LogicGraph: Benchmarking Multi-Path Logical Reasoning via Neuro-Symbolic Generation and Verification
cs.AI
Submitted: 2026-02-24
Updated: 2026-02-24
Code: https://github.com/kkkkarry/LogicGraph
Terminology
Sources
- JustLogic: A Comprehensive Benchmark for Evaluating Deductive Reasoning in Large Language Models
- Transformers as Soft Reasoners over Language
- Are We on the Right Way to Assessing LLM-as-a-Judge?
- GeoLaux: A Benchmark for Evaluating MLLMs' Geometry Performance on Long-Step Problems Requiring Auxiliary Lines
- MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations
- LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning
- gpt-oss-120b & gpt-oss-20b Model Card
- LogicBench: Towards Systematic Evaluation of Logical Reasoning Ability of Large Language Models
- Large Language Models Meet Symbolic Provers for Logical Reasoning Evaluation
- Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought
- REAL-Prover: Retrieval Augmented Lean Prover for Mathematical Reasoning
- TheoremLlama: Transforming General-Purpose LLMs into Lean4 Experts
- Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs
- TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them
- Qwen3 Technical Report
- ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning
- AR-LSAT: Investigating Analytical Reasoning of Text
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents