7 papers
Multi-Agent Teams Hold Experts Back
Aneesh Pappu, Batu El, Hancheng Cao +4
Multi-agent LLM systems are increasingly deployed as autonomous collaborators, where agents interact freely rather than execute fixed, pre-specified workflows. In such settings, ef…
Hilbert: Recursively Building Formal Proofs with Informal Reasoning
Sumanth Varambally, Thomas Voice, Yanchao Sun +3
Large Language Models (LLMs) demonstrate impressive mathematical reasoning abilities, but their solutions frequently contain errors that cannot be automatically checked. Formal the…
CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning
Xinyu Zhu, Yihao Feng, Yanchao Sun +5
Large Language Models (LLMs) have recently exhibited remarkable reasoning capabilities, largely enabled by supervised fine-tuning (SFT)- and reinforcement learning (RL)-based post-…
Interleaved Reasoning for Large Language Models via Reinforcement Learning
Roy Xie, David Qiu, Deepak Gopinath +5
Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increa…
RLAX: Large-Scale, Distributed Reinforcement Learning for Large Language Models on TPUs
Runlong Zhou, Lefan Zhang, Shang-Chen Wu +29
Reinforcement learning (RL) has emerged as the de-facto paradigm for improving the reasoning capabilities of large language models (LLMs). We have developed RLAX, a scalable RL fra…
Checklists Are Better Than Reward Models For Aligning Language Models
Vijay Viswanathan, Yanchao Sun, Shuang Ma +4
Language models must be adapted to understand and follow user instructions. Reinforcement learning is widely used to facilitate this -- typically using fixed criteria such as "help…