7 papers
AbstRAG: Learning to Abstract for Retrieval Problems
Lei Xu, Xin Quan, Daniel Pedronette +1
Retrieval-augmented generation often fails when the query, the document evidence, and the user's intent are expressed at different levels of abstraction. A query may ask about a cl…
Reasoning without Gold Standards: A Proxy-Judge Theory of Autoformalization
Lei Xu, Xin Quan, André Freitas
Complex reasoning tasks increasingly require systems to produce outputs whose correctness cannot be judged by exact match against a single reference. Autoformalization (AF) is a re…
Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals
Sirui Chen, Lei Xu, Yuying Zhao +6
Recent RL methods have substantially improved the reasoning abilities of LLMs. Existing reward designs mainly follow two paradigms: (1) Reinforcement learning with verifiable rewar…
CauScientist: Teaching LLMs to Respect Data for Causal Discovery
Bo Peng, Sirui Chen, Lei Xu +1
Causal discovery is fundamental to scientific understanding and reliable decision-making. Existing approaches face critical limitations: purely data-driven methods suffer from stat…
DEPO: Dual-Efficiency Preference Optimization for LLM Agents
Sirui Chen, Mengshi Zhao, Lei Xu +5
Recent advances in large language models (LLMs) have greatly improved their reasoning and decision-making abilities when deployed as agents. Richer reasoning, however, often comes…
Synthesis by Design: Controlled Data Generation via Structural Guidance
Lei Xu, Sirui Chen, Yuxuan Huang +1
Mathematical reasoning remains challenging for LLMs due to complex logic and the need for precise computation. Existing methods enhance LLM reasoning by synthesizing datasets throu…