3 papers
cs.CR2026
BenchShield: Formal Model-Backed Instrumentation for Reward Integrity in LLM-Agent Evaluation Infrastructure
Shenghan Zheng, Zonglin Di, Yimin Liu +19
LM-agent benchmarks increasingly function as interactive evaluation infrastructure. Agents observe state, call tools, modify workspaces, submit artifacts, and receive rewards from…
cs.AI2026
ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces
Xiangyi Li, Kyoung Whan Choe, Yimin Liu +12
Large language model (LLM) agents are increasingly deployed to automate productivity tasks (e.g., email, scheduling, document management), but evaluating them on live services is r…
cs.LG2025
Results of the NeurIPS 2023 Neural MMO Competition on Multi-task Reinforcement Learning
Joseph Suárez, Kyoung Whan Choe, David Bloomin +22
We present the results of the NeurIPS 2023 Neural MMO Competition, which attracted over 200 participants and submissions. Participants trained goal-conditional policies that genera…