Mingchen Li
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
NLP×1Crypto×1Emerging Tech×1HCI×1Multiagent×1
Frequent co-authors
Research Timeline
2026
"What Did It Actually Do?": Understanding Risk Awareness and Traceability for Computer-Use Agents
The paper addresses the lack of user understanding regarding the actions and residual effects of advanced computer-use agents by proposing AgentTrace, a traceability framework for visualizing agent behavior and system changes.
Counterfactual Graph for Multi-Agent LLM Calibration
The paper proposes CAGE-CAL, a counterfactual graph calibration framework, to accurately assess the reliability and detect over-confidence in multi-agent LLM systems after agents communicate.
Highlighted terms show continued research focus across papers
Papers
cs.CLRecentMay 28, 2026
Counterfactual Graph for Multi-Agent LLM Calibration
Jiatan Huang, Mingchen Li, Ziming Li, Sunjae Kwon +2 more
The paper proposes CAGE-CAL, a counterfactual graph calibration framework, to accurately assess the reliability and detect over-confidence in multi-agent LLM systems after agents communicate.
View →
cs.CRcs.ETcs.HCRecentMar 30, 2026