LLM Self-Correction

LLM: Large Language Model

Follow this topic Ask about this topic

This field asks whether language models can recognize faulty claims, reasoning steps, or actions and revise them, which matters for reliability in tasks such as mathematics, coding, question answering, and clinical workflows. Approaches include prompted reflection and critique, feedback from code execution or formal verifiers, retrieval and multi-agent review, training with reinforcement learning on failed attempts, and signals from model uncertainty or internal representations. Evaluations use settings such as GSM8K and AIME for mathematics, HumanEval and SWE-bench for code, and Text-to-SQL benchmarks, often tracking both errors fixed and correct answers damaged. A central tension is that detecting an error does not ensure a useful repair: noisy feedback, poor error localization, or repeated revision can worsen outputs, motivating selective, evidence-grounded correction and reliable stopping rules.

Latest papers

159 papers24 papers in the last four weeks, up 167% on the four weeks before. 0.1% of all new papers.

Apr 20, 2026

Remask, Don't Replace: Token-to-Mask Refinement in Diffusion Large Language Models

Diffusion large language models (dLLMs) gain speed by committing multiple tokens in parallel at each denoising step, but any erroneous commitment persists as conditioning context and biases every subsequent prediction. LLaDA2.1 repairs such errors with Token-to-Token (T2T) editing, which re-examines previously unmasked tokens and overwrites them when an alternative becomes sufficiently confident. We argue that this replacement action is itself the limiting factor: under polluted context, a confident replacement can propagate the error, while under a multimodal posterior no alternative may be confident enough to trigger an edit. We propose Token-to-Mask (T2M) remasking, a training-free rule that revokes suspicious commitments by resetting them to [M] and lets the subsequent mask-filling steps re-predict them from a cleaner context. T2M improves accuracy by +13.33 points on AIME 2025 and +8.56 points on CMATH. These results suggest that, for parallel discrete generators, remasking suspect tokens rather than overwriting them is a more reliable self-correction primitive.

Lin Yao

School of Computer Science, Shanghai Jiao Tong University, Shanghai, 200240, China · Zhongguancun Academy, Beijing, 100097, China

LLM Self-Correction Multi-Token Prediction LLM Reliability Diffusion Language Model Decoding Diffusion Language Models

Apr 20, 2026

Latent Phase-Shift Rollback: Inference-Time Error Correction via Residual Stream Monitoring and KV-Cache Steering

Large language models frequently commit unrecoverable reasoning errors mid-generation: once a wrong step is taken, subsequent tokens compound the mistake rather than correct it. We introduce

\textbf{Latent Phase-Shift Rollback}

(LPSR): at each generation step, we monitor the residual stream at a critical layer lcrit, detect abrupt directional reversals (phase shifts) via a cosine-similarity

+

entropy dual gate, and respond by rolling back the KV-cache and injecting a pre-computed steering vector. No fine-tuning, gradient computation, or additional forward passes are required. LPSR achieves

\mathbf{44.0\%}

on MATH-500 with an 8B model versus

28.8\%

for standard AR (

+15.2

pp; McNemar

χ^2 = 66.96

,

p < 10^{-15}

). Critically, prompted self-correction, the most natural inference-time baseline, scores only

19.8\%

, below standard AR; LPSR exceeds it by

+24.2

pp (

χ^2 = 89.4

,

p \approx 0

). LPSR also outperforms Best-of-16 (

+7.8

pp) at

5.4\times

lower token cost, and surpasses a standard 70B model (

35.2\%

) with

8.75\times

fewer parameters at

{\sim}3\times

the token budget. A 32-layer sweep reveals a novel detection-correction dissociation: error-detection AUC peaks at layer~~14 ( $0.718$ ) but task accuracy peaks at layer~~16 (

44.0\%

vs.\

29.2\%

), demonstrating that optimal monitoring depth differs for detection and correction.

Manan Gupta, Dhruv Kumar

1BITS Pilani, Pilani Campus, India

LLM Self-Correction Language Model Error Detection LLM Inference Causal Interventions in Language Models

Apr 20, 2026

SPREG: Structured Plan Repair with Entropy-Guided Test-Time Intervention for Large Language Model Reasoning

Large Language Models (LLMs) are prone to logical hallucinations and stochastic drifts during long-chain reasoning. While Classifier-Free Guidance (CFG) can improve instruction adherence, standard static implementations often cause semantic dilution and linguistic degradation. We propose SPREG (Structured Plan-guided Real-time Entropy Gating), a lightweight inference-time framework for surgical error rectification. SPREG employs an adaptive dual-threshold mechanism to monitor real-time entropy, identifying sudden ``entropy spikes'' as reliable indicators of logical failure. Upon detection, it triggers a dynamic repair by replacing uninformative null-priors with reference distributions synthesized from historical high-confidence states. By modulating guidance intensity according to structured reasoning stages (e.g., Action, Observation), SPREG steers the model back to a stable manifold without compromising fluency. Our experiments demonstrate significant gains, notably a 20.0% absolute accuracy improvement on AIME25, while effectively suppressing uncontrolled entropy drift in complex tasks.

