RELIC
Governed protocol formation, runtime binding, and capability that persists across work and member turnover.
Researcher in AI agents and organizations
UIUCUrbana–Champaign
Building the
organizational
layer of AI.
I study how AI systems evolve from models to agents, from collaboration to organizations, and from human–agent organizations to agent societies.
I work on AI agents, their organizations, and the interfaces that connect them to people. At the University of Illinois Urbana-Champaign, my research spans agentic problem solving, communication protocols, and persistent organizational capability.
I explore these questions at different scales, through the projects and papers connected to each stage.
What can a model understand?
A latent intelligence core with capability, but without agency.
How does intelligence become action?
The model becomes an acting unit with goals, tools, and interaction with the world.
When does collaboration help?
Multiple agents begin to interact, coordinate, and sometimes interfere with one another.
What keeps an agent system running?
Agent interaction becomes a continuously running system with shared state and runtime structure.
What makes capability organizational?
Capabilities become organizational when they are encoded into persistent structure, responsibility, and governance.
How should humans enter the loop?
Humans interface with an organization through judgment, authority, and translation layers.
What exists beyond one organization?
Beyond a single organization lies a larger ecology of interacting organizations, roles, norms, and institutions.
Governed protocol formation, runtime binding, and capability that persists across work and member turnover.
Diagnosing evidence-boundary overclaiming in automated research, then retrieving decisive prior work and repairing unsupported novelty claims.
Comparing A2A, ACP, ANP, and Agora across success, latency, overhead, and failures—with learned selection through ProtocolRouter.
MARBLE’s interactive environments evaluate task outcomes and coordination milestones across different communication structures and planning strategies.
Organizational memory, responsibility, and reusable capability across tasks.
Follow the researchWhen more agents create more coordination work—not better work. From MultiAgentBench to persistent organizational capability.
Modern individual capabilities, primitive working arrangements: the missing language, institutions, and continuity of collective work.
From communication protocols to generated, governed rules of work—and the institutions between organizations.
@misc{protocolbench,
title = {ProtocolBench: Which LLM MultiAgent Protocol to Choose?},
author = {Hongyi Du and Jiaqi Su and Jisen Li and Lijie Ding and Yingxuan Yang and Peixuan Han and Xiangru Tang and Kunlun Zhu and Jiaxuan You},
eprint = {2510.17149},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2510.17149}
}@misc{psibench,
title = {Ψ-Bench: Evaluating Persona-Sensitive Influencing in Persuasive Dialogues},
author = {Peixuan Han and Hongyi Du and Jiayu Liu and Yihang Sun and Jiaxuan You},
eprint = {2606.02754},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.02754}
}@misc{multiagentbench,
title = {MultiAgentBench: Evaluating the Collaboration and Competition of LLM Agents},
author = {Kunlun Zhu and Hongyi Du and Zhaochen Hong and Xiaocheng Yang and Shuyi Guo and Zhe Wang and Zhenhailong Wang and Cheng Qian and Xiangru Tang and Heng Ji and Jiaxuan You},
eprint = {2503.01935},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2503.01935}
}@misc{modelingagent,
title = {ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challenges},
author = {Cheng Qian and Hongyi Du and Hongru Wang and Xiusi Chen and Yuji Zhang and Avirup Sil and Chengxiang Zhai and Kathleen McKeown and Heng Ji},
eprint = {2505.15068},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2505.15068}
}@misc{escapebench,
title = {EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents},
author = {Cheng Qian and Peixuan Han and Qinyu Luo and Bingxiang He and Xiusi Chen and Yuji Zhang and Hongyi Du and Jiarui Yao and Xiaocheng Yang and Denghui Zhang and Yunzhu Li and Heng Ji},
eprint = {2412.13549},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2412.13549}
}A long-horizon testbed for LLM-agent organizations, including OrgEnv and professional profile graphs.
Read updateWorking on graph-grounded learning and reskilling, learner state, and human verification.
Read updateOur work studies multi-agent communication protocols and scenario-aware selection with ProtocolRouter. First-author paper.
Read updateQuestions and perspectives on this page are welcome.
This conversation belongs to Home. Comments appear only after review. For contact details or personal matters, use the private message form.
Loading comments…