Skip to yearly menu bar Skip to main content


Workshop Mon, Apr 27, 2026 • 5:00 AM – 1:00 PM PDT 208

Workshop on Multi-Agent Learning and Its Opportunities in the Era of Generative AI

Jianhong Wang ⋅ Caroline Wang ⋅ Feng Chen ⋅ Arrasy Rahman ⋅ Felipe Leno da Silva ⋅ Rupali Bhati ⋅ Bo Liu ⋅ Mustafa Mert Çelikok
Project Page

Abstract

Video

Chat is not available.

Schedule

Timezone: America/Los_Angeles
5:00 AM
Opening Remarks
Jianhong Wang
7:10 AM
EconAI: Dynamic Persona Evolution and Memory-Aware Agents inEvolving Economic Environments
Yijin Chen ⋅ Ning Lyu ⋅ Shengning Lang ⋅ Hao Yan ⋅ Zhiguo Tao ⋅ Xiaotong Ding ⋅ Xiaotong Zhu
7:17 AM
GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory
Xuanqiang Angelo Huang ⋅ Pepijn Cobben ⋅ Thao Pham ⋅ Terry Zhang ⋅ Zhijing Jin
7:24 AM
AI Organizations Are More Effective but Less Aligned than Individual Agents
Judy Shen ⋅ Daniel Zhu ⋅ Siddarth Srinivasan ⋅ Henry Sleight ⋅ Lawrence Wagner ⋅ Morgan Matthews ⋅ Jascha Sohl-Dickstein ⋅ Erik Jones
7:31 AM
CooperBench: Benchmarking Cooperation in Coding Agents
Arpandeep Khatua ⋅ Hao Zhu ⋅ Peter Tran ⋅ Arya Prabhudesai ⋅ Frederic Sadrieh ⋅ Johann Lieberwirth ⋅ Xinkai Yu ⋅ Yicheng Fu ⋅ Michael J Ryan ⋅ Jiaxin Pei ⋅ Diyi Yang
7:38 AM
AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization
Genghan Zhang ⋅ Shaowei Zhu ⋅ Anjiang Wei ⋅ Zhenyu Song ⋅ Allen Nie ⋅ Zhen Jia ⋅ Nandita Vijaykumar ⋅ Yida Wang ⋅ Kunle Olukotun
7:45 AM
ArchPilot: A Proxy-Guided Multi-Agent Approach for Machine Learning Engineering
Zhuowen Yuan ⋅ Tao Liu ⋅ Yang Yang ⋅ Yang Wang ⋅ Feng Qi ⋅ Kaushik Rangadurai ⋅ Bo Li ⋅ Shuang Yang
→ AI Organizations Are More Effective but Less Aligned than Individual Agents
Judy Shen ⋅ Daniel Zhu ⋅ Siddarth Srinivasan ⋅ Henry Sleight ⋅ Lawrence Wagner ⋅ Morgan Matthews ⋅ Jascha Sohl-Dickstein ⋅ Erik Jones
→ EvoCF: Multi-Agent Collaboration via Agentic Memory-Driven Evolutionary Counterfactual Planning
Haotian Chi ⋅ Zeyu Feng ⋅ Xingrui Yu ⋅ Linbo Luo ⋅ Yew-Soon Ong ⋅ Ivor Tsang ⋅ Hechang Chen ⋅ Yi Chang ⋅ Haiyan Yin
→ AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization
Genghan Zhang ⋅ Shaowei Zhu ⋅ Anjiang Wei ⋅ Zhenyu Song ⋅ Allen Nie ⋅ Zhen Jia ⋅ Nandita Vijaykumar ⋅ Yida Wang ⋅ Kunle Olukotun
→ EconAI: Dynamic Persona Evolution and Memory-Aware Agents inEvolving Economic Environments
Yijin Chen ⋅ Ning Lyu ⋅ Shengning Lang ⋅ Hao Yan ⋅ Zhiguo Tao ⋅ Xiaotong Ding ⋅ Xiaotong Zhu
→ RPRA: Predicting an LLM-Judge for Efficient but Performant Inference
