arXiv Computation and Language September 18, 2026 By Qirui Chen, Renjie Pi, Jiahui Gao, Lingpeng Kong

Reflective Recovery: A Self-Supervised Method for Reasoning by Learning from Mistakes

Read the original on arXiv Computation and Language →

Reflective Recovery is a self‑supervised method that turns failed reasoning attempts into training data, enabling large language models to learn how to correct mistakes during inference. By extracting initial segments of erroneous trajectories and using them as prompts, the approach teaches models to recognize and recover from errors without external critics. Experiments show significant accuracy gains on benchmarks such as AIME 2025 and Minerva, and the method overcomes the scaling collapse problem, fostering emergent self‑correction behaviors.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

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

Hugging Face Trending Papers

Aug 4

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

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.

llms benchmarks

arXiv AI

Jul 21

Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering

arXiv:2607. 18100v1 Announce Type: new Abstract: Extended reasoning has become standard for frontier Large Language Models (LLMs), yet the trajectories these models produce remain largely uncontrollable.

By Sheldon Yu, Tong Yu, Xunyi Jiang, Rohan Surana, Gagan Mundada, Sungchul Kim, Lina Yao, Julian McAuley, Junda Wu

llms

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

Aug 7

Woodpecker Distillation: Weak Models Diagnose Reasoning Bugs in Strong Models

arXiv:2608. 05168v1 Announce Type: new Abstract: Large language models often fail on reasoning tasks despite possessing the capability to solve them.

By Dayu Wang, Jiaye Yang, Weikang Li, Jiahui Liang, Yang Li, Deguo Xia, Jizhou Huang

llms fine-tuning efficiency benchmarks

arXiv Machine Learning

Sep 11

Negative Self-Distillation: Learning to Reason by Avoiding Flaws

Negative Self-Distillation (NSD) is a new framework for improving large language models by encouraging them to diverge from their own flawed reasoning rather than imitate privileged solutions. Unlike On-Policy Self-Distillation, which can suppress uncertainty and exploratory behavior, NSD generates a question‑specific negative condition (e.g., a careless reasoner) and uses a dynamic gating mechanism to target only reasoning‑critical tokens for penalization. This approach preserves foundational language capabilities while consistently outperforming OPSD and other label‑free self‑bootstrapping reinforcement learning baselines.

By Rongcan Pei, Zhepei Wei, Shuyao Xu, Xinyu Zhu, Wei-Lin Chen, Yu Meng

llms reinforcement-learning efficiency

One email a morning, machine-written

Related stories

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

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

Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering

CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning

Woodpecker Distillation: Weak Models Diagnose Reasoning Bugs in Strong Models

Negative Self-Distillation: Learning to Reason by Avoiding Flaws