5 papers
Rethinking Memory as Continuously Evolving Connectivity
Jizhan Fang, Buqiang Xu, Zhixian Wang +12
Existing memory-augmented LLM agents often treat memory as a static repository with pre-defined representations and fixed retrieval pipelines, which is brittle in dynamic agentic e…
Securing the Floor and Raising the Ceiling: A Merging-based Paradigm for Multi-modal Search Agents
Zhixiang Wang, Jingxuan Xu, Dajun Chen +3
Recent advances in Vision-Language Models (VLMs) have motivated the development of multi-modal search agents that can actively invoke external search tools and integrate retrieved…
EGSS: Entropy-guided Stepwise Scaling for Reliable Software Engineering
Chenhui Mao, Yuanting Lei, Zhixiang Wei +6
Agentic Test-Time Scaling (TTS) has delivered state-of-the-art (SOTA) performance on complex software engineering tasks such as code generation and bug fixing. However, its practic…
Learning Adaptive Parallel Execution for Efficient Code Localization
Ke Xu, Siyang Xiao, Ming Liang +6
Code localization constitutes a key bottleneck in automated software development pipelines. While concurrent tool execution can enhance discovery speed, current agents demonstrate…
One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents
Zhaoxi Zhang, Yitong Duan, Yanzhi Zhang +9
Locating files and functions requiring modification in large software repositories is challenging due to their scale and structural complexity. Existing LLM-based methods typically…