Dylan Ashley ⋅ Gael Le Lan ⋅ Changsheng Zhao ⋅ Naina Dhingra ⋅ zhipeng cai ⋅ Ernie Chang ⋅ Mingchen Zhuge ⋅ Yangyang Shi ⋅ Vikas Chandra ⋅ Jürgen Schmidhuber
→ MetroRehearsal: Tool-Guided Multi-Agent Debate for Metro Emergency Planning
Jinlin Li ⋅ Xiao Zhou ⋅ Yingying Zhang ⋅ Xian Wu
→ Self-Improvement of Language Models by Post-Training on Multi-Agent Debate
Ankur Samanta ⋅ Akshayaa Magesh ⋅ Runzhe Wu ⋅ Ayush Jain ⋅ Youliang Yu ⋅ Daniel Jiang ⋅ Boris Vidolov ⋅ Paul Sajda ⋅ Yonathan Efroni ⋅ Kaveh Hassani
→ AffectMind: Proactive Knowledge Grounding with Affective Multimodal Signals for Aligned Marketing Dialogue
Xinyu Wang ⋅ Xiaomin Zhao ⋅ Zhihao Lin ⋅ Xiang Luo ⋅ Zhang Chengbiao ⋅ Jin Cheng ⋅ Yixin Wang ⋅ Yangyang Zhang ⋅ Ernie Tian ⋅ Zhiguo Tao ⋅ Yifei Kang ⋅ Xiaofei Han ⋅ Xiaotong Ding
→ UT-Evolve: AN EVOLUTIONARY AGENT FOR UNIT TEST WRITING
Arshika Lalan ⋅ rajat ghosh ⋅ Debojyoti Dutta
→ Verified Multi-Agent Orchestration: A Plan-Execute-Verify-Replan Framework for Complex Query Resolution
Xing Zhang ⋅ Yanwei CUI ⋅ Guanghui Wang ⋅ Qucy Qiu ⋅ Ziyuan Li ⋅ Fangwei Han ⋅ Yajing Huang ⋅ Hengzhi Qiu ⋅ Bing Zhu ⋅ Peiyang He
→ Can Small Agents Collaborate to Beat a Single Large Language Model?
Agata Żywot ⋅ Xinyi Chen ⋅ Yifei Yuan ⋅ Anders Søgaard ⋅ Maarten de Rijke
→ Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic
Shuo Liu ⋅ Tianle Chen ⋅ Ryan Amiri ⋅ Christopher Amato
→ Let’s Talk, Not Type: An Oral-First Multi-Agent Architecture for Guarani
Samantha Adorno ⋅ Akshata Kishore Moharir ⋅ Ratna Kandala
→ Federation over Text
Dixi Yao ⋅ Tahseen Rabbani ⋅ Tian Li
→ SkillTracer: Structural Failure Attribution and Refinement of Agentic Skills in Long-Horizon Web Tasks
Yuyang Li ⋅ Yiran Dou ⋅ Jie-Jing Shao ⋅ YUEMING LYU ⋅ Ivor Tsang ⋅ Haiyan Yin
→ Heterogeneous Low-Bandwidth Pre-Training of LLMs
Yazan Obeidi ⋅ Amir Sarfi ⋅ Joel Lidin ⋅ Paul Janson ⋅ Eugene Belilovsky
→ Simulating Human Decision-Making During Disasters in Dynamic Environments
Maria Mendoza ⋅ Lucas Waldburger ⋅ Jin Lee ⋅ S. Sastry
→ BEYOND SYNTAX: ACTION SEMANTICS LEARNING FOR APP AGENTS
Bohan Tang ⋅ Dezhao Luo ⋅ Jianheng Liu ⋅ Jingxuan Chen ⋅ Shaogang Gong ⋅ Jianye Hao ⋅ Jun Wang ⋅ Kun Shao
→ Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems
Lang Feng ⋅ Longtao Zheng ⋅ Shuo He ⋅ Fuxiang Zhang ⋅ Bo An
→ Talk Before You Retrieve: Agent-Led Discussions for Better RAG in Medical QA
XUANZHAO DONG ⋅ Wenhui Zhu ⋅ Hao Wang ⋅ Xiwen Chen ⋅ Peijie Qiu ⋅ Rui Yin ⋅ Yi Su ⋅ Yalin Wang
→ Evaluating Cooperation in LLM Social Groups through Self-Organizing Leadership
