Hugging Face Trending Papers August 4, 2026

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

Read the original on Hugging Face Trending Papers →

On-policy training has emerged as a powerful post-training paradigm for improving the reasoning capabilities of large language models, and is often enhanced by golden trajectories from stronger expert models. However, when the expert fails on harder problems, existing trajectory-guided methods lose their main source of supervision, and these failed trajectories are typically discarded as negative samples.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI

Aug 5

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

arXiv:2608. 03972v1 Announce Type: new Abstract: On-policy training has emerged as a powerful post-training paradigm for improving the reasoning capabilities of large language models, and is often enhanced by golden trajectories from stronger expert models.

By Jinhe Bi, Chennan Zhou, Zengjie Jin, Aniri, Shuo Lu, Wenke Huang, Hu Cao, Xun Xiao, Zhihong Zhu, Volker Tresp, Fei Shen, Yunpu Ma, Tat-Seng Chua

llms benchmarks

arXiv Machine Learning

Jun 4

Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement Learning

arXiv:2603. 09803v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally, potentially reinforcing flawed traces that arrive at correct answers by chance.

By Tiehua Mei, Minxuan Lv, Leiyu Pan, Zhenpeng Su, Hongru Hou, Hengrui Chen, Ao Xu, Deqing Yang

llms reinforcement-learning benchmarks

arXiv Machine Learning

Jun 8

RASFT: Rollout-Adaptive Supervised Fine-Tuning for Reasoning

arXiv:2606. 07006v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) is a prevailing method for adapting large language models to reasoning tasks by imitating offline expert demonstrations, often treating a single expert trajectory as the target behavior.

By Yongliang Miao, Fengyuan Liu, Wei Shi, Yanguang Liu, Fei Sun, Na Zou, Mengnan Du

llms reinforcement-learning fine-tuning benchmarks

arXiv AI

Aug 7

Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models

arXiv:2605. 12519v2 Announce Type: replace-cross Abstract: Training language models to produce both correct answers and sound reasoning remains an open challenge.

By Kyuyoung Kim, Kevin Wang, Yunfei Xie, Peiyang Xu, Peiyao Sheng, Chen Wei, Zhangyang Wang, Jinwoo Shin, Pramod Viswanath, Sewoong Oh

llms reinforcement-learning fine-tuning

arXiv AI

Jun 8

CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning

arXiv:2605. 28742v2 Announce Type: replace Abstract: Language models can use verifiable rewards to improve at a wide variety of reasoning tasks.

By Linas Nasvytis, Simon Jerome Han, Ben Prystawski, Satchel Grant, Noah D. Goodman, Judith E. Fan

llms rag

arXiv AI

Jun 10

Learning Evidence Highlighting for Frozen LLMs

arXiv:2604. 22565v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) can reason well, yet often miss decisive evidence when it is buried in long, noisy contexts.

By Shaoang Li, Yanhang Shi, Yufei Li, Mingfu Liang, Xiaohan Wei, Yunchen Pu, Fei Tian, Chonglin Sun, Frank Shyu, Luke Simon, Sandeep Pandey, Xi Liu, Jian Li

llms nlp reinforcement-learning

Related stories

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

Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement Learning

RASFT: Rollout-Adaptive Supervised Fine-Tuning for Reasoning

Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models

CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning

Learning Evidence Highlighting for Frozen LLMs