This doctoral research integrates Multi-Agent Systems (MAS) and reinforcement learning concepts into XAI evaluation and aims to systematically improve the robustness and clarity of AI explanations in complex, multi-stakeholder environments.
Comprehensive evaluations of MAREval establish MAREval as a scalable and reliable solution for human-aligned evaluation of recommendation explanations in real-world systems and improves alignment with human judgments over strong singleand multi-agent baselines.
Multi-agent LLM systems are a natural fit for complex reasoning tasks, yet most existing frameworks handle conflicting agent outputs through majority voting or confidence-based selection, without ever checking the evidence behind those outputs. We propose Confidence Adaptive Agent Negotiation (CAAN), an evidence-ground...
Swathika K, Sai Siva Rubha H, R. N et al.· 2026 International Conferenc...· 0 citations
Multi-agent reasoning with large language models (LLMs) raises a central question for collective decision-making: when agents disagree, whose decision should be trusted? Resolving such disagreements is difficult because agents'decisions are susceptible to non-semantic biases such as majority pressure and response-style...
Sungjae Lee, Soheil Abbasloo, Jabin Koo et al.· 0 citations
This work extends the mechanistic study of ICL to strategic multi-agent settings, introduces REE as a diagnostic tool for distinguishing reasoning from extrapolation, and provides a reusable framework for probing the boundaries of LLM reasoning in recursive belief tasks.
Y. Liu, Wen-Wen Li, Yi-Fan Dou et al.· Conference on Empirical Meth...· 0 citations
As agents take on long-horizon tasks, users shift from making individual decisions to overseeing autonomous execution. Yet the volume of agent activity and the fragmentation of supporting evidence make it difficult to determine which decisions warrant user verification. We study monitors that identify consequential dec...
Zhong-Xiang Sun, Jia-Hao Yan, Hong-Kang Zhao et al.· 0 citations
As agents evolve from single-tool systems into modular, composite architectures, skills are becoming an important mechanism for capability development and distribution. However, the academic community lacks a structured framework for systematically analyzing and evaluating skills. Drawing on information gain and behavi...
Zong-Rui Yang, Xin-Tong Li, Run-Chen Xu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.