Ryan Faulkner ⋅ Anushka Deshpande ⋅ David Guzman Piedrahita ⋅ Joel Z Leibo ⋅ Zhijing Jin
→ JaxAHT: A JAX-Based Library for Ad Hoc Teamwork
Caroline Wang ⋅ Rolando Fernandez ⋅ Jiaxun Cui ⋅ Johnny Liu ⋅ Aditya Madhan ⋅ Zhihan Wang ⋅ Lingyun Xiao ⋅ Di Shi ⋅ Arrasy Rahman ⋅ Peter Stone
→ CooperBench: Benchmarking Cooperation in Coding Agents
Arpandeep Khatua ⋅ Hao Zhu ⋅ Peter Tran ⋅ Arya Prabhudesai ⋅ Frederic Sadrieh ⋅ Johann Lieberwirth ⋅ Xinkai Yu ⋅ Yicheng Fu ⋅ Michael J Ryan ⋅ Jiaxin Pei ⋅ Diyi Yang
→ GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory
Xuanqiang Angelo Huang ⋅ Pepijn Cobben ⋅ Thao Pham ⋅ Terry Zhang ⋅ Zhijing Jin
→ Self-Questioning Language Models
Lili Chen ⋅ Mihir Prabhudesai ⋅ Katerina Fragkiadaki ⋅ Hao Liu ⋅ Deepak Pathak
→ ArchPilot: A Proxy-Guided Multi-Agent Approach for Machine Learning Engineering
Zhuowen Yuan ⋅ Tao Liu ⋅ Yang Yang ⋅ Yang Wang ⋅ Feng Qi ⋅ Kaushik Rangadurai ⋅ Bo Li ⋅ Shuang Yang
→ Interpretable Multi-Agent Debate for Political Opinion Simulation
Aali Azamat uulu ⋅ ⋅ Alibek Dadajonov ⋅
→ Outbidding and Outbluffing Elite Humans: Mastering Liar’s Poker via Self-Play and Reinforcement Learning
Richard Dewey ⋅ János Botyánszki ⋅ Ciamac Moallemi ⋅ Andrew Zheng
→ LaneRoPE: Positional Encoding for Collaborative Parallel Reasoning and Generation
Gabriele Cesa ⋅ Thomas Hehn ⋅ Aleix Torres i Camps ⋅ Àlex Casellas ⋅ Jordi Ros-Giralt ⋅ Arash Behboodi ⋅ Tribhuvanesh Orekondy
→ Novelty-Gated Experience Sharing for Multi-Agent Reinforcement Learning
Manish Kota ⋅ Thomas Fan ⋅ Harshita Poojary ⋅ Nolawi Teklehaimanot ⋅ Aishwarya Balwani
→ Zero-Shot Coordination among LLM Agents
Adrian Hayler ⋅ Shashank Reddy Chirra ⋅ Andrei Lupu ⋅ Johannes Forkel ⋅ Bidipta Sarkar ⋅ Siheng Feng ⋅ Jakob Foerster
→ The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind
Andrei Lupu ⋅ Timon Willi ⋅ Jakob Foerster
→ AI-BAAM: AI-Driven Bank Statement Analytics as Alternative Data for Malaysian MSME Credit Scoring
Chun Chet Ng ⋅ Zhen Hao Chu ⋅ Jia Yu Lim ⋅ Boon Yin ⋅ Low Zeng ⋅ Jin Tan
→ Expanding the Capabilities of Reinforcement Learning via Text Feedback
Yuda Song ⋅ Lili Chen ⋅ Fahim Tajwar ⋅ Remi Munos ⋅ Deepak Pathak ⋅ Drew Bagnell ⋅ Aarti Singh ⋅ Andrea Zanette
→ Build, Judge, Optimize: A Blueprint for Continuous Improvement of Multi-Agent Consumer Assistants
Steven Xu ⋅ Alejandro Herrera ⋅ ⋅ Sudeep Das ⋅ ⋅ Hong Wei ⋅ ⋅
→ MAPLE: Multi-Agent Prior Learning for Constructing Tree Ensembles
Tuan-Kiet Nguyen-Viet ⋅ Nguyen Thinh ⋅ Thanh Huynh ⋅ Hieu Pham
→ Not All Clients Are Equal: Collaborative Model Personalization on Heterogeneous Multi-Modal Clients
Minhyuk Seo ⋅ Taeheon Kim ⋅ Hankook Lee ⋅ Jonghyun Choi ⋅ Tinne Tuytelaars
→ MAGIC: Multi-Agent Generative Intention Coordination
David Huk ⋅ Oliver Hamelijnck ⋅ Dimitris Demiris ⋅ Theodoros Damoulas
→ Group Distributionally Robust Optimization-Driven RL for LLM Reasoning
Kishan Panaganti ⋅ Zhenwen Liang ⋅ Wenhao Yu ⋅ Haitao Mi ⋅ Dong Yu
→ ASSESSING SOVEREIGNTY IN MULTI-AGENT COLLABORATIONS
Eleonore Vissol-Gaudin ⋅ Janosch Haber ⋅ Andikan Otung
→ Safe Test-Time Reinforcement learning for Imperfect Information Games
Ondrej Kubicek ⋅ Viliam Lisý ⋅ Tuomas Sandholm
→ Evaluating LLM Agents as Human Simulators in Climate Social Dilemmas
Kaiyuan Liu ⋅ Xiaoxuan Hou ⋅ Jiayi Yuan ⋅ Natasha Jaques
→ Learning the Preferences of a Learning Agent
Karim Sadek ⋅ Mark Bedaywi ⋅ Rhys Gould ⋅ Stuart Russell
→ ComplLLM: Fine-tuning LLMs to Discover Complementary Signals for Decision-making
Ziyang Guo ⋅ Yifan Wu ⋅ Jason Hartline ⋅ Ken Holstein ⋅ Jessica Hullman
10:20 AM
Build, Judge, Optimize: A Blueprint for Continuous Improvement of Multi-Agent Consumer Assistants
Steven Xu ⋅ Alejandro Herrera ⋅ ⋅ Sudeep Das ⋅ ⋅ Hong Wei ⋅ ⋅
10:27 AM
ComplLLM: Fine-tuning LLMs to Discover Complementary Signals for Decision-making
Ziyang Guo ⋅ Yifan Wu ⋅ Jason Hartline ⋅ Ken Holstein ⋅ Jessica Hullman
10:34 AM
Group Distributionally Robust Optimization-Driven RL for LLM Reasoning
Kishan Panaganti ⋅ Zhenwen Liang ⋅ Wenhao Yu ⋅ Haitao Mi ⋅ Dong Yu
10:41 AM
Team of Thoughts: Efficient Test-time Scaling of Agentic Systems through Orchestrated Tool Calling
Jeffrey T. H. Wong ⋅ Zixi Zhang ⋅ Junyi Liu ⋅ Yiren Zhao
10:48 AM
Evaluating LLM Agents as Human Simulators in Climate Social Dilemmas
Kaiyuan Liu ⋅ Xiaoxuan Hou ⋅ Jiayi Yuan ⋅ Natasha Jaques
12:00 PM
Poster Session 2
→ ComplLLM: Fine-tuning LLMs to Discover Complementary Signals for Decision-making
Ziyang Guo ⋅ Yifan Wu ⋅ Jason Hartline ⋅ Ken Holstein ⋅ Jessica Hullman
→ Learning the Preferences of a Learning Agent
Karim Sadek ⋅ Mark Bedaywi ⋅ Rhys Gould ⋅ Stuart Russell
→ Evaluating LLM Agents as Human Simulators in Climate Social Dilemmas
Kaiyuan Liu ⋅ Xiaoxuan Hou ⋅ Jiayi Yuan ⋅ Natasha Jaques
→ Safe Test-Time Reinforcement learning for Imperfect Information Games
Ondrej Kubicek ⋅ Viliam Lisý ⋅ Tuomas Sandholm
→ ASSESSING SOVEREIGNTY IN MULTI-AGENT COLLABORATIONS
Eleonore Vissol-Gaudin ⋅ Janosch Haber ⋅ Andikan Otung
→ Group Distributionally Robust Optimization-Driven RL for LLM Reasoning
