Theorem-Proving Agent over Abstract Syntax Tree
cs.SE, cs.AI, cs.LG, cs.PL
Submitted: 2026-07-17
Updated: 2026-11-12
Code: https://github.com/xqyww123/Isa-Mini
Project page: https://trishullab.github.io/PutnamBench/leaderboard.html
Terminology
Sources
- Generative Language Modeling for Automated Theorem Proving
- Seed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from Experience
- DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition
- Numina-Lean-Agent: An Open and General Agentic Reasoning System for Formal Mathematics
- MerLean: An Agentic Framework for Autoformalization in Quantum Computation
- VeriSoftBench: Repository-Scale Formal Verification Benchmarks for Lean
- A Minimal Agent for Automated Theorem Proving
- Automated Conjecture Resolution with Formal Verification
- A Minimalist Proof Language for Neural Theorem Proving over Isabelle/HOL
- Why Do Large Language Models (LLMs) Struggle to Count Letters?
- Neural Theorem Proving for Verification Conditions: A Real-World Benchmark
- Prover Agent: An Agent-Based Framework for Formal Mathematical Proofs
- Archon: An Architecture Search Framework for Inference-Time Techniques
- LEAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks
- Kimi K2: Open Agentic Intelligence
- GLM-5: from Vibe Coding to Agentic Engineering
- Pythagoras-Prover: Advancing Efficient Formal Proving via Augmented Lean Formalisation
- Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learning
- OProver: A Unified Framework for Agentic Formal Theorem Proving
- LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning
Related papers
- ArkEval: Benchmarking and Evaluating Automated CodeRepair for ArkTS
- TestPrism: Rethinking Test Evaluation Beyond a Single Reference
- Mining Workflow Graphs for Black-Box Boundary Testing of Conversational LLM Agents
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- For Coding Agents, the Repository Matters