4 papers
TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks
Zhaoyang Chu, Jiarui Hu, Xingyu Jiang +8
We introduce TerminalWorld, a scalable data engine that automatically reverse-engineers high-fidelity evaluation tasks from "in-the-wild" terminal recordings. Processing 80,870 ter…
CodeTracer: Towards Traceable Agent States
Han Li, Yifan Yao, Letian Zhu +13
Code agents are advancing rapidly, but debugging them is becoming increasingly difficult. As frameworks orchestrate parallel tool calls and multi-stage workflows over complex tasks…
MARINE: Theoretical Optimization and Design for Multi-Agent Recursive IN-context Enhancement
Hongwei Zhang, Ji Lu, Yongsheng Du +5
Large Language Model (LLM)-based agents demonstrate advanced reasoning capabilities, yet practical constraints frequently limit outputs to single responses, leaving significant per…
Co-Sight: Enhancing LLM-Based Agents via Conflict-Aware Meta-Verification and Trustworthy Reasoning with Structured Facts
Hongwei Zhang, Ji Lu, Shiqing Jiang +11
Long-horizon reasoning in LLM-based agents often fails not from generative weakness but from insufficient verification of intermediate reasoning. Co-Sight addresses this challenge…