No article text was recorded for this version.
first-error localization
Version 1 of 147 papers60 conceptsfrozen 2026-10-04
Papers in this version
- Blog: OpenPRM: Building Open-domain Process-based Reward Models with Preference Trees
- Blog: Linking Process to Outcome: Conditional Reward Modeling for LLM Reasoning
- Blog: InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning
- Blog: Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards
- Blog: Structure Enables Effective Self-Localization of Errors in LLMs
- Blog: Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
- Blog: Sherlock: Self-Correcting Reasoning in Vision-Language Models
- Blog: Process Reward Model with Q-value Rankings
- Blog: Table-Critic: A Multi-Agent Framework for Collaborative Criticism and Refinement in Table Reasoning
- Blog: RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold
- Blog: Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
- Blog: Reasoning Paths Optimization: Learning to Reason and Explore From Diverse Paths
- Blog: Ekka: Automated Diagnosis of Silent Errors in LLM Inference
- Blog: Changing the Rules: A Comprehensive Approach to Theory Refinement
- Blog: MPBench: A Comprehensive Multimodal Reasoning Benchmark for Process Errors Identification
- Blog: CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning
- Blog: CHAMP: A Competition-level Dataset for Fine-Grained Analyses of LLMs' Mathematical Reasoning Capabilities
- Blog: MM-PRM: Enhancing Multimodal Mathematical Reasoning with Scalable Step-Level Supervision
- Blog: Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives
- Blog: MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning
- Blog: Local Prompt Optimization
- Blog: Constructive Circuit Amplification: Improving Math Reasoning in LLMs via Targeted Sub-Network Updates
- Blog: SDPO: Segment-Level Direct Preference Optimization for Social Agents
- Blog: SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction
- Blog: CRAFT: Counterexample-guided Repair And Falsification of Theorems in ML and Optimization
- Blog: Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models
- Blog: Critic-CoT: Boosting the Reasoning Abilities of Large Language Model via Chain-of-Thought Critic
- Blog: HyPER: Bridging Exploration and Exploitation for Scalable LLM Reasoning with Hypothesis Path Expansion and Reduction
- Blog: GRACE: Discriminator-Guided Chain-of-Thought Reasoning
- Blog: Guiding LLM-Based Loop Invariant Synthesis via Feedback on Local Reasoning Errors
- Blog: Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution
- Blog: TRACE: A Framework for Analyzing and Enhancing Stepwise Reasoning in Vision-Language Models
- Blog: S^3cMath: Spontaneous Step-Level Self-Correction Makes Large Language Models Better Mathematical Reasoners
- Blog: PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning
- Blog: Enhancing Mathematical Reasoning in LLMs by Stepwise Correction
- Blog: FAPO: Flawed-Aware Policy Optimization for Efficient and Reliable Reasoning
- Blog: Finding the Cracks: Improving LLMs Reasoning with Paraphrastic Probing and Consistency Verification
- Blog: Argue with Me Tersely: Towards Sentence-Level Counter-Argument Generation
- Blog: Error-driven Data-efficient Large Multimodal Model Tuning
- Blog: GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinements
- Blog: GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinements
- Blog: GRAIL: Gradient-Reweighted Advantages for Reinforcement Learning with Verifiable Rewards
- Blog: Self-Explore to Avoid the Pit: Improving the Reasoning Capabilities of Language Models with Fine-grained Rewards
- Blog: Improving Test-Time Search for LLMs with Backtracking Against In-Context Value Verifiers
- Blog: Advancing LLM Reasoning with Natural Language and Numerical Feedback
- Blog: ProcessBench: Identifying Process Errors in Mathematical Reasoning
- Blog: Process-Verified Reinforcement Learning for Theorem Proving via Lean
History & citation
Current · Permanent link
- This direction split from Localizing the First Error in Multi-Step Reasoning (55% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_first_error_localization_57471e62,
title = {first-error localization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/first-error-localization/rdr_57471e62322c41b19e84506e04023eb4},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_first_error_localization_57471e62_v1,
title = {first-error localization},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/first-error-localization/rdr_57471e62322c41b19e84506e04023eb4/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}