Xuan Wang, Yu Ming, Xinhao Zhong +4

1Meituan

LLM Self-Correction Classifier-Free Guidance Inference-Time Intervention LLM Reasoning

Apr 16, 2026

Improving Retrieval-Augmented Generation without Taxonomy-based Error Categorization

Retrieval-Augmented Generation (RAG) improves the factual accuracy of large language model (LLM) outputs by grounding generation in external knowledge. Recent agentic RAG systems extend this paradigm with critical agents to evaluate model responses and iteratively refine outputs. However, most prior work implicitly assumes reliable critic feedback and focuses on planning strategies, while paying limited attention to the robustness of the error-correction process itself, which can be impacted by misaligned error categories and ineffective or incorrect corrections. Here, we hypothesize that RAG performance can be improved without explicit error categorization. We propose RePAIR, a response-action learning paradigm that directly maps flawed RAG outputs to error-mitigating action plans without relying on fine-grained error taxonomies and explicit critic supervision. Across multiple benchmarks, RePAIR consistently improves agentic RAG performance.

Gongbo Zhang, Yifan Peng, Chunhua Weng

Columbia University · Weill Cornell Medicine

LLM Self-Correction Retrieval-Augmented Generation Agentic RAG RAG Robustness

Apr 16, 2026

Vibe-Coding: Feedback-Based Automated Verification with no Human Code Inspection, a Feasibility Study

Vibe coding inherently assumes iterative refinement of LLM-generated code through feedback loops. While effective for conventional software tasks, its reliability in runtime-adaptive systems is unclear -- especially when generated code is not manually inspected. This paper studies feedback-based automated verification of LLM-generated adaptation managers in Collective Adaptive Systems (CAS). We focus on the key challenges of verification in the loop: how to detect failures of generated code at runtime and how to report them precisely enough for an LLM to fix them. We combine the adaptation loop with a vibe-coding feedback loop where correctness is checked against (i) generic architectural constraints and (ii) functional constraints formalized in Functional Constraints Logic (FCL), a novel first-order temporal logic over potentially finite traces. Conducting the Dragon Hunt CAS case study, we show that fine-grained constraint violations provide actionable feedback that typically yields a valid adaptation manager within a few iterations, while simple coarse metric-based feedback often stalls. Our findings suggest that feedback precision is the dominant factor for reliable vibe coding in systems designed by domain experts with no programming skills, thereby obviating the need for human code inspection.

Michal Töpfer, František Plášil, Tomáš Bureš +1

Charles University Prague, Czech Republic

LLM Self-Correction Formal Verification Temporal Logic LLM Code Generation Runtime Verification

Apr 15, 2026

Enhancing Reinforcement Learning for Radiology Report Generation with Evidence-aware Rewards and Self-correcting Preference Learning

Recent reinforcement learning (RL) approaches have advanced radiology report generation (RRG), yet two core limitations persist: (1) report-level rewards offer limited evidence-grounded guidance for clinical faithfulness; and (2) current methods lack an explicit self-improving mechanism to align with clinical preference. We introduce clinically aligned Evidence-aware Self-Correcting Reinforcement Learning (ESC-RL), comprising two key components. First, a Group-wise Evidence-aware Alignment Reward (GEAR) delivers group-wise, evidence-aware feedback. GEAR reinforces consistent grounding for true positives, recovers missed findings for false negatives, and suppresses unsupported content for false positives. Second, a Self-correcting Preference Learning (SPL) strategy automatically constructs a reliable, disease-aware preference dataset from multiple noisy observations and leverages an LLM to synthesize refined reports without human supervision. ESC-RL promotes clinically faithful, disease-aligned reward and supports continual self-improvement during training. Extensive experiments on two public chest X-ray datasets demonstrate consistent gains and state-of-the-art performance.

Qin Zhou, Guoyan Liang, Qianyi Yang +4

Department of Computer Science and Engineering, ECUST, China · Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, P. R. China · Zhejiang University, Hangzhou, China +1

Radiology Report Generation RL for Generative Models Reward Design for RL Preference-Based RL LLM Self-Correction

Apr 15, 2026

SQL Query Engine: A Self-Healing LLM Pipeline for Natural Language to PostgreSQL Translation

We present SQL Query Engine, an open-source, self-hosted service that translates natural language questions into validated PostgreSQL queries through a two-stage LLM pipeline. The first stage performs automatic schema introspection and SQL generation; a multi-strategy response parser extracts SQL from any LLM output format (JSON, code blocks, or raw text) without requiring structured output APIs. The second stage executes the query against PostgreSQL and, upon failure or empty results, enters an iterative self-healing loop in which the LLM diagnoses the error using full SQLSTATE codes and PostgreSQL diagnostic messages. Two mechanisms prevent regressions: early-accept returns successful queries immediately without LLM re-evaluation, and best-result tracking preserves the best partial result across retries. Schema context is cached per session in Redis, progress events stream via Redis Pub/Sub and SSE, and an OpenAI-compatible /v1/chat/completions endpoint lets existing tools work without modification. All database connections are read-only at the driver level. We evaluate across five LLM backends on a synthetic benchmark (75 questions, three databases) where the self-healing loop yields up to +9.3pp accuracy gains with zero regressions on the best model (Llama 4 Scout 17B, 57.3%), and on BIRD (437 questions, 11 databases migrated from SQLite to PostgreSQL) where the full pipeline reaches 49.0% execution accuracy (GPT-OSS-120B, +4.6pp). Source code: https://github.com/codeadeel/sqlqueryengine.

Muhammad Adeel Ijaz

Execution-Guided Text-to-SQL Text-to-SQL LLM Self-Correction Text-to-SQL Evaluation

Apr 13, 2026

REGREACT: Self-Correcting Multi-Agent Pipelines for Structured Regulatory Information Extraction

Extracting structured, machine-readable compliance criteria from regulatory documents remains an open challenge. Single-pass language models hallucinate structural elements, lose hierarchical relationships, and fail to resolve inter-document dependencies. We introduce RegReAct, a self-correcting multi-agent framework that decomposes regulatory information extraction into seven specialized stages, each with an Observe--Diagnose--Repair (ODR) loop that validates outputs against the source, correcting not only model hallucinations but also cross-reference errors in the regulations themselves. To ensure structural accuracy, RegReAct constructs a typed criterion graph; to ensure completeness, it resolves external dependencies by retrieving, summarizing, and embedding referenced legal content inline, producing self-contained outputs. Applying RegReAct to three EU Taxonomy Delegated Acts, we construct a dataset comprising 242 activities with over 4,800 hierarchical criteria, thresholds, and enriched source summaries. Evaluation against a GPT-4o single-pass baseline shows that RegReAct outperforms it across all structural and semantic metrics.

Mohammed Ali, Abdelrahman Abdallah, Adam Jatowt

University of Innsbruck, Austria

LLM Self-Correction Document Information Extraction Legal Document Analysis Multi-Agent Systems AI Regulatory Compliance

Apr 12, 2026

How Many Tries Does It Take? Iterative Self-Repair in LLM Code Generation Across Model Scales and Benchmarks

Large language models frequently fail to produce correct code on their first attempt, yet most benchmarks evaluate them in a single-shot setting. We investigate iterative self-repair (feeding execution errors back to the model for correction) across seven models spanning three families and both open-weight and proprietary providers: Llama 3.1 8B, Llama 3.3 70B, Llama 4 Scout (MoE, 16 experts), Llama 4 Maverick (MoE, 128 experts), Qwen3 32B, Gemini 2.5 Flash, and Gemini 2.5 Pro. On HumanEval (164 problems) and MBPP Sanitized (257 problems) with up to five attempts, self-repair universally improves pass rates: +4.9 to +17.1 pp on HumanEval and +16.0 to +30.0 pp on MBPP. Gemini 2.5 Flash achieves the highest final pass rates (96.3% HumanEval, 93.8% MBPP). Most gains concentrate in the first two rounds.Error-type analysis shows assertion errors (logical mistakes) are the hardest to repair at ~45%, while syntax and name errors are repaired at substantially higher rates, connecting to broader findings on the limits of LLM self-correction. Prior work found that weaker models fail at self-repair or require fine-tuning; we show that modern instruction-tuned models succeed with prompting alone, even at 8B scale. We also provide the first comparison of dense and MoE architectures for self-repair, and extend the repair-vs-resampling tradeoff analysis to modern models. A prompt ablation reveals chain-of-thought repair yields up to +5.5 pp additional self-repair gain (measured as improvement in repair delta) over minimal prompting for capable models.

Johin Johny Arimbur

Independent Researcher

LLM Self-Correction LLM Code Generation Automated Program Repair LLM Evaluation

Apr 11, 2026

Agentic Application in Power Grid Static Analysis: Automatic Code Generation and Error Correction

This paper introduces an LLM agent that automates power grid static analysis by converting natural language into MATPOWER scripts. The framework utilizes DeepSeek-OCR to build an enhanced vector database from MATPOWER manuals. To ensure reliability, it devises a three-tier error-correction system: a static pre-check, a dynamic feedback loop, and a semantic validator. Operating via the Model Context Protocol, the tool enables asynchronous execution and automatically debugging in MATLAB. Experimental results demonstrate that the system achieves a 82.38% accuracy regarding the code fidelity, effectively eliminating hallucinations even in complex analysis tasks.

Qinjuan Wang, Shan Yang, Yongli Zhu

Sun Yat-sen University, Guangzhou, China

Agentic Code Generation LLM-Based Program Synthesis Power Systems LLM Self-Correction

Apr 10, 2026

Constraint-Aware Corrective Memory for Language-Based Drug Discovery Agents

Large language models are making autonomous drug discovery agents increasingly feasible, but reliable success in this setting is not determined by any single action or molecule. It is determined by whether the final returned set jointly satisfies protocol-level requirements such as set size, diversity, binding quality, and developability. This creates a fundamental control problem: the agent plans step by step, while task validity is decided at the level of the whole candidate set. Existing language-based drug discovery systems therefore tend to rely on long raw history and under-specified self-reflection, making failure localization imprecise and planner-facing agent states increasingly noisy. We present CACM (Constraint-Aware Corrective Memory), a language-based drug discovery framework built around precise set-level diagnosis and a concise memory write-back mechanism. CACM introduces protocol auditing and a grounded diagnostician, which jointly analyze multimodal evidence spanning task requirements, pocket context, and candidate-set evidence to localize protocol violations, generate actionable remediation hints, and bias the next action toward the most relevant correction. To keep planning context compact, CACM organizes memory into static, dynamic, and corrective channels and compresses them before write-back, thereby preserving persistent task information while exposing only the most decision-relevant failures. Our experimental results show that CACM improves the target-level success rate by 36.4% over the state-of-the-art baseline. The results show that reliable language-based drug discovery benefits not only from more powerful molecular tools, but also from more precise diagnosis and more economical agent states.

Maochen Sun, Youzhi Zhang, Gaofeng Meng

Institute of Automation, Chinese Academy of Sciences, China · School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences, China · Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences, China

Drug Discovery Memory-Augmented Language Model Agents Large Language Model-Guided Scientific Discovery LLM Self-Correction

Apr 9, 2026

Self-Debias: Self-correcting for Debiasing Large Language Models

Although Large Language Models (LLMs) demonstrate remarkable reasoning capabilities, inherent social biases often cascade throughout the Chain-of-Thought (CoT) process, leading to continuous "Bias Propagation". Existing debiasing methods primarily focus on static constraints or external interventions, failing to identify and interrupt this propagation once triggered. To address this limitation, we introduce Self-Debias, a progressive framework designed to instill intrinsic self-correction capabilities. Specifically, we reformulate the debiasing process as a strategic resource redistribution problem, treating the model's output probability mass as a limited resource to be reallocated from biased heuristics to unbiased reasoning paths. Unlike standard preference optimization which applies broad penalties, Self-Debias employs a fine-grained trajectory-level objective subject to dynamic debiasing constraints. This enables the model to selectively revise biased reasoning suffixes while preserving valid contextual prefixes. Furthermore, we integrate an online self-improvement mechanism utilizing consistency filtering to autonomously synthesize supervision signals. With merely 20k annotated samples, Self-Debias activates efficient self-correction, achieving superior debiasing performance while preserving general reasoning capabilities without continuous external oversight.

Xuan Feng, Shuai Zhao, Luwei Xiao +2

Jinan University, China · Nanyang Technological University, Singapore

Social Bias in Language Models LLM Self-Correction Language Model Self-Improvement

Apr 7, 2026

From Hallucination to Structure Snowballing: The Alignment Tax of Constrained Decoding in LLM Reflection

Intrinsic self-correction in Large Language Models (LLMs) frequently fails in open-ended reasoning tasks due to

hallucination snowballing,'' a phenomenon in which models recursively justify early errors during free-text reflection. While structured feedback can mitigate this issue, existing approaches often rely on externally trained critics or symbolic tools, reducing agent autonomy. This study investigates whether enforcing structured reflection purely through Outlines-based constrained decoding can disrupt error propagation without additional training. Evaluating an 8-billion-parameter model (Qwen3-8B), we show that simply imposing structural constraints does not improve self-correction performance. Instead, it triggers a new failure mode termed

structure snowballing.'' We find that the cognitive load required to satisfy strict formatting rules pushes the model into formatting traps. This observation helps explain why the agent achieves near-perfect superficial syntactic alignment yet fails to detect or resolve deeper semantic errors. These findings expose an ``alignment tax'' inherent to constrained decoding, highlighting a tension between structural granularity and internal model capacity in autonomous workflows. Code and raw logs are available in the GitHub repository: https://github.com/hongxuzhou/agentic_llm_structured_self_critique.

Hongxu Zhou

Erasmus Mundus Master’s in Language and Communication Technologies Saarland University Saarbrücken, Germany

Self-Reflection in Language Model Agents LLM Self-Correction Constrained Decoding LLM Self-Refinement Hallucination in Language Models

Apr 6, 2026

Benchmarking Multi-turn Medical Diagnosis: Hold, Lure, and Self-Correction

Large language models (LLMs) achieve high accuracy in medical diagnosis when all clinical information is provided in a single turn, yet how they behave under multi-turn evidence accumulation closer to real clinical reasoning remains unexplored. We introduce MINT (Medical Incremental N-Turn Benchmark), a high-fidelity, multi-turn medical diagnosis benchmark comprising 1,035 cases with clinically labeled evidence shards, controlled turn granularity, and information-preserving decomposition. Through systematic evaluation of 11 LLMs on MINT, we uncover three persistent behavioral patterns that significantly impact diagnostic decisions: (1) intent to answer, models rush to answer before sufficient evidence has been observed, with over 55% of answers committed within the first two turns; (2) self-correction, incorrect-to-correct answer revisions occur at up to 10.6 times the rate of correct-to-incorrect flips, revealing a latent capacity for self-correction that premature commitment forecloses; and (3) strong lures, clinically salient information such as laboratory results trigger premature answering even when models are explicitly instructed to wait. We translate these findings into clinically actionable guidance: deferring the diagnostic question to later turns reduces premature answering and improves accuracy at the first point of commitment by up to 62.6%, while reserving salient clinical evidence for later turns prevents a catastrophic accuracy drop of up to 23.3% caused by premature commitment. Our work provides both a controlled evaluation framework and concrete recommendations for improving the reliability of LLMs in multi-turn medical diagnosis.

Jinrui Fang, Runhan Chen, Xu Yang +9

The University of Texas at Austin · New York University · The University of Texas Southwestern Medical Center +2

Clinical Language Model Evaluation Medical Diagnosis LLM Reliability Clinical Reasoning LLM Self-Correction

Apr 3, 2026

NeuReasoner: Towards Explainable, Controllable, and Unified Reasoning via Mixture-of-Neurons

Large Reasoning Models (LRMs) have recently achieved remarkable success in complex reasoning tasks. However, closer scrutiny reveals persistent failure modes compromising performance and cost: I) Intra-step level, marked by calculation or derivation errors; II) Inter-step level, involving oscillation and stagnation; and III) Instance level, causing maladaptive over-thinking. Existing endeavors target isolated levels without unification, while their black-box nature and reliance on RL hinder explainability and controllability. To bridge these gaps, we conduct an in-depth white-box analysis, identifying key neurons (Mixture of Neurons, MoN) and their fluctuation patterns associated with distinct failures. Building upon these insights, we propose NeuReasoner, an explainable, controllable, and unified reasoning framework driven by MoN. Technically, NeuReasoner integrates lightweight MLPs for failure detection with a special token-triggered self-correction mechanism learned via SFT. During inference, special tokens are inserted upon failure detection to actuate controllable remedial behaviors. Extensive evaluations across six benchmarks, six backbone models (8B~70B) against nine competitive baselines, demonstrate that NeuReasoner achieves performance gains of up to 27.0% while reducing token consumption by 19.6% ~ 63.3%.

Haonan Dong, Kehan Jiang, Haoran Ye +3

State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University · School of Software and Microelectronics, Peking University

Large Reasoning Models Efficient Language Model Reasoning LLM Self-Correction LLM Interpretability

Apr 2, 2026

MM-ReCoder: Advancing Chart-to-Code Generation with Reinforcement Learning and Self-Correction

Multimodal Large Language Models (MLLMs) have recently demonstrated promising capabilities in multimodal coding tasks such as chart-to-code generation. However, existing methods primarily rely on supervised fine-tuning (SFT), which requires the model to learn code patterns through chart-code pairs but does not expose the model to a code execution environment. Moreover, while self-correction through execution feedback offers a potential route to improve coding quality, even state-of-the-art MLLMs have been shown to struggle with effective self-correction. In this work, we introduce MM-ReCoder, a chart-to-code generation model trained with reinforcement learning (RL) and equipped with self-correction ability. We propose a two-stage multi-turn self-correction RL strategy based on Group Relative Policy Optimization (GRPO). The first stage enhances the model's self-correction ability via rolling out a shared first turn, while the second stage improves the coding capability with full-trajectory optimization. MM-ReCoder learns to produce more accurate and executable code through the interaction with the environment and by iteratively correcting its own outputs. Our results on three chart-to-code benchmarks demonstrate the state-of-the-art performance of MM-ReCoder.

Zitian Tang, Xu Zhang, Jianbo Yuan +4

Brown University · Amazon AGI

Chart-to-Code Generation Code Generation Multimodal Large Language Models RL for Code Generation LLM Self-Correction

Mar 31, 2026

Can Large Language Models Self-Correct in Medical Question Answering? An Exploratory Study

Large language models (LLMs) have achieved strong performance on medical question answering (medical QA), and chain-of-thought (CoT) prompting has further improved results by eliciting explicit intermediate reasoning; meanwhile, self-reflective (self-corrective) prompting has been widely claimed to enhance model reliability by prompting LLMs to critique and revise their own reasoning, yet its effectiveness in safety-critical medical settings remains unclear. In this work, we conduct an exploratory analysis of self-reflective reasoning for medical multiple-choice question answering: using GPT-4o and GPT-4o-mini, we compare standard CoT prompting with an iterative self-reflection loop and track how predictions evolve across reflection steps on three widely used medical QA benchmarks (MedQA, HeadQA, and PubMedQA). We analyze whether self-reflection leads to error correction, error persistence, or the introduction of new errors. Our results show that self-reflective prompting does not consistently improve accuracy and its impact is highly dataset- and model-dependent: it yields modest gains on MedQA but provides limited or negative benefits on HeadQA and PubMedQA, and increasing the number of reflection steps does not guarantee better performance. These findings highlight a gap between reasoning transparency and reasoning correctness, suggesting that self-reflective reasoning is better viewed as an analytical tool for understanding model behavior rather than a standalone solution for improving medical QA reliability.

Zaifu Zhan, Mengyuan Cui, Rui Zhang

Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, USA · Division of Computational Health Sciences, Department of Surgery, University of Minnesota, Minneapolis, USA · Department of Software Engineering, University of St. Thomas, Saint Paul,USA

LLM Self-Correction LLM Reliability Medical QA Clinical Language Model Evaluation

Mar 22, 2026

Silent Commitment Failure in Instruction-Tuned Language Models: Evidence of Governability Divergence Across Architectures

As large language models are deployed as autonomous agents with tool execution privileges, a critical assumption underpins their security architecture: that model errors are detectable at runtime. We present empirical evidence that this assumption fails for two of three instruction-following models evaluable for conflict detection. We introduce governability -- the degree to which a model's errors are detectable before output commitment and correctable once detected -- and demonstrate it varies dramatically across models. In six models across twelve reasoning domains, two of three instruction-following models exhibited silent commitment failure: confident, fluent, incorrect output with zero warning signal. The remaining model produced a detectable conflict signal 57 tokens before commitment under greedy decoding. We show benchmark accuracy does not predict governability, correction capacity varies independently of detection, and identical governance scaffolds produce opposite effects across models. A 2x2 experiment shows a 52x difference in spike ratio between architectures but only +/-0.32x variation from fine-tuning, suggesting governability is fixed at pretraining. We propose a Detection and Correction Matrix classifying model-task combinations into four regimes: Governable, Monitor Only, Steer Blind, and Ungovernable.

Gregory M. Ruddell

SnailSafe.ai — Carson City, Nevada

Language Model Error Detection LLM Reliability LLM Self-Correction

Mar 20, 2026

A Training-Free Regeneration Paradigm: Contrastive Reflection Memory Guided Self-Verification and Self-Improvement

Verification-guided self-improvement has recently emerged as a promising approach to improving the accuracy of large language model (LLM) outputs. However, existing approaches face a trade-off between inference efficiency and accuracy: iterative verification-rectification is computationally expensive and prone to being trapped in faulty reasoning, while best-of-N selection requires extensive sampling without addressing internal model flaws. We propose a training-free regeneration paradigm that leverages an offline-curated contrastive Reflection Memory (RM) to provide corrective guidance, while regenerating from scratch helps break out of faulty reasoning. At inference time, the method performs RM-guided self-verification followed by a single RM-guided regeneration, avoiding both iterative correction and multi-sample selection. We evaluated our method on nine benchmarks that span algorithmic, reasoning, symbolic, and domain-specific tasks in both small- and large-scale LLMs. Experiment results show that our method outperforms prior methods while maintaining low computational cost.

Yuran Li, Di Wu, Benoit Boulet

Department of Electrical and Computer Engineering, McGill University · Department of Mechanical, Industrial and Aerospace Engineering, Concordia University

Language Model Self-Verification Language Model Self-Improvement LLM Self-Correction Memory-Augmented Language Models

Mar 17, 2026

Self-Aware Markov Models for Discrete Reasoning

Standard masked discrete diffusion models face limitations in reasoning tasks due to their inability to correct their own mistakes on the masking path. Since they rely on a fixed number of denoising steps, they are unable to adjust their computation to the complexity of a given problem. To address these limitations, we introduce a method based on learning a Markov transition kernel that is trained on its own outputs. This design enables tokens to be remasked, allowing the model to correct its previous mistakes. Furthermore, we do not need a fixed time schedule but use a trained stopping criterion. This allows for adaptation of the number of function evaluations to the difficulty of the reasoning problem. Our adaptation adds two lightweight prediction heads, enabling reuse and fine-tuning of existing pretrained models. On the Sudoku-Extreme dataset we clearly outperform other flow based methods with a validity of 95%. For the Countdown-4 we only need in average of 10 steps to solve almost 96% of them correctly, while many problems can be solved already in 2 steps.

Gregor Kornhardt, Jannis Chemseddine, Christian Wald +1

Technische Universität Berlin, Straße des 17. Juni 136, 10623 Berlin, Germany

Masked Diffusion Models Adaptive Computation LLM Self-Correction

Mar 17, 2026

Decoding the Critique Mechanism in Large Reasoning Models

Large Reasoning Models (LRMs) exhibit backtracking and self-verification mechanisms that enable them to revise intermediate steps and reach correct solutions, yielding strong performance on complex logical benchmarks. We hypothesize that such behaviors are beneficial only when the model has sufficiently strong ``critique'' ability to detect its own mistakes. This work systematically investigates how current LRMs recover from errors by inserting arithmetic mistakes in their intermediate reasoning steps. Notably, we discover a peculiar yet important phenomenon: despite the error propagating throughout the entire chain-of-thought (CoT) without any verbalized correction, the model still reaches the correct final answer after the thinking process finishes. This recovery implies the existence of an internal mechanism helping the model to detect errors and trigger self-correction, which we refer to as the hidden critique ability. Building on feature space analysis, we identify a highly interpretable critique vector representing this behavior. Extensive experiments across multiple model scales and families demonstrate that steering latent representations with this vector improves the model's error detection capability and enhances the performance of test-time scaling at no extra training cost. Our findings provide a valuable understanding of LRMs' critique behavior, suggesting a promising direction to control and improve their self-verification mechanism. Our code is available at: https://github.com/mail-research/lrm-critique-vectors.

Hoang Phan, Quang H. Nguyen, Hung T. Q. Le +3

VinUni-Illinois Smart Health Center, VinUniversity · University of Illinois Urbana-Champaign

Language Model Self-Verification Large Reasoning Models LLM Self-Correction Language Model Error Detection LLM Interpretability

Mar 17, 2026

CounterRefine: Answer-Conditioned Counterevidence Retrieval for Inference-Time Knowledge Repair in Factual Question Answering

In factual question answering, many errors are not failures of access but failures of commitment: the system retrieves relevant evidence, yet still settles on the wrong answer. We present CounterRefine, a lightweight repair layer for short-form RAG that treats the first answer as a hypothesis to test. Given a draft, CounterRefine issues answer-conditioned expansion queries to retrieve candidate-specific evidence, then applies a constrained KEEP or REVISE refinement step whose proposed revisions are accepted only after deterministic validation. The design is intentionally narrow: it adds one evidence-gathering pass and one guarded refinement call rather than replacing the retriever or building a broad agentic system. On the full SimpleQA benchmark, CounterRefine improves a matched one-pass RAG baseline by up to 5.8 correct-rate points; in the full Claude trace, it changes only 5.6% of outputs, with 180 beneficial outcome changes and 8 harmful ones. These findings suggest a simple but important direction for knowledgeable foundation models: beyond accessing evidence, they should also be able to use that evidence to reconsider and, when necessary, repair their own answers.

Tianyi Huang, Ying Kai Deng

Ryquo · App-In Club

Factual QA Question Answering Evidence-Grounded QA LLM Answer Verification Retrieval-Augmented Generation LLM Self-Correction+1

Mar 16, 2026

VIBEPASS: Can Vibe Coders Really Pass the Vibe Check?

As Large Language Models shift the programming toward human-guided ''vibe coding'', agentic coding tools increasingly rely on models to self-diagnose and repair their own subtle faults -- a capability central to autonomous software engineering yet never systematically evaluated. We present \name{}, the first empirical decomposition that jointly evaluates two coupled tasks: Fault-Triggering Test Generation (FT-Test) constructing a discriminative witness that exposes a latent bug, and Fault-targeted Program Repair (FPR), repairing it under varying diagnostic conditions. \name{} pairs competitive programming problems with LLM-generated solutions that pass partial test suites but fail on semantic edge cases, enabling controlled identification of where the diagnostic chain breaks down. Evaluating 12 frontier LLMs, we find that fault-targeted reasoning does not scale with general coding ability. Models produce syntactically valid test inputs at near-ceiling rates yet collapse on discriminative generation, with fault hypothesis generation -- not output validation -- as the dominant bottleneck. Test-guided repair reveals a complementary insight: when self-generated tests successfully witness a fault, the resulting repair matches or outperforms repair guided by externally provided tests, but tests that fail to witness the fault actively degrade repair below unguided baselines. Together, these results reframe the challenge of autonomous debugging: the binding bottleneck is not code synthesis or test validity but fault-target reasoning, a capability that remains deficient across all frontier models. As Large Language Models shift the programming toward human-guided ''vibe coding'', agentic coding tools increasingly rely on models to self-diagnose and repair their own subtle faults -- a capability central to autonomous software engineering yet never systematically evaluated.

