mlsanityData to 14 Oct 2026

The Error You See Is Not the Error You Made: Progression-aware Reasoning Origin for Reasoning Error Localization

arXiv 2609.33297 ↗First posted 27 Sep 2026cs.AIcited by 0

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

Verifying multi-step LLM reasoning requires more than determining whether a trace is correct: a useful verifier should identify where the reasoning first goes wrong. However, existing holistic methods provide little positional evidence, while forward sequential verification often treats the first rejected step as the error source. Under error propagation, this assumption can fail, since an earlier mistake may remain locally plausible and become observable only through its downstream consequences. We therefore rethink reasoning verification as a progression-aware error-source localization problem: rather than asking only where a reasoning trace first appears inconsistent, we ask which earlier step best explains how that inconsistency emerges along the trajectory. Based on this view, we propose Progression-aware Reasoning Origin (PRO), a training-free framework for first-error localization. PRO jointly models incoming support from the preceding context and outgoing compatibility with subsequent reasoning, selectively refines regions where these signals disagree, and finally performs detector-conditioned source attribution with intervention-based evidence to distinguish the true error origin from its propagated manifestations. We further formalize the gap between forward rejection and structural exposure, showing why incoming-side evidence alone is insufficient for reliable localization under error propagation. Experiments across open-form, medical, and structured reasoning tasks demonstrate consistent improvements over strong verification baselines, supporting progression-aware source attribution as a more faithful formulation of reasoning verification.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 23 of its 23 references that are in the map. First posted on arXiv 27 Sep 2026.

Builds on

23 of 23 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024Derailer-Rerailer: Adaptive Verification for Efficient and Reliable Language Model Reasoning25 Aug
  2. 2023Large Language Models Cannot Self-Correct Reasoning Yet3 Oct
  3. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing19 May
  4. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Models17 May
  5. 2023Self-Refine: Iterative Refinement with Self-Feedback30 Mar

Other references · 18

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  4. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  5. 2023Let's Verify Step by Stepcited by 3,789
  6. 2023Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotationscited by 928
  7. 2022Solving math word problems with process- and outcome-based feedbackcited by 901
  8. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
  9. 2024Improve Mathematical Reasoning in Language Models by Automated Process Supervisioncited by 441
  10. 2023Chain-of-Verification Reduces Hallucination in Large Language Modelscited by 324
  11. 2022Large Language Models are Better Reasoners with Self-Verificationcited by 307
  12. 2024ProcessBench: Identifying Process Errors in Mathematical Reasoningcited by 292
6 more
  1. 2025MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphscited by 110
  2. 2025Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?cited by 44
  3. 2024Large Language Models Can Self-Correct with Key Condition Verificationcited by 39
  4. 2025Premise-Augmented Reasoning Chains Improve Error Identification in Math reasoning with LLMscited by 22
  5. 2025Graph of Verification: Structured Verification of LLM Reasoning with Directed Acyclic Graphscited by 8
  6. 2026MedPRMBench: A Fine-grained Benchmark for Process Reward Models in Medical Reasoningcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Structure Enables Effective Self-Localization of Errors in LLMs
  2. 2025NCV: A Node-Wise Consistency Verification Approach for Low-Cost Structured Error Localization in LLM Reasoning
  3. 2025Not All Errors Are Created Equal: ASCoT Addresses Late-Stage Fragility in Efficient LLM Reasoning
  4. 2026ReFlect: An Effective Harness System for Complex Long-Horizon LLM Reasoning
  5. 2026REFLECT: Intervention-Supported Error Attribution for Silent Failures in LLM Agent Traces
  6. 2026LLM Reasoning as Trajectories: Step-Specific Representation Geometry and Correctness Signals
  7. 2026Reasoning Errors Have a Region and a Direction in the Residual-Stream Trajectory of LLMs
  8. 2026How Language Models Fail: Token-Level Signatures of Committed and Persistent Reasoning Failures