mlsanityData to 14 Oct 2026

CORE: Conflict-Oriented Reasoning Elimination for Verifiable Language-Model Search

arXiv 2609.39069 ↗First posted 30 Sep 2026cs.CLcited by 0

On the map: LLM reasoning → Test-time compute and efficient thinking also fits: Reasoning for agents, planning and code

Abstract (arXiv)

Test-time reasoning systems often respond to failure by restarting or revising the latest step, even when an earlier decision caused the error. We introduce CORE, a search controller that requests a certified conflict core from a verifier, backjumps to the latest decision in that core, and caches the conflict to avoid repeating it. Under sound verification, finite branching and depth, and exhaustive proposals, the uncapped search is complete and never prunes a valid solution. On 2,000 planted graph-coloring instances with matched proposals and an exact verifier, CORE reduces median verifier calls by 39.8% at 30 variables and 35.0% at 36 variables relative to chronological repair; caching further improves on backjumping alone. Across five reasoning tasks, CORE achieves 75.9% mean success with Qwen2.5-7B-Instruct and 84.2% with Qwen3-8B, compared with 72.5% and 81.8% for Tree of Thoughts. It also uses fewer verifier calls and generated tokens on both backbones. These results show the value of using certified failure explanations to direct language-model search.

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 14 of its 25 references that are in the map. First posted on arXiv 30 Sep 2026.

Builds on

14 of 25 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing19 May
  2. 2023Self-Refine: Iterative Refinement with Self-Feedback30 Mar

Other references · 12

  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. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  4. 2023Let's Verify Step by Stepcited by 3,789
  5. 2023Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Promptingcited by 1,122
  6. 2022Solving math word problems with process- and outcome-based feedbackcited by 901
  7. 2023Reasoning with Language Model is Planning with World Modelcited by 861
  8. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Modelscited by 574
  9. 2022PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Changecited by 382
  10. 2024ProcessBench: Identifying Process Errors in Mathematical Reasoningcited by 292
  11. 2024LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworkscited by 179
  12. 2024Deliberate Reasoning in Language Models as Structure-Aware Planning with an Accurate World Modelcited by 23

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Divergent-Convergent Reasoning: Scaling Test-Time Compute through Structured Solution Synthesis
  2. 2026Pencil Puzzle Bench: A Benchmark for Multi-Step Verifiable Reasoning
  3. 2025Adaptive Test-Time Reasoning via Reward-Guided Dual-Phase Search
  4. 2026When LLM Meets Tree Search: A Systematic View of Inference as Search in Large Language Models
  5. 2025First Finish Search: Efficient Test-Time Scaling in Large Language Models
  6. 2026Efficient Test-Time Scaling via Temporal Reasoning Aggregation
  7. 2025Chain-in-Tree: Back to Sequential Reasoning in LLM Tree Search
  8. 2026Project Aletheia: Verifier-Guided Distillation of Backtracking for Small Language Models