7 papers
S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?
Jiajun Shi, Siyuan Tao, Yuhao Wu +18
Large language models (LLMs) increasingly interact with external environments and accumulate substantial behavioral experience, yet existing agent benchmarks largely evaluate them…
RealClawBench: Live OpenClaw Benchmarks from Real Developer-Agent Sessions
Zongwei Lv, Yaoming Li, Zhewen Tan +7
Agent benchmarks should reflect what users actually ask deployed agents to do, yet existing benchmarks often miss key realism properties of real developer-agent sessions. We introd…
ESPO: Early-Stopping Proximal Policy Optimization
Zihang Li, Rui Zhou, Yingcheng Shi +8
When a large language model under reinforcement learning commits a wrong reasoning step early in a trajectory, standard algorithms force it to keep generating until the maximum hor…
Harness-Bench: Evaluating Agent Harnesses across Models and Realistic Workflows
Yilun Yao, Xinyu Tan, Chao-Hsuan Liu +10
LLM agents are increasingly deployed as executable systems that use tools, modify workspaces, and produce concrete artifacts. In such workflows, performance depends not only on the…
MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection
Zhewen Tan, Yilun Yao, Huiyan Jin +9
Large language model agents increasingly rely on persistent memory to store past interactions, retrieve relevant demonstrations, and improve long-horizon task execution. However, t…
ARC: Active and Reflection-driven Context Management for Long-Horizon Information Seeking Agents
Yilun Yao, Shan Huang, Elsie Dai +5
Large language models are increasingly deployed as research agents for deep search and long-horizon information seeking, yet their performance often degrades as interaction histori…
NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents
Jingzhe Ding, Shengda Long, Changxin Pu +46
Recent advances in coding agents suggest rapid progress toward autonomous software development, yet existing benchmarks fail to rigorously evaluate the long-horizon capabilities re…