unresolved cited work

Reference 52

Resolution: unresolved; raw_fallback, observed 2026-08-05T04:53:14.039323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e82dd163-107b-494f-8a7d-0843a8f6677a · outbound

This paper cites an unresolved cited work.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Unresolved cited work

Reference 53

Resolution: unresolved; raw_fallback, observed 2026-08-05T04:53:14.021601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 615e3fea-8876-41e4-b695-975684456f7a · outbound

This paper cites 17 Figure 10Case Study: Reflective Reasoning (Success).

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning 17 Figure 10Case Study: Reflective Reasoning (Success)

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:53:14.002582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 165e5c50-9541-4901-b645-34bffda28b24 · outbound

This paper cites an unresolved cited work.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-08-05T04:53:13.985398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 185dcd77-df9f-48aa-b89b-249267a1f57f · outbound

This paper cites The reference solution suggests there were some errors in the previous attempts. Recomputing:.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning The reference solution suggests there were some errors in the previous attempts. Recomputing:

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:53:13.968802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c1872307-fff5-456f-8650-4dfb8e02e1e9 · outbound

This paper cites an unresolved cited work.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning Unresolved cited work

Reference 483

Resolution: unresolved; raw_fallback, observed 2026-08-05T04:53:14.461761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation edd914fa-d6f8-45f0-8048-8e58b2befa49 · outbound

This paper cites https://thinkingmachines.ai/blog/on-policy-distillation.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning https://thinkingmachines.ai/blog/on-policy-distillation

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-05T04:53:12.971795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fa1c871-1e68-4fbe-a32c-6e00ee3212e2 · outbound

This paper cites URLhttps://openreview.net/forum?id=9SkkifLopZ.

ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning URLhttps://openreview.net/forum?id=9SkkifLopZ

Reference 2026

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T04:53:14.253295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers