arXiv AI October 12, 2026 By Jiwon Jeon, Myungsik Cho, Jeonghye Kim, Youngchul Sung

Inject a Turn, Not a Token: Learning Where to Redirect LLM Reasoning for Self-Correction

The paper introduces UPTURN, a method that improves large language model self‑correction by learning where to intervene in a failed reasoning rollout and injecting a new user turn to redirect the model, rather than fine‑tuning the LLM. A small 130K‑parameter MLP head is trained on a frozen encoder using only final‑answer correctness to select intervention points. Experiments on four reasoners and six math benchmarks show that UPTURN consistently raises accuracy over a 32‑rollout baseline and outperforms existing self‑correction and reflection‑token injection techniques while transferring to new tasks without retraining.

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 AI.

arXiv AI

Jun 12

LLMs as ASP Programmers: Self-Correction Enables Task-Agnostic Nonmonotonic Reasoning

arXiv:2604. 27960v2 Announce Type: replace Abstract: Recent large language models (LLMs) have achieved impressive reasoning milestones but continue to struggle with high computational costs, logical inconsistencies, and sharp performance degradation on high-complexity problems.

By Adam Ishay, Joohyung Lee

llms benchmarks

arXiv Machine Learning

Jul 31

LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints

arXiv:2410. 06458v2 Announce Type: replace-cross Abstract: Instruction following is a key capability for LLMs.

By Thomas Palmeira Ferraz, Kartik Mehta, Yu-Hsiang Lin, Haw-Shiuan Chang, Shereen Oraby, Sijia Liu, Vivek Subramanian, Tagyoung Chung, Mohit Bansal, Nanyun Peng

llms benchmarks

arXiv AI

Jun 6

ReTreVal: Reasoning Tree with Validation and Cross-Problem Memory for Large Language Models

arXiv:2601. 02880v2 Announce Type: replace Abstract: Every existing inference-time reasoning framework discards all failure context at problem boundaries, leaving a model solving problem 500 no wiser than it was on problem 1.

By Abhishek HS, Pavan C Shekar, Arpit Jain, Ashwanth Krishnan

llms fine-tuning benchmarks

arXiv Machine Learning

Aug 4

Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in Large Language Models

arXiv:2507. 02778v3 Announce Type: replace-cross Abstract: Although large language models (LLMs) have transformed AI, they still make errors and follow unproductive reasoning paths.

By Ken Tsui

llms fine-tuning safety

arXiv AI

Aug 13

Reinforcing Step-level Reasoning for Effective Self-Correction in LLMs

arXiv:2608. 11573v1 Announce Type: cross Abstract: Achieving effective self-correction, where models verify and correct their own mistakes, remains a fundamental challenge for large language models (LLMs).

By Vu Duc Anh, Nhat M. Hoang, Do Xuan Long, Cong-Duy Nguyen, Ponhvoan Srey, Luu Anh Tuan

llms reinforcement-learning

arXiv Machine Learning

Jul 9

MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoning

arXiv:2607. 06974v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly improve their reasoning at test time via additional computation, yet most existing works treat each problem in isolation.

By Ruilin Tong, Dong Gong

llms rag

One email a morning, machine-written

Related stories

LLMs as ASP Programmers: Self-Correction Enables Task-Agnostic Nonmonotonic Reasoning

LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints

ReTreVal: Reasoning Tree with Validation and Cross-Problem Memory for Large Language Models

Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in Large Language Models

Reinforcing Step-level Reasoning for Effective Self-Correction in LLMs

MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoning