LogicHunter combines specification-driven test generation with a ReAct-based agentic oracle to discover 40 previously unknown bugs in LangChain, LlamaIndex, and CrewAI, achieving 91.17% oracle precision.
hub Canonical reference
Large Language Models Cannot Self-Correct Reasoning Yet
Canonical reference. 88% of citing Pith papers cite this work as background.
68
Pith papers citing it
35
external citations · Pith
Background
88% of classified citations
abstract
Large Language Models (LLMs) have emerged as a groundbreaking technology with their unparalleled text generation capabilities across various applications. Nevertheless, concerns persist regarding the accuracy and appropriateness of their generated content. A contemporary methodology, self-correction, has been proposed as a remedy to these issues. Building upon this premise, this paper critically examines the role and efficacy of self-correction within LLMs, shedding light on its true potential and limitations. Central to our investigation is the notion of intrinsic self-correction, whereby an LLM attempts to correct its initial responses based solely on its inherent capabilities, without the crutch of external feedback. In the context of reasoning, our research indicates that LLMs struggle to self-correct their responses without external feedback, and at times, their performance even degrades after self-correction. Drawing from these insights, we offer suggestions for future research and practical applications in this field.
hub tools
citation-role summary
background 7
baseline 1
citation-polarity summary
representative citing papers
A²utoLPBench is a generator that produces unlimited LP word problems with ground-truth answers known by construction via inverse-KKT, bundled with a Docker environment for agent evaluation.
Controlled ablation finds Popperian code-generation skill adds no separable correctness benefit over labels-only scaffold; gains track structure not content.
AIP models skills as graphs of discrete steps connected by typed I/O edges under a validated schema, raising agent mean reward from 0.60 to 0.71 and pass rate from 53% to 67% on 27 SkillsBench tasks while enabling node-level fixes.
ARBITER models reasoning trajectory basins in test-time sampling and uses model-internal signals to correct majority-vote failures, recovering part of the oracle gap on math benchmarks.
A decoupled question-conditioned image editor trained via supervised imitation then VLM-reward enhancement improves MLLM visual reasoning Pass@1 by 4.6-5.5 points across models and tasks.
LinAlg-Bench shows LLMs switch from execution errors to computational abandonment and structured fabrication at 4x4 matrix scale, indicating a working memory limit rather than knowledge gaps.
AgentForesight introduces an online auditor model that predicts decisive errors in multi-agent trajectories at the earliest step using a coarse-to-fine reinforcement learning recipe on a new curated dataset AFTraj-2K.
In 30-step recursive LLM loops, append-mode persistent escape from source basins reaches 50% near 400 tokens under full history but plateaus below 50% under tail-clip memory policy, while replace-mode switching largely reflects state reset.
Homogeneous multi-agent debate introduces sycophantic conformity, contextual fragility, and consensus collapse, leading to equal or lower accuracy than isolated self-correction at 2.1-3.4x higher token cost on GSM-Hard and MMLU-Hard.
A model-agnostic Geometric Risk Controller reduces extreme errors in VLM-based OCR by requiring cross-view consensus before accepting outputs.
A survey of 1,250 papers organizes AI self-improvement along two axes—what is improved and loop closure—finding that demonstrated self-improvement strength tracks a verification hierarchy from formal verifiers down to intrinsic self-assessment.
A benchmark for LLM agents in partially observable joint decision-making reveals that deliberation challenges current models but can enable reflection and error correction.
Internal probes across three model families fail generalization and specificity tests and therefore do not support robust pre-action misalignment monitoring.
Introduces loop engineering as a distinct practice layer for coding agents, supplies a taxonomy and verification ladder, and analyzes a hand-coded corpus of fifty real loops.
On-policy self-distillation with sampled demonstrations reduces rollout diversity by amplifying existing probability gaps in the base model, unlike ideal RL which preserves ratios among correct outputs.
EDV decouples execution, distillation by a third-party agent, and consensus verification to filter erroneous trajectories in LLM agent experience learning, outperforming baselines on tau2-bench, Mind2Web, and MMTB.
Many-shot ICL with LLMs matches or exceeds supervised BERT on NER and generates high-quality labels for low-resource settings, producing ~10% absolute F1 gains when used to fine-tune BERT.
No detectable self-preference in LLMs accepting verified fixes to their own IFEval drafts versus neutral judges across four models and 85 comparisons (gap -5.1 pp, CI crossing zero).
CATPO introduces an informativeness score F(T) and critique-guided healing for failed trees to improve efficiency and performance in tree-based RLVR, reaching 37.5% macro accuracy on math benchmarks.
LLMs flag byte-identical errors 23-93 points more often when the error is presented under an external chat role than inside their own <thought> block, so role labeling, not content, gates explicit self-correction.
Reward-guided optimization of SAE latents, gated by reward and confidence, improves multi-benchmark reasoning and is post-hoc associated with more verification and course correction.
A systematic review of over 200 studies concludes that LLMs in recommender systems act as a double-edged sword, creating both opportunities and new risks for trustworthiness.
Introduces ePCA framework using neural-symbolic isolation to force agents to formalize intentions as logical constraints, claiming zero attack success and false positive rates in tested scenarios.
citing papers explorer
-
LogicHunter: Testing LLM Agent Frameworks with an Agentic Oracle
LogicHunter combines specification-driven test generation with a ReAct-based agentic oracle to discover 40 previously unknown bugs in LangChain, LlamaIndex, and CrewAI, achieving 91.17% oracle precision.
-
A$^{2}$utoLPBench: An Auto-Generated, Agent-Friendly LP Benchmark via Inverse-KKT Construction
A²utoLPBench is a generator that produces unlimited LP word problems with ground-truth answers known by construction via inverse-KKT, bundled with a Docker environment for agent evaluation.
-
Scaffold, Not Vocabulary? A Controlled, Two-Tier, Pre-Registered Study of a Popperian Code-Generation Skill
Controlled ablation finds Popperian code-generation skill adds no separable correctness benefit over labels-only scaffold; gains track structure not content.
-
AIP: A Graph Representation for Learning and Governing Agent Skills
AIP models skills as graphs of discrete steps connected by typed I/O edges under a validated schema, raising agent mean reward from 0.60 to 0.71 and pass rate from 53% to 67% on 27 SkillsBench tasks while enabling node-level fixes.
-
ARBITER: Reasoning Trajectory Basins and Majority Vote Failures in Test-Time Sampling
ARBITER models reasoning trajectory basins in test-time sampling and uses model-internal signals to correct majority-vote failures, recovering part of the oracle gap on math benchmarks.
-
ETCHR: Editing To Clarify and Harness Reasoning
A decoupled question-conditioned image editor trained via supervised imitation then VLM-reward enhancement improves MLLM visual reasoning Pass@1 by 4.6-5.5 points across models and tasks.
-
LinAlg-Bench: A Forensic Benchmark Revealing Structural Failure Modes in LLM Mathematical Reasoning
LinAlg-Bench shows LLMs switch from execution errors to computational abandonment and structured fabrication at 4x4 matrix scale, indicating a working memory limit rather than knowledge gaps.
-
AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems
AgentForesight introduces an online auditor model that predicts decisive errors in multi-agent trajectories at the earliest step using a coarse-to-fine reinforcement learning recipe on a new curated dataset AFTraj-2K.
-
Perturbation Dose Responses in Recursive LLM Loops: Raw Switching, Stochastic Floors, and Persistent Escape under Append, Replace, and Dialog Updates
In 30-step recursive LLM loops, append-mode persistent escape from source basins reaches 50% near 400 tokens under full history but plateaus below 50% under tail-clip memory policy, while replace-mode switching largely reflects state reset.
-
The Cost of Consensus: Isolated Self-Correction Prevails Over Unguided Homogeneous Multi-Agent Debate
Homogeneous multi-agent debate introduces sycophantic conformity, contextual fragility, and consensus collapse, leading to equal or lower accuracy than isolated self-correction at 2.1-3.4x higher token cost on GSM-Hard and MMLU-Hard.
-
From Plausibility to Verifiability: Risk-Controlled Generative OCR with Vision-Language Models
A model-agnostic Geometric Risk Controller reduces extreme errors in VLM-based OCR by requiring cross-view consensus before accepting outputs.
-
Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops
A survey of 1,250 papers organizes AI self-improvement along two axes—what is improved and loop closure—finding that demonstrated self-improvement strength tracks a verification hierarchy from formal verifiers down to intrinsic self-assessment.
-
LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability
A benchmark for LLM agents in partially observable joint decision-making reveals that deliberation challenges current models but can enable reflection and error correction.
-
Internal-State Probes Read the Situation, Not the Action: Three Negative Results for Pre-Action Misalignment Monitoring
Internal probes across three model families fail generalization and specificity tests and therefore do not support robust pre-action misalignment monitoring.
-
Stop Hand-Holding Your Coding Agent: Engineering the Loops that Replace Step-by-Step Prompting
Introduces loop engineering as a distinct practice layer for coding agents, supplies a taxonomy and verification ladder, and analyzes a hand-coded corpus of fifty real loops.
