LLM Self-Correction

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, up 167% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 105

All topics

Can Language Models Learn to Reject Their Own Bad Reasoning Steps?
Oct 5, 2026Siheng Xiong, Xiaoze Liu, Yiqiao Jin +2LLM Self-Correction Language Model Decoding
Georgia Institute of Technology · Purdue University
Why, Where, How: Taxonomy-guided Error Grounding for Code Repair in NL2SQL
Oct 4, 2026Suchan Lee, Woomin Song, Hwanjo Yu +1LLM Self-Correction Execution-Guided Code Generation
POSTECH · KAIST
Self-Spec Verifiable Code Generation
Sep 30, 2026Jiaru Qian, Yihong Dong, Yongmin Li +3LLM Self-Correction Code Generation
School of Computer Science, Peking University · Beijing Key Laboratory of Trustworthy Code Large Language Models · Key Laboratory of High Confidence Software Technologies, Peking University, Ministry of Education +3
After the Fix: Transfer of Corrected Agent Experience
Sep 28, 2026Yanfei Zhang, Xu LinLLM Self-Correction LLM Agent Memory
International Digital Economy Academy (IDEA)
Exact Feedback Is Not Control: Evaluating Text-based Closed-Loop Revision in LLMs
Sep 23, 2026Haitong Jiang, Chunlin Liu, Yile Wang +1LLM Self-Correction Controllable Text Generation
College of Computer Science and Software Engineering, Shenzhen University
Sage: Formalization with Semantic Correction
Sep 16, 2026Thomas Hirtz, Farzad Jafarrahmani, Abdelmouksit Sagueni +3LLM Self-Correction Lean Theorem Proving
Huawei Lagrange Mathematics and Computing Research Center Paris, France
SAGE-Loop: Reliable Closed-Loop LLM-Driven AutoML with Trial-and-Correction and Adaptive Ensembling
Sep 14, 2026Junquan Gu, Shibo Cui, Xiangfeng Luo +1LLM Self-Correction Ensemble Learning
RetroThinker: Enabling Retrospective Thinking in Speech LLMs
Sep 12, 2026Yi-Jen Shih, Puyuan Peng, Abdelrahman Mohamed +1LLM Self-Correction Efficient Language Model Reasoning
The University of Texas at Austin · FAIR, Meta Superintelligence Labs
If It's Not Buggy, Don't Fix It: On the Dynamics of Iterative Bug-fixing with LLMs
Sep 9, 2026Xietao Wang-Lin, Anton Isopoussu, Louis MahonLLM Self-Correction Automated Program Repair
University of Warwick · UnlikelyAI
Towards Expert Financial QA via Self-Improving RAG
Aug 27, 2026Junjie Xiong, Shawheen Ghezavat, Aum HirparaLLM Self-Correction Financial QA
University of California, Berkeley · California Polytechnic State University · Hofstra University
Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction
Aug 12, 2026Pan Wang, Yihao Hu, Hang Wang +6Agent Failure Analysis LLM Self-Correction
Ant International
Reinforcing Step-level Reasoning for Effective Self-Correction in LLMs
Aug 12, 2026Vu Duc Anh, Nhat M. Hoang, Do Xuan Long +3LLM Self-Correction Direct Preference Optimization
Nanyang Technological University, Singapore · National University of Singapore · Institute for Infocomm Research (I2R), A*STAR +1
Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning
Aug 6, 2026Ahsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer +4Numerical Reasoning in Language Models LLM Self-Correction
University of Oklahoma · Stanford University · Universitat Pompeu Fabra +1
ExeCRE: Execution-Consistency Guided Reliability Estimation for Self-Correcting Code Generation
Aug 5, 2026Yiru Dong, Richong Zhang, Fanshuang Kong +1LLM Self-Correction Execution-Guided Code Generation
Beihang University Beijing, China
The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale
Aug 5, 2026Mingguang Chen, Bo Qu, Licheng WangLLM Self-Correction LLM Evaluation
DeepGrounding · AlphaAvatar
AMTFV: Agentic Mathematical Tool-Flow Verification for LLM Self-Correction
Jul 31, 2026Rui Zou, Yutao Zhu, Mengqi Wei +1LLM Self-Correction LLM Answer Verification
Gaoling School of Artificial Intelligence, Renmin University of China · National Engineering Research Center of Educational Big Data, Central China Normal University
Reflection or Re-Generation? Why LLM Revision Fails Where Human Revision Succeeds
Jul 31, 2026Yefan Tao, Gerald Friedland, Madhusudhanan Chandrasekaran +1LLM Self-Correction LLM Self-Refinement
Amazon
GGC: Selective Query Correction for Reliable Text-to-SPARQL Generation
Jul 30, 2026Ziyi Yang, Thanh-Son Nguyen, Tuan Anh Nguyen +1LLM Self-Correction LLM Reliability
1Nanyang Technological University, Centre for Info. Sciences and Systems · Institute of High Performance Computing, Agency for Science, Technology and Research (A*STAR), Singapore
Try Again, Don't Look Back: Blind Resampling Outperforms Self-Repair in Small Code Models
Jul 28, 2026Yuvraj VermaLLM Self-Correction Code Generation
Independent Researcher, India.
Looping Is Not Reliability: State-Bound Evidence and Typed Revision Contracts for Agentic Code Repair
Jul 27, 2026Xueping Gao, Jianwei Yang, Qiang YangAgent Failure Analysis LLM Self-Correction
Alibaba Cloud Computing Hangzhou, China
Closed-Loop Validation-Repair for Healthcare Interoperability: A Multi-Model Study of Schema Compliance in Clinical LLMs
Jul 27, 2026Jianru ShenLLM Self-Correction Healthcare
University of Montana, Missoula, MT 59812, USA
DualityCert: Verifier-Gated Language-Model Repair of Broken Duality Claims in Quantum Field Theory
Jul 26, 2026Xingyang YuLLM Self-Correction Claim Verification
Department of Physics Virginia Tech Blacksburg, VA 24061, USA
LA-RL: Label-Aware Self-Reflection for Reinforcement Learning in Information Extraction
Jul 26, 2026Xiao You, Tianwei Yan, Zixu Shan +2LLM Self-Correction RL for Language Models
Hefei University of Technology, Hefei, China · Chongqing Jiaotong University, Chongqing, China
PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents
Jul 21, 2026Tianyue Jiang, Yanlin Wang, Xin He +7LLM Self-Correction Software Engineering Agents
Sun Yat-sen University, China · State Key Laboratory of Blockchain and Data Security, Zhejiang University, China · School of Cyber Science and Engineering, Huazhong University of Science and Technology, China +1
Verify, Repair, Repeat, or Stop? Robust Stopping for Noisy Verify-Repair Loops in LLM Agents
Jul 20, 2026Yitao Wu, Si Shen, Rui Yang +2AI Agent Reliability LLM Self-Correction
saofund.ai, Shenzhen, China · Shenzhen Xingqing Zhiti Technology Co., Ltd., Shenzhen, China · School of Information Technology and Engineering, Lanzhou University, Lanzhou, China
Grounded verification of chemical and materials reasoning: detection is the bottleneck
Jul 19, 2026Can Polat, Mustafa Kurban, Erchin Serpedin +1LLM Self-Correction LLM Grounding
Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX, USA · Department of Electrical and Computer Engineering, Texas A&M University at Qatar, Doha, Qatar · Department of Prosthetics and Orthotics, Ankara University, Ankara, Turkey +1
Reward-Driven LLM Agent Workflows: Synthesizing POMDP Routing and Self-Correction for Autonomous Decision-Making
Jul 19, 2026Amez Amanj Ali, Kuo-Kun TsengReward Modeling LLM Self-Correction
School of Computer Science and Technology Harbin Institute of Technology, Shenzhen
Though Language Models Err While They Strive: Conformal Prediction for Self-Correcting Scientific Generation
Jul 18, 2026Mingqiao Mo, Yunlong Tan, Hao ZhangLLM Self-Correction Scientific Reasoning
University of Chinese Academy of Sciences
Deep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning Models
Jul 15, 2026Hefeng Zhou, Jinxuan Zhang, Jiong Lou +4LLM Self-Correction LLM Prompting
Shanghai Artificial Intelligence Laboratory · Shanghai Jiao Tong University
Experience Memory Graph: One-Shot Error Correction for Agents
Jul 15, 2026Wenjun Wang, Yuchen Fang, Fengrui Liu +2Agent Memory LLM Self-Correction
University of Electronic Science and Technology of China

