collaborators

6 papers

cs.AI2026

Distilling LLM Feedback for Lean Theorem Proving

Gaetan Narozniak, Gérard Biau, Rémi Munos +2

Post-training for reasoning models typically combines supervised fine-tuning with reinforcement learning from verifiable rewards, most commonly with GRPO. However, this algorithm s…

cs.AI2026

Formalizing Mathematics at Scale

Ahmad Rammal, Niket Patel, Fabian Gloeckle +5

We present AutoformBot, a multi-agent system for building an Autoformalized Textbook Library At Scale (Atlas) in Lean 4. AutoformBot orchestrates thousands of LLM agents, equipped…

cs.AI2026

Automatic Textbook Formalization

Fabian Gloeckle, Ahmad Rammal, Charles Arnal +4

We present a case study where an automatic AI system formalizes a textbook with more than 500 pages of graduate-level algebraic combinatorics to Lean. The resulting formalization r…

cs.AI2025

Safety Alignment of LMs via Non-cooperative Games

Anselm Paulus, Ilia Kulikov, Brandon Amos +4

Ensuring the safety of language models (LMs) while maintaining their usefulness remains a critical challenge in AI alignment. Current approaches rely on sequential adversarial trai…

cs.LG2025

Iterative GRPO: Batch-Online Multi-Turn RL via Single-Turn RLHF

Daniel R. Jiang, Ankur Samanta, Yukai Yang +3

Practical LLM agents often operate over multi-turn conversations where success is determined only after the full interaction ends. Most multi-turn RL methods train via on-policy ro…

cs.CL2025

Positional Encoding via Token-Aware Phase Attention

Yu Wang, Sheng Shen, Rémi Munos +2

We prove under practical assumptions that Rotary Positional Embedding (RoPE) introduces an intrinsic distance-dependent bias in attention scores that limits RoPE's ability to model…