9 papers
LeAct: Learning to Reason from Expert Actions
Ziran Yang, Chengshuai Shi, Raj Ghugare +3
Modern reasoning models depend on reasoning data, today sourced from human annotations or distilled from stronger LLMs. However, a rich and largely untapped source of supervision l…
MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
Bohan Lyu, Yucheng Yang, Siqiao Huang +25
Modern AI progress has been driven by ML methods that are generalizable across settings and scalable to larger regimes. As large language models demonstrate advanced capabilities i…
Goedel-Architect: Streamlining Formal Theorem Proving with Blueprint Generation and Refinement
Jui-Hui Chung, Ziyang Cai, Zihao Li +14
We introduce Goedel-Architect, an agentic framework for formal theorem proving in Lean 4 centered on blueprint generation and refinement. A blueprint is a dependency graph of defin…
Continual Harness: Online Adaptation for Self-Improving Foundation Agents
Seth Karten, Joel Zhang, Tersoo Upaa +5
Coding harnesses such as Claude Code and OpenHands wrap foundation models with tools, memory, and planning, but no equivalent exists for embodied agents' long-horizon partial-obser…
Awakening the Sleeping Agent: Lean-Specific Agentic Data Reactivates General Tool Use in Goedel Prover
Jui-Hui Chung, Hongzhou Lin, Lai Jiang +2
Heavy supervised fine-tuning on a target domain can strongly suppress capabilities that were present in the base model. We study this phenomenon in formal mathematics using Goedel-…
Goedel-Code-Prover: Hierarchical Proof Search for Open State-of-the-Art Code Verification
Zenan Li, Ziran Yang, Deyuan He +7
Large language models (LLMs) can generate plausible code but offer limited guarantees of correctness. Formally verifying that implementations satisfy specifications requires constr…