Kishan Panaganti ⋅ Zhenwen Liang ⋅ Wenhao Yu ⋅ Haitao Mi ⋅ Dong Yu
→ MAGIC: Multi-Agent Generative Intention Coordination
David Huk ⋅ Oliver Hamelijnck ⋅ Dimitris Demiris ⋅ Theodoros Damoulas
→ Not All Clients Are Equal: Collaborative Model Personalization on Heterogeneous Multi-Modal Clients
Minhyuk Seo ⋅ Taeheon Kim ⋅ Hankook Lee ⋅ Jonghyun Choi ⋅ Tinne Tuytelaars
→ MAPLE: Multi-Agent Prior Learning for Constructing Tree Ensembles
Tuan-Kiet Nguyen-Viet ⋅ Nguyen Thinh ⋅ Thanh Huynh ⋅ Hieu Pham
→ Build, Judge, Optimize: A Blueprint for Continuous Improvement of Multi-Agent Consumer Assistants
Steven Xu ⋅ Alejandro Herrera ⋅ ⋅ Sudeep Das ⋅ ⋅ Hong Wei ⋅ ⋅
→ Expanding the Capabilities of Reinforcement Learning via Text Feedback
Yuda Song ⋅ Lili Chen ⋅ Fahim Tajwar ⋅ Remi Munos ⋅ Deepak Pathak ⋅ Drew Bagnell ⋅ Aarti Singh ⋅ Andrea Zanette
→ AI-BAAM: AI-Driven Bank Statement Analytics as Alternative Data for Malaysian MSME Credit Scoring
Chun Chet Ng ⋅ Zhen Hao Chu ⋅ Jia Yu Lim ⋅ Boon Yin ⋅ Low Zeng ⋅ Jin Tan
→ The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind
Andrei Lupu ⋅ Timon Willi ⋅ Jakob Foerster
→ Zero-Shot Coordination among LLM Agents
Adrian Hayler ⋅ Shashank Reddy Chirra ⋅ Andrei Lupu ⋅ Johannes Forkel ⋅ Bidipta Sarkar ⋅ Siheng Feng ⋅ Jakob Foerster
→ Novelty-Gated Experience Sharing for Multi-Agent Reinforcement Learning
Manish Kota ⋅ Thomas Fan ⋅ Harshita Poojary ⋅ Nolawi Teklehaimanot ⋅ Aishwarya Balwani
→ LaneRoPE: Positional Encoding for Collaborative Parallel Reasoning and Generation
Gabriele Cesa ⋅ Thomas Hehn ⋅ Aleix Torres i Camps ⋅ Àlex Casellas ⋅ Jordi Ros-Giralt ⋅ Arash Behboodi ⋅ Tribhuvanesh Orekondy
→ Outbidding and Outbluffing Elite Humans: Mastering Liar’s Poker via Self-Play and Reinforcement Learning
Richard Dewey ⋅ János Botyánszki ⋅ Ciamac Moallemi ⋅ Andrew Zheng
→ Interpretable Multi-Agent Debate for Political Opinion Simulation
Aali Azamat uulu ⋅ ⋅ Alibek Dadajonov ⋅
→ ArchPilot: A Proxy-Guided Multi-Agent Approach for Machine Learning Engineering
Zhuowen Yuan ⋅ Tao Liu ⋅ Yang Yang ⋅ Yang Wang ⋅ Feng Qi ⋅ Kaushik Rangadurai ⋅ Bo Li ⋅ Shuang Yang
→ Self-Questioning Language Models
Lili Chen ⋅ Mihir Prabhudesai ⋅ Katerina Fragkiadaki ⋅ Hao Liu ⋅ Deepak Pathak
→ GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory
Xuanqiang Angelo Huang ⋅ Pepijn Cobben ⋅ Thao Pham ⋅ Terry Zhang ⋅ Zhijing Jin
→ CooperBench: Benchmarking Cooperation in Coding Agents
Arpandeep Khatua ⋅ Hao Zhu ⋅ Peter Tran ⋅ Arya Prabhudesai ⋅ Frederic Sadrieh ⋅ Johann Lieberwirth ⋅ Xinkai Yu ⋅ Yicheng Fu ⋅ Michael J Ryan ⋅ Jiaxin Pei ⋅ Diyi Yang