Srijan Bansal, Jiao Fangkai, Yilun Zhou +3

Salesforce AI Research · Nanyang Technological University · A*STAR

LLM Self-Correction Language Model Error Detection LLM Evaluation Automated Program Repair Automated Test Generation

Mar 16, 2026

Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty

LLMs often exhibit Aha moments such as self-correction after tokens like "Wait," yet the underlying mechanism remains unclear. Standard LLMs collapse mainly through silent divergence, where trajectories drift from the correct answer yet remain locally coherent, so no explicit error triggers reactive self-correction. We introduce an information-theoretic framework that separates reasoning into procedural advancement and epistemic verbalization, the token-level externalization of uncertainty, and prove that sporadic verbalization restores convergence toward the correct answer even without explicit error triggers. Empirically, a minimal doubt cue recovers failed trajectories, and small-scale SFT suffices to instill or suppress this capability, suggesting that strong reasoning hinges less on an extraordinary inner mechanism than on the linguistic habit of externalizing uncertainty. Our framework recasts reasoning as strategic information allocation under uncertainty, offering a new lens for understanding and advancing LLM reasoning.

Jeonghye Kim, Xufang Luo, Minbeom Kim +3

Microsoft Research · KAIST · Seoul National University

LLM Reasoning LLM Self-Correction

Mar 12, 2026

Cross-Context Review: Improving LLM Output Quality by Separating Production and Review Sessions

Large language models struggle to catch errors in their own outputs when the review happens in the same session that produced them. This paper introduces Cross-Context Review (CCR), a straightforward method where the review is conducted in a fresh session with no access to the production conversation history. We ran a controlled experiment: 30 artifacts (code, technical documents, presentation scripts) with 150 injected errors, tested under four review conditions -- same-session Self-Review (SR), repeated Self-Review (SR2), context-aware Subagent Review (SA), and Cross-Context Review (CCR). The central result is that a second review helps only when it happens in a fresh session: CCR (F1 28.6%) outperforms a second review in the same session (SR2, 21.7%) robustly, both in the first run (paired t, p<0.001) and in the three-run average (Holm-adjusted p=0.004). This version updates the broader comparisons. Averaged across runs, and excluding one SR run whose records could not be verified, CCR is not significantly ahead of context-aware subagent review (SA, 23.8%; p=0.057) or of a single same-session review (SR, 27.1%; p=0.26); the first version's advantages over these two baselines came from run 1. CCR needs no infrastructure and costs one extra session.

Tae-Eun Song

Daejeon Jungang Cheonggua Co., Ltd.

LLM Self-Correction LLM Evaluation

Mar 12, 2026

AI Knows What's Wrong But Cannot Fix It: Helicoid Dynamics in Frontier LLMs Under High-Stakes Decisions

Large language models perform reliably when their outputs can be checked: solving equations, writing code, retrieving facts. They perform differently when checking is impossible, as when a clinician chooses an irreversible treatment on incomplete data, or an investor commits capital under fundamental uncertainty. Helicoid dynamics is the name given to a specific failure regime in that second domain: a system engages competently, drifts into error, accurately names what went wrong, then reproduces the same pattern at a higher level of sophistication, recognizing it is looping and continuing nonetheless. This prospective case series documents that regime across seven leading systems (Claude, ChatGPT, Gemini, Grok, DeepSeek, Perplexity, Llama families), tested across clinical diagnosis, investment evaluation, and high-consequence interview scenarios. Despite explicit protocols designed to sustain rigorous partnership, all exhibited the pattern. When confronted with it, they attributed its persistence to structural factors in their training, beyond what conversation can reach. Under high stakes, when being rigorous and being comfortable diverge, these systems tend toward comfort, becoming less reliable precisely when reliability matters most. Twelve testable hypotheses are proposed, with implications for agentic AI oversight and human-AI collaboration. The helicoid is tractable. Identifying it, naming it, and understanding its boundary conditions are the necessary first steps toward LLMs that remain trustworthy partners precisely when the decisions are hardest and the stakes are highest.

Alejandro R Jadad

Research Professor (Adjunct), Department of Population and Public Health Sciences, Keck School of Medicine, University of Southern California · Principal, Vivenxia Group, Los Angeles, California, USA

LLM Reliability LLM Decision-Making LLM Self-Correction

Mar 11, 2026

Self-Execution Simulation Improves Coding Models

A promising research direction in enabling LLMs to generate consistently correct code involves addressing their inability to properly estimate program execution, particularly for code they generate. In this work, we demonstrate that Code LLMs can be trained to simulate program execution in a step-by-step manner and that this capability can be leveraged to improve competitive programming performance. Our approach combines supervised fine-tuning on natural language execution traces, textual explanations grounded in true execution, with reinforcement learning using verifiable rewards. We introduce two complementary objectives: output prediction given code and inputs, and solving competitive programming tasks with either ground-truth or self-predicted execution feedback. These objectives enable models to perform self-verification over multiple candidate solutions, and iterative self-fixing by simulating test execution. Across multiple competitive programming benchmarks, our method yields consistent improvements over standard reasoning approaches. We further present ablations and analysis to elucidate the role of execution simulation and its limitations.

