5 papers
AttriMem: Attribution-Guided Process Feedback for Agent Memory Construction
Qinfeng Li, Yuntai Bao, Xinyan Yu +8
Effective memory is crucial for LLM agents, yet constructing it effectively remains challenging. A memory-construction policy decides what information to extract, store, update, co…
Dep-Search: Learning Dependency-Aware Reasoning Traces with Persistent Memory
Yanming Liu, Xinyue Peng, Zixuan Yan +7
Large Language Models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks, particularly when augmented with search mechanisms that enable systematic explora…
NC2C: Automated Convexification of Generic Non-Convex Optimization Problems
Xinyue Peng, Yanming Liu, Yihan Cang +4
Non-convex optimization problems are pervasive across mathematical programming, engineering design, and scientific computing, often posing intractable challenges for traditional so…
ToolGate: Contract-Grounded and Verified Tool Execution for LLMs
Yanming Liu, Xinyue Peng, Jiannan Cao +5
Large Language Models (LLMs) augmented with external tools have demonstrated remarkable capabilities in complex reasoning tasks. However, existing frameworks rely heavily on natura…
LLM-OptiRA: LLM-Driven Optimization of Resource Allocation for Non-Convex Problems in Wireless Communications
Xinyue Peng, Yanming Liu, Yihan Cang +2
Solving non-convex resource allocation problems poses significant challenges in wireless communication systems, often beyond the capability of traditional optimization techniques.…