5 papers
ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment
Yijun Lu, Rui Ye, Jiajun Wang +4
Long-horizon search agents must make multiple sequential actions (steps) to search, retrieve, verify, and integrate evidence to reach a final answer. However, existing methods for…
HyperTool: Beyond Step-Wise Tool Calls for Tool-Augmented Agents
Yaxin Du, Yifan Zhou, Yujie Ge +7
Tool-augmented LLM agents commonly rely on step-wise atomic tool calls, where each invocation, observation, and value transfer is exposed in the main reasoning trace. This creates…
LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents
Yijun Lu, Rui Ye, Yuwen Du +3
Long-horizon search agents must manage a rapidly growing working context as they reason, call tools, and observe information. Naively accumulating all intermediate content can over…
MIST-RL: Mutation-based Incremental Suite Testing via Reinforcement Learning
Sicheng Zhu, Jiajun Wang, Jiawei Ai +1
Large Language Models (LLMs) often fail to generate correct code on the first attempt, which requires using generated unit tests as verifiers to validate the solutions. Despite the…
Taming System Complexity: Demystifying Software Engineering Agents in Diagnosing Linux Kernel Faults
Zhenhao Zhou, Zhuochen Huang, Yike He +5
The Linux kernel is a critical system, serving as the foundation for numerous systems. Bugs in the Linux kernel can cause serious consequences, affecting billions of users. Fault l…