7 papers
RealClawBench: Live OpenClaw Benchmarks from Real Developer-Agent Sessions
Zongwei Lv, Zhewen Tan, Yaoming Li +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…
ConMoE: Expert-Pool Consolidation via Prototype Reassignment for MoE Compression
Yilun Yao, Jiaming Pan, Elsie Dai +3
Mixture-of-Experts (MoE) language models reduce per-token computation but still require storing and serving all experts, making deployment memory-intensive. Existing post-training…
Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows
Yilun Yao, Xinyu Tan, Chao-Hsuan Liu +9
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…
Formal Skill: Programmable Runtime Skills for Efficient and Accurate LLM Agents
Xi Zhang, Meijun Gao, Yuntian Zhao +6
Large Language Model (LLM) agents increasingly act inside real workspaces, where tools and skills determine whether model reasoning becomes reliable action. Existing skills remain…
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…