Oct 5, 2026, cs.CLJ/K move · Enter open · S save

Can Language Models Learn to Reject Their Own Bad Reasoning Steps?

Siheng Xiong, Xiaoze Liu, Yiqiao Jin, Xiaoqian Wang+1

Georgia Institute of Technology · Purdue University

LLM Self-Correction Language Model Decoding Efficient Language Model Reasoning LLM Reasoning Reasoning Verification

Open paper AskPDF arXiv

Verifier-guided decoding can prevent harmful reasoning steps from contaminating subsequent generation, but typically relies on an external learned verifier. We ask whether a language model can instead reject its own bad reasoning steps. We define a prefix's recoverability as the probability that the frozen generator can complete it correctly. Diagnostics show that adjacent recoverability changes are often difficult to resolve with practical Monte Carlo budgets, while same-prefix candidates exhibit a sparse low-recoverability tail. We introduce Self-Step Rejection (SSR), which trains a lightweight LoRA acceptance gate on the generator backbone while keeping the base model frozen. SSR uses confidence-qualified first-passage supervision: steps before the first resolved crossing of a root-relative recoverability barrier are accepted, the crossing step is rejected, and unresolved steps and suffixes are excluded. Training combines pointwise classification, same-prefix pairwise learning, and group-relative policy refinement using final-answer correctness. At inference, SSR accepts candidates or resamples from the unchanged prefix under rejection budgets, without an external learned verifier. Across three reasoning models and five mathematical reasoning benchmarks, SSR improves macro-average accuracy over single-pass decoding by 5.4--10.1 points using 1.21--1.40x as many generated tokens, and achieves the highest macro-average accuracy among evaluated step-level methods. Full-solution scaling methods require 4.47--8.27x the single-pass token cost for comparable performance.

Momentum

Related topics

Latest papers 105