-
On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity
On-policy self-distillation with sampled demonstrations reduces rollout diversity by amplifying existing probability gaps in the base model, unlike ideal RL which preserves ratios among correct outputs.
-
Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning
EDV decouples execution, distillation by a third-party agent, and consensus verification to filter erroneous trajectories in LLM agent experience learning, outperforming baselines on tau2-bench, Mind2Web, and MMTB.
-
Scaling Performance and Low-Resource Annotation with Many-Shot In-Context Learning for Named Entity Recognition
Many-shot ICL with LLMs matches or exceeds supervised BERT on NER and generates high-quality labels for low-resource settings, producing ~10% absolute F1 gains when used to fine-tune BERT.
-
Self-Preference Is Weak or Absent in Verifiable Instruction-Following Revision: A Four-Model Test Under Genuine Authorship
No detectable self-preference in LLMs accepting verified fixes to their own IFEval drafts versus neutral judges across four models and 85 comparisons (gap -5.1 pp, CI crossing zero).
-
CATPO: Critique-Augmented Tree Policy Optimization
CATPO introduces an informativeness score F(T) and critique-guided healing for failed trees to improve efficiency and performance in tree-based RLVR, reaching 37.5% macro accuracy on math benchmarks.
-
The Self-Correction Illusion: Role Relabeling Gates Explicit Error Flagging in Large Language Models
LLMs flag byte-identical errors 23-93 points more often when the error is presented under an external chat role than inside their own <thought> block, so role labeling, not content, gates explicit self-correction.
-
Latent Reward Steering: An Adaptive Inference-Time Framework that Implicitly Promotes Cognitive Behaviors in Reasoning LLMs
Reward-guided optimization of SAE latents, gated by reward and confidence, improves multi-benchmark reasoning and is post-hoc associated with more verification and course correction.
-
Trustworthy Recommendation in the Era of Large Language Models: Opportunities and Challenges
A systematic review of over 200 studies concludes that LLMs in recommender systems act as a double-edged sword, creating both opportunities and new risks for trustworthiness.
-
Provably Secure Agent Guardrail
Introduces ePCA framework using neural-symbolic isolation to force agents to formalize intentions as logical constraints, claiming zero attack success and false positive rates in tested scenarios.
-
ProCrit: Self-Elicited Multi-Perspective Reasoning with Critic-Guided Revision for Multimodal Sarcasm Detection
ProCrit proposes a Proposal-Critic framework that synthesizes process-level annotations via agentic rollout and uses draft-critique-revise with mutual-refinement RL to improve multimodal sarcasm detection.
-
Stage-Audit: Auditable Source-Frontier Discovery for Cross-Wiki Tables
Stage-Audit raises source-frontier precision from 0.356 to 0.505 and F1 from 0.334 to 0.451 on a 51-instance cross-domain set by enforcing disjoint write rights and row-level source gates.
-
OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences
OEP poisons self-evolving LLM agents by constructing clean edge-case experiences that appear locally valid yet cause harmful over-generalization during reflection, achieving over 50% attack success rate on GPT-4o agents across three domains.
-
Wasserstein Equilibrium Decoding for Reliable Medical Visual Question Answering
Introduces Wasserstein equilibrium decoding that improves accuracy and convergence speed for small VLMs on medical VQA benchmarks by using semantic consensus instead of lexical order.
-
Agentic AI Translate: An Agentic Translator Prototype for Translation as Communication Design
Describes a conceptual agentic prototype for AI translation that operationalizes skopos theory and GEMBA-MQM verification into a four-stage cycle with user dialogue and memory for coherence.
-
OpenDeepThink: Parallel Reasoning via Bradley-Terry Aggregation
OpenDeepThink uses Bradley-Terry aggregation of LLM pairwise judgments to rank and evolve parallel reasoning traces, improving Gemini 3.1 Pro Codeforces Elo by 405 points over eight rounds.
-
OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces
OPT-BENCH and OPT-Agent evaluate LLM self-optimization in large search spaces, showing stronger models improve via feedback but stay constrained by base capacity and below human performance.
-
ReFlect: An Effective Harness System for Complex Long-Horizon LLM Reasoning
ReFlect is a harness that wraps LLMs to detect and recover from reasoning errors, achieving 7-29 pp gains over direct CoT on long-horizon tasks and improving code patch quality to 82-87%.
-
Temporal Reasoning Is Not the Bottleneck: A Probabilistic Inconsistency Framework for Neuro-Symbolic QA
Temporal reasoning is not the core bottleneck for LLMs on time-based QA; the real issue is unstructured text-to-event mapping, addressed by a neuro-symbolic system with PIS that reaches 100% accuracy on benchmarks when representations are correct.
