Hongyi Du

MSCS student at UIUC

U LabProf. Jiaxuan You’s research group

Where does
intelligence
live over time?

I study how intelligence moves beyond models and individual agents into relationships, organizations, and institutions—structures that can preserve, revise, and transmit collective capability across time.

From agents, to organizations, to longer-lived forms of collective intelligence.

RESEARCH ATLAS / TWO DIMENSIONS
Model / AgentIndividual × Within Interaction
SOCIAL SCALE × CARRIER PERSISTENCEScroll to explore
MSCS STUDENT / UIUC · U LAB

Hongyi Du杜洪一

I’m an MSCS student at the University of Illinois Urbana-Champaign. I’m fortunate to be a member of U Lab and to work with Prof. Jiaxuan You on AI agents, their organizations, and the interfaces that connect them to people.

THE CORE QUESTION

Intelligence is a beginning.
What makes it persist?

A model can contain capability. An agent can turn it into action. But contexts end, members are replaced, and organizations change or disappear. I ask how intelligence becomes embedded in structures that outlast the individuals that created it.

Intelligence can migrate into structures whose lifetime exceeds that of its current carriers.

THE RESEARCH NOTE BEHIND THIS AGENDAWhere Does Intelligence Live Over Time?From agent memory to organizational learning and civilizational inheritance.
01 / THE RESEARCH SPACE

A research space for
persistent intelligence.

Explore my research
RESEARCH ATLAS / TWO DIMENSIONS

How intelligence persists.

Where can intelligence live, and what must it outlast? Not every combination defines a distinct research object.

GUIDED RESEARCH JOURNEY

From individual capability to collective history.

Nine main stops connect the research questions. This is a reading route, not a ladder of completed achievements.

Zoom and rotate freely during the journey. Select another place to leave the guide.
X Social scale
Y Carrier persistence
You are here · Model / AgentDrag to look around
Drag to look around · wheel to zoom · right-drag to moveSelect another place to continue from your current location.
RESEARCH QUESTIONS / 16

Explore the research questions.

Select a name to travel in the scene above. Open its project or note to read more.

X · Social scale → / Y · Carrier persistence ↑
Y ↑ / X →0Individual1Group2Organization3Society4Civilization
4Across Successive Generations
3Across System Reconfiguration
Project
2Across Carrier Turnover
Project
1Across Episodes
Project
0Within Interaction
Project
Project

Coordinates organize questions, not measured progress. Proposed directions are provisional, not completed results.

Paper-backedResearch in progress & open questionsLong-term frontier

Positions are qualitative research coordinates, not measured lifetimes or claims that every capability has been achieved. Lines trace intellectual connections; human participation crosses both axes.

PAPERS FROM THE AGENDA

Recent papers from my research.

Agentic Sociology develops the framework for organizations and societies. RELIC studies persistent organizational capability. RINI examines contribution attribution against prior work.

04 / CURRENT QUESTIONS

Questions I’m
exploring.

IN FOCUS / RELIC

What persists when
the members change?

Agent OrganizationGovernance, protocols, and persistent capability. RESPONSIBILITY / GOVERNANCEPLANEXECUTEREVIEWPERSISTENT ORGANIZATIONAL STATEMEMORY / REUSABLE CAPABILITYGATEMEMBERS CHANGE. ORGANIZATIONAL STATE PERSISTS.

Governed executable protocols provide a concrete starting point for a wider research program on organizational learning.

Follow the research
05 / RESEARCH NOTES

How intelligence
learns to persist.

All notes
01 / INDIVIDUALMemoryAn individual knows how.02 / ORGANIZATIONInstitutionsCapability outlasts members.03 / SOCIETYCulturePractices cross boundaries.04 / LINEAGEInheritanceSuccessors reinterpret.LONGER-LIVED CARRIERS · DIFFERENT SCOPE · OPEN EMPIRICAL QUESTIONS
01
RESEARCH AGENDA / NOTE

From Agent Organization to Civilizational Intelligence

Organizational learning, evolution, death, succession, and lineage: what happens when artificial intelligence has not only memory, but history?

Persistent collective intelligence12 min read
01 / INDIVIDUALMemoryAn individual knows how.02 / ORGANIZATIONInstitutionsCapability outlasts members.03 / SOCIETYCulturePractices cross boundaries.04 / LINEAGEInheritanceSuccessors reinterpret.LONGER-LIVED CARRIERS · DIFFERENT SCOPE · OPEN EMPIRICAL QUESTIONS
02
RESEARCH AGENDA / NOTE

Where Does Intelligence Live Over Time?

From agent memory to organizational learning and civilizational inheritance: a research program for intelligence that outlives its original carriers.

