Lea: An Agent Backbone for Mathematician-Controlled Formalization in Lean
cs.HC
Submitted: 2026-11-06
Updated: 2026-11-06
Code: https://github.com/VIDA-NYU/Lea
Terminology
Sources
- Aristotle: IMO-level Automated Theorem Proving
- Seed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from Experience
- You Shall Not Pass! Where and Why Developers Draw The Line on AI Autonomy
- Human agency in initial human-AI proof formalization workflows
- Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction
- Numina-Lean-Agent: An Open and General Agentic Reasoning System for Formal Mathematics
- DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition
- The Impact of AI Coding Assistants on Software Engineering: A Longitudinal Study
- Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learning
- DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search
- AXLE: A Cloud Infrastructure for Lean 4 Theorem Proving Utilities
- Beyond Compilation: Evaluating Faithful Natural-Language-to-Lean Statement Formalization
- LeanMarathon: Toward Reliable AI Co-Mathematicians through Long-Horizon Lean Autoformalization
- LeanArchitect: Automating Blueprint Generation for Humans and AI
Related papers
- EmoPhone: A Multi-Wave Dataset for In-the-Wild Mobile and Wearable Affect Sensing
- Tasteply: Externalizing Stable and Situational Preference as Manipulable Spatial Objects
- Shielded Trajectory Sampling for Personalized Relational Safety in Conversational AI
- From Tasks to Turns: Measuring Human Labor Contributions in Human-Agent Joint Production
- Reconstruction and Reflection of Positive Experiences through Resurfacing Laughter-indexed Everyday Moments
- LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems