6 papers
JURY-RL: Votes Propose, Proofs Dispose for Label-Free RLVR
Xinjie Chen, Biao Fu, Jing Wu +4
Reinforcement learning with verifiable rewards (RLVR) enhances the reasoning of large language models (LLMs), but standard RLVR often depends on human-annotated answers or carefull…
ReForm: Reflective Autoformalization with Prospective Bounded Sequence Optimization
Guoxin Chen, Jing Wu, Xinjie Chen +6
Autoformalization, which translates natural language mathematics into machine-verifiable formal statements, is critical for using formal mathematical reasoning to solve math proble…
SCOUT-RAG: Scalable and Cost-Efficient Unifying Traversal for Agentic Graph-RAG over Distributed Domains
Longkun Li, Yuanben Zou, Jinghan Wu +4
Graph-RAG improves LLM reasoning using structured knowledge, yet conventional designs rely on a centralized knowledge graph. In distributed and access-restricted settings (e.g., ho…
Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression
Peijun Zhu, Ning Yang, Baoliang Tian +4
Mixture-of-Experts (MoE) Large Language Models (LLMs) face a trilemma of load imbalance, parameter redundancy, and communication overhead. We introduce a unified framework based on…
Internal Representations as Indicators of Hallucinations in Agent Tool Selection
Kait Healy, Bharathi Srinivasan, Visakh Madathil +1
Large Language Models (LLMs) have shown remarkable capabilities in tool calling and tool usage, but suffer from hallucinations where they choose incorrect tools, provide malformed…
Designing Large Foundation Models for Efficient Training and Inference: A Survey
Dong Liu, Yanxuan Yu, Yite Wang +5
This paper focuses on modern efficient training and inference technologies on foundation models and illustrates them from two perspectives: model and system design. Model and Syste…