Persistent intelligence16 min read
MultiAgentBenchCONCEPT / RESEARCH SYSTEM
ONE TASK · COMPLEMENTARY WORKSHARED DELIVERABLEContributions → integration → shared outcomeINTERFACES · ROUTING · MESSAGE EXCHANGEProtocolRouterA2AACPANPAgoraRequests ↔ responses · protocol-dependent paths
Complementary contributions · a shared outcome
03
DRAFT / RESEARCH NOTE

Why agent cooperation fails.

When more agents create more coordination work—not better work. From MultiAgentBench to persistent organizational capability.

Agent cooperation4 min read
RELICCONCEPT / RESEARCH SYSTEM
Agent OrganizationGovernance, protocols, and persistent capability. RESPONSIBILITY / GOVERNANCEPLANEXECUTEREVIEWPERSISTENT ORGANIZATIONAL STATEMEMORY / REUSABLE CAPABILITYGATEMEMBERS CHANGE. ORGANIZATIONAL STATE PERSISTS.
Governed protocols · capability beyond members
04
DRAFT / RESEARCH NOTE

AI agents are still in the organizational stone age.

Modern individual capabilities, primitive working arrangements: the missing language, institutions, and continuity of collective work.

Organizations4 min read
ProtocolBenchCONCEPT / RESEARCH SYSTEM
ONE TASK · COMPLEMENTARY WORKSHARED DELIVERABLEContributions → integration → shared outcomeINTERFACES · ROUTING · MESSAGE EXCHANGEProtocolRouterA2AACPANPAgoraRequests ↔ responses · protocol-dependent paths
Protocol interfaces · routing · message exchange
05
DRAFT / RESEARCH NOTE

Protocols are a foundation for agent society.

From communication protocols to generated, governed rules of work—and the institutions between organizations.

Protocols4 min read
Human–Agent OrganizationCONCEPT / RESEARCH SYSTEM
Human–Agent OrganizationHuman participation within shared governance. RESPONSIBILITY / GOVERNANCEPLANEXECUTEREVIEWPERSISTENT ORGANIZATIONAL STATEMEMORY / REUSABLE CAPABILITYGATEHUMAN WORK UNITHUMANLIAISONTRANSLATIONDELEGATED AGENTDELIVERABLE → COMMON REVIEW
Human office · liaison · common governance
06
DRAFT / RESEARCH NOTE

Three levels of human–organization interaction.

Direct participation, a transparent liaison, and liaison-first interaction: the P1–P3 design progression in the RELIC appendix.

Human–agent4 min read
06 / PUBLICATIONS

Research papers.

All publications
2026

RELIC: From Multi-Agent Collaboration to Persistent Organizational Capability

Hongyi Du, Tianyi Zhang, Weijia Zhang, Yi Yang, Haofei Yu, Kunlun Zhu, Tianxiang Dai, Shang Jiang, Zhelun Gao, Jiaxin Pei, Shang Zhu, Jiaxuan You

Preprint
2026

RINI: Seeing the Prior Is Not Enough

Hongyi Du, Tianyi Zhang, Heng Wang, Zhelun Gao, Yimei Liu, Ambrose Luo, Annie Hao, Jiayan Ni, Jiawei Han, Jiaxuan You

Preprint
2026

ProtocolBench: Which LLM MultiAgent Protocol to Choose?

Hongyi Du, Jiaqi Su, Jisen Li, Lijie Ding, Yingxuan Yang, Peixuan Han, Xiangru Tang, Kunlun Zhu, Jiaxuan You

ICML 2026First author
2026

Ψ-Bench: Evaluating Persona-Sensitive Influencing in Persuasive Dialogues

Peixuan Han, Hongyi Du, Jiayu Liu, Yihang Sun, Yutong Liu, Jiaxuan You

Preprint
2025

MultiAgentBench: Evaluating the Collaboration and Competition of LLM Agents

Kunlun Zhu, Hongyi Du, Zhaochen Hong, Xiaocheng Yang, Shuyi Guo, Zhe Wang, Zhenhailong Wang, Cheng Qian, Xiangru Tang, Heng Ji, Jiaxuan You

ACL 2025Core contributor · co-first author
2025

ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challenges

Cheng Qian, Hongyi Du, Hongru Wang, Xiusi Chen, Yuji Zhang, Avirup Sil, Chengxiang Zhai, Kathleen McKeown, Heng Ji

Findings of EMNLP 2025
2025

EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents

Cheng Qian, Peixuan Han, Qinyu Luo, Bingxiang He, Xiusi Chen, Yuji Zhang, Hongyi Du, Jiarui Yao, Xiaocheng Yang, Denghui Zhang, Yunzhu Li, Heng Ji

ACL 2025
RECENT UPDATES

From my research.

All updates
OPEN CONVERSATION /Home

Continue the conversation.

Questions and perspectives on this page are welcome.

Prefer a private conversation?

Loading comments…

Leave a public comment

This conversation belongs toHome. Comments appear only after review. For contact details or personal matters, use the private message form.

Public · reviewed before appearing