-
Process Supervision via Verbal Critique Improves Reasoning in Large Language Models
Verbal Process Supervision uses structured critiques from stronger models in an iterative loop to improve LLM reasoning, reaching 94.9% on GPQA Diamond and large gains on AIME 2025.
-
SOCIA-EVO: Automated Simulator Construction via Dual-Anchored Bi-Level Optimization
SOCIA-EVO generates statistically consistent simulators by separating structural refinement from parameter calibration via bi-level optimization and falsifying strategies through execution feedback in a Bayesian-weighted playbook.
-
When Verification Fails: How Compositionally Infeasible Claims Escape Rejection
AI claim verification models rely on salient-constraint shortcuts instead of full compositional reasoning under the closed-world assumption, as revealed by their over-acceptance of claims with supported salient constraints but contradicted non-salient ones.
-
Verify Before You Fix: Agentic Execution Grounding for Trustworthy Cross-Language Code Analysis
A framework combining universal AST normalization, hybrid graph-LLM embeddings, and strict execution-grounded validation achieves 89-92% intra-language accuracy and 74-80% cross-language F1 while resolving 70% of vulnerabilities at 12% failure rate.
-
FACT-E: Causality-Inspired Evaluation for Trustworthy Chain-of-Thought Reasoning
FACT-E uses controlled perturbations as an instrumental signal to measure intra-chain faithfulness in CoT reasoning and combines it with answer consistency to select trustworthy trajectories.
-
BEAGLE: Behavior-Enforced Agent for Grounded Learner Emulation
BEAGLE uses a semi-Markov model, Bayesian knowledge tracing with injected flaws, and decoupled strategy-code actions to make LLM agents produce authentic student learning trajectories that humans cannot distinguish from real data at better than chance level.
-
LACY: A Vision-Language Model-based Language-Action Cycle for Self-Improving Robotic Manipulation
LACY is a VLM framework jointly trained on L2A, A2L, and L2C tasks that uses an active augmentation cycle to self-improve robotic manipulation policies, reporting a 56.46% average success rate gain in simulation and real-world experiments.
-
GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis
GenoMAS deploys six specialized LLM agents with guided planning to preprocess transcriptomic data and identify genes, reaching 89.13% composite similarity and 60.48% F1 on the GenoTEX benchmark while outperforming prior methods.
-
Training Language Models to Self-Correct via Reinforcement Learning
SCoRe uses multi-turn online RL with regularization on self-generated traces to improve LLM self-correction, achieving 15.6% and 9.1% gains on MATH and HumanEval for Gemini models.
-
From Local to Global: A Graph RAG Approach to Query-Focused Summarization
GraphRAG improves comprehensiveness and diversity of answers to global questions over million-token document sets by constructing entity graphs and hierarchical community summaries before combining partial responses.
-
LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
LiveCodeBench collects 400 recent contest problems to create a contamination-free benchmark evaluating LLMs on code generation and related capabilities like self-repair and execution.
-
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
Math-Shepherd is an automatically trained process reward model that scores solution steps to verify and reinforce LLMs, lifting Mistral-7B from 77.9% to 89.1% on GSM8K and 28.6% to 43.5% on MATH.
-
Search, Fail, Recover: A Training Framework for Correction-Aware Reasoning
Pyligent trains LLMs to search, detect failures via task validators, and backtrack to recoverable prefixes, improving solve rates by 13–73 points over gold-only SFT on hidden graphs, Sudoku, and Blocksworld.
-
Data Selection Through Iterative Self-Filtering for Vision-Language Settings
An iterative bootstrapped self-filtering approach selects balanced clean and diverse subsets from noisy vision-language datasets to train improved CLIP models.
-
Neuro-Symbolic Verification of LLM Outputs for Data-Sensitive Domains (extended preprint)
Neuro-symbolic pipeline using formal logic and semantic embeddings detects hallucinations in LLM medical reports at 83%+ for entities and 72% for fabrications while cutting creation time 30%.
-
ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling
ExComm adds cross-agent conflict detection and soft belief correction plus trajectory diversification to agentic test-time scaling, yielding 5-6% gains over baselines on AIME and GAIA benchmarks.
-
Context, Reasoning, and Hierarchy: A Cost-Performance Study of Compound LLM Agent Design in an Adversarial POMDP
In CybORG CAGE-2, programmatic state abstraction improves mean return up to 76% over raw observations while adding deliberation tools to hierarchies degrades performance up to 3.4x and increases token use.