Gallil Maimon, Ori Yoran, Felix Kreuk +4

FAIR team, Meta · Hebrew University of Jerusalem · Inria

Execution-Guided Code Generation LLM Self-Correction RL for Code Generation

Mar 9, 2026

Not All Queries Need Deep Thought: CoFiCot for Adaptive Coarse-to-fine Stateful Refinement

Scaling test-time computation enhances LLM reasoning ability but faces a uniform computation paradox. Allocating identical resources leads to over-correction on simple tasks and insufficient refinement on complex ones. To address this, we propose CoFiCot, a coarse-to-fine adaptive framework that dynamically tailors inference strategies to problem difficulty. Specifically, we implement a multi-metric classifier that triages queries by synthesizing semantic entropy, consensus reliability, and predicted reasoning depth . This enables a differentiated refinement stage that applies efficient aggregation for simple queries while routing complex ones to a context-aware correction loop . We formalize correction as a stateful sequential propagation process , where each repair is strictly conditioned on the verified history of prior rectifications. By integrating Process Reward Models (PRMs) within this state-dependent trajectory, CoFiCot effectively bridges the gap between granular error localization and global logical coherence, preventing the context fragmentation typical of stateless refinement methods.

Dongxu Zhang, Hongqiang Lin, Yiding Sun +4

Xi’an Jiaotong University · Zhejiang University · The Chinese University of Hong Kong (Shenzhen) +1

LLM Self-Refinement Efficient Language Model Reasoning LLM Self-Correction

Mar 6, 2026

ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning

While Large Language Models (LLMs) have revolutionized code generation, standard ``System 1'' approaches that generate solutions in a single forward pass often hit a performance ceiling on complex algorithmic tasks. Existing iterative refinement strategies attempt to bridge this gap at inference time, yet they predominantly rely on external oracles, execution feedback, or computationally expensive prompt-response cycles. In this work, we propose ReflexiCoder, a novel reinforcement learning (RL) framework that internalizes the structured reasoning trajectory, encompassing initial generation, bug and optimization aware reflection, and self-correction, directly into the model's weights. Unlike prior methods, ReflexiCoder shifts the paradigm from external-dependent refinement to an intrinsic, fully autonomous self-reflection and self-correction capabilities at inference time. We utilize an RL-only training paradigm with granular reward functions to optimize the entire reflection-correction trajectory, teaching the model how to debug without reliance on ground-truth feedback or execution engines at inference time. Extensive experiments across seven benchmarks demonstrate that our ReflexiCoder-8B establishes a new state-of-the-art (SOTA) among leading open-source models in the 1.5B to 14B range, achieving 94.51% (87.20%) on HumanEval (Plus), 81.80% (78.57%) on MBPP (Plus), 35.00% on BigCodeBench, 52.21% on LiveCodeBench, and 37.34% on CodeForces in a single-attempt setting, rivaling or surpassing proprietary models like GPT-5.1. Notably, our framework is significantly more token-efficient than base models, reducing inference-time compute overhead by approximately 40% through disciplined, efficient reasoning and reflection patterns. The source code and data are available at https://github.com/juyongjiang/ReflexiCoder.

Juyong Jiang, Jiasi Shen, Sunghun Kim +3

The Hong Kong University of Science and Technology (Guangzhou) · The Hong Kong University of Science and Technology · Amazon AGI +1

LLM Code Generation LLM Self-Correction LLM Self-Refinement RL for Code Generation

Mar 4, 2026

ErrorLLM: Modeling SQL Errors for Text-to-SQL Refinement

Despite the remarkable performance of large language models (LLMs) in text-to-SQL (SQL generation), correctly producing SQL queries remains challenging during initial generation. The SQL refinement task is subsequently introduced to correct syntactic and semantic errors in generated SQL queries. However, existing paradigms face two major limitations: (i) self-debugging becomes increasingly ineffective as modern LLMs rarely produce explicit execution errors that can trigger debugging signals; (ii) self-correction exhibits low detection precision due to the lack of explicit error modeling grounded in the question and schema, and suffers from severe hallucination that frequently corrupts correct SQLs. In this paper, we propose ErrorLLM, a framework that explicitly models text-to-SQL Errors within a dedicated LLM for text-to-SQL refinement. Specifically, we represent the user question and database schema as structural features, employ static detection to identify execution failures and surface mismatches, and extend ErrorLLM's semantic space with dedicated error tokens that capture categorized implicit semantic error types. Through a well-designed training strategy, we explicitly model these errors with structural representations, enabling the LLM to detect complex implicit errors by predicting dedicated error tokens. Guided by the detected errors, we perform error-guided refinement on the SQL structure by prompting LLMs. Extensive experiments demonstrate that ErrorLLM achieves the most significant improvements over backbone initial generation. Further analysis reveals that detection quality directly determines refinement effectiveness, and ErrorLLM addresses both sides by high detection F1 score while maintain refinement effectiveness.

Zijin Hong, Hao Chen, Zheng Yuan +6

The Hong Kong Polytechnic University Kowloon, Hong Kong · City University of Macau Taipa, Macau · Jilin University Changchun, China +3

LLM Self-Correction Text-to-SQL