mlsanityData to 14 Oct 2026

ProofSketch: Efficient Verified Reasoning for Large Language Models

arXiv 2510.24811 ↗First posted 28 Oct 2025cs.CL cs.AI cs.LGcited by 0

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Reasoning methods such as chain-of-thought prompting and self-consistency have shown immense potential to improve the accuracy of large language models across various reasoning tasks. However such methods involve generation of lengthy reasoning chains, which substantially increases token consumption, computational cost, and latency. To address this inefficiency, we propose ProofSketch, a verification-guided reasoning framework that integrates symbolic closure computation, lexicographic verification and adaptive sketch generation. Our experiments show that ProofSketch consistently reduces token usage while improving accuracy, demonstrating that this approach offers a promising path for efficient and trustworthy reasoning.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 12 of its 19 references that are in the map. First posted on arXiv 28 Oct 2025.

Builds on

12 of 19 references.

References · 12

  1. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  3. 2023Mistral 7Bcited by 3,164
  4. 2020ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Languagecited by 324
  5. 2025Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketchingcited by 117
  6. 2025SelfBudgeter: Adaptive Token Allocation for Efficient LLM Reasoningcited by 48
  7. 2025Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Modelscited by 37
  8. 2024Direct Evaluation of Chain-of-Thought in Multi-hop Reasoning with Knowledge Graphscited by 32
  9. 2025Efficient Reasoning for LLMs through Speculative Chain-of-Thoughtcited by 22
  10. 2025SABER: Switchable and Balanced Training for Efficient LLM Reasoningcited by 12
  11. 2025Zero-Shot Verification-guided Chain of Thoughtscited by 10
  12. 2025Atomic Reasoning for Scientific Table Claim Verificationcited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025PCRLLM: Proof-Carrying Reasoning with Large Language Models under Stepwise Logical Constraints
  2. 2026Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification
  3. 2025Can Large Language Models Learn Formal Logic? A Data-Driven Training and Evaluation Framework
  4. 2025Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification
  5. 2024Exploring the Role of Reasoning Structures for Constructing Proofs in Multi-Step Natural Language Reasoning with Large Language Models
  6. 2026Enhancing reasoning accuracy in large language models during inference time
  7. 2024Derailer-Rerailer: Adaptive Verification for Efficient and Reliable Language Model Reasoning
  8. 2025Graph of Verification: Structured Verification of LLM Reasoning with Directed Acyclic Graphs