🛰️ Daily AI Frontier
‹ back to 2026-09-21

LogicTrack: Auditing Reasoning Trajectories of Large Language Models with Formal Logic Solvers

Research LLMs & Foundation Models

Ranking

Overall 85
Content 100
Popularity N/A

No observed public metrics; popularity remains neutral/archived.

Representative image for LogicTrack: Auditing Reasoning Trajectories of Large Language Models with Formal Logic Solvers

Merged summary

TL;DR - LogicTrack is a neuro-symbolic framework that uses formal logic solvers to audit each step in an LLM’s chain of thought. It aims to improve both reasoning-chain validity and final-answer accuracy, addressing cases where models reach correct conclusions through flawed logic.

  • Automatically formalizes intermediate reasoning steps into symbolic representations and checks them with theorem provers.
  • Introduces Solver-Based Backtracking Reward, a step-level score that guides backtracking tree search during inference.
  • Generates supervised fine-tuning data containing backtracking traces, helping models internalize step-wise auditing.
  • Experiments spanning eight reasoning benchmarks and seven LLMs report improvements in reasoning verifiability and final-answer pass rate.

Sources (1)

LogicTrack: Auditing Reasoning Trajectories of Large Language Models with Formal Logic Solvers

arXiv cs.AI Jingyu Hu, Shu Yang, Weiru Liu, Di Wang 2026-09-18 arXiv:2609.21492
Public signals N/A
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · N/A X · N/A Fetched 2026-09-26 14:14:55.614123 UTC

TL;DR - LogicTrack is a neuro-symbolic framework that uses formal logic solvers to audit each step in an LLM’s chain of thought. It aims to improve both reasoning-chain validity and final-answer accuracy, addressing cases where models reach correct conclusions through flawed logic.

  • Automatically formalizes intermediate reasoning steps into symbolic representations and checks them with theorem provers.
  • Introduces Solver-Based Backtracking Reward, a step-level score that guides backtracking tree search during inference.
  • Generates supervised fine-tuning data containing backtracking traces, helping models internalize step-wise auditing.
  • Experiments spanning eight reasoning benchmarks and seven LLMs report improvements in reasoning verifiability and final-answer pass rate.
item →