→ JaxAHT: A JAX-Based Library for Ad Hoc Teamwork
Caroline Wang ⋅ Rolando Fernandez ⋅ Jiaxun Cui ⋅ Johnny Liu ⋅ Aditya Madhan ⋅ Zhihan Wang ⋅ Lingyun Xiao ⋅ Di Shi ⋅ Arrasy Rahman ⋅ Peter Stone
→ Evaluating Cooperation in LLM Social Groups through Self-Organizing Leadership
Ryan Faulkner ⋅ Anushka Deshpande ⋅ David Guzman Piedrahita ⋅ Joel Z Leibo ⋅ Zhijing Jin
→ Talk Before You Retrieve: Agent-Led Discussions for Better RAG in Medical QA
XUANZHAO DONG ⋅ Wenhui Zhu ⋅ Hao Wang ⋅ Xiwen Chen ⋅ Peijie Qiu ⋅ Rui Yin ⋅ Yi Su ⋅ Yalin Wang
→ Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems
Lang Feng ⋅ Longtao Zheng ⋅ Shuo He ⋅ Fuxiang Zhang ⋅ Bo An
→ BEYOND SYNTAX: ACTION SEMANTICS LEARNING FOR APP AGENTS
Bohan Tang ⋅ Dezhao Luo ⋅ Jianheng Liu ⋅ Jingxuan Chen ⋅ Shaogang Gong ⋅ Jianye Hao ⋅ Jun Wang ⋅ Kun Shao
→ Simulating Human Decision-Making During Disasters in Dynamic Environments
Maria Mendoza ⋅ Lucas Waldburger ⋅ Jin Lee ⋅ S. Sastry
→ Heterogeneous Low-Bandwidth Pre-Training of LLMs
Yazan Obeidi ⋅ Amir Sarfi ⋅ Joel Lidin ⋅ Paul Janson ⋅ Eugene Belilovsky
→ SkillTracer: Structural Failure Attribution and Refinement of Agentic Skills in Long-Horizon Web Tasks
Yuyang Li ⋅ Yiran Dou ⋅ Jie-Jing Shao ⋅ YUEMING LYU ⋅ Ivor Tsang ⋅ Haiyan Yin
→ Federation over Text
Dixi Yao ⋅ Tahseen Rabbani ⋅ Tian Li
→ Let’s Talk, Not Type: An Oral-First Multi-Agent Architecture for Guarani
Samantha Adorno ⋅ Akshata Kishore Moharir ⋅ Ratna Kandala
→ Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic
Shuo Liu ⋅ Tianle Chen ⋅ Ryan Amiri ⋅ Christopher Amato
→ Can Small Agents Collaborate to Beat a Single Large Language Model?
Agata Żywot ⋅ Xinyi Chen ⋅ Yifei Yuan ⋅ Anders Søgaard ⋅ Maarten de Rijke
→ Verified Multi-Agent Orchestration: A Plan-Execute-Verify-Replan Framework for Complex Query Resolution
Xing Zhang ⋅ Yanwei CUI ⋅ Guanghui Wang ⋅ Qucy Qiu ⋅ Ziyuan Li ⋅ Fangwei Han ⋅ Yajing Huang ⋅ Hengzhi Qiu ⋅ Bing Zhu ⋅ Peiyang He
→ UT-Evolve: AN EVOLUTIONARY AGENT FOR UNIT TEST WRITING
Arshika Lalan ⋅ rajat ghosh ⋅ Debojyoti Dutta
→ AffectMind: Proactive Knowledge Grounding with Affective Multimodal Signals for Aligned Marketing Dialogue
Xinyu Wang ⋅ Xiaomin Zhao ⋅ Zhihao Lin ⋅ Xiang Luo ⋅ Zhang Chengbiao ⋅ Jin Cheng ⋅ Yixin Wang ⋅ Yangyang Zhang ⋅ Ernie Tian ⋅ Zhiguo Tao ⋅ Yifei Kang ⋅ Xiaofei Han ⋅ Xiaotong Ding
→ Self-Improvement of Language Models by Post-Training on Multi-Agent Debate
Ankur Samanta ⋅ Akshayaa Magesh ⋅ Runzhe Wu ⋅ Ayush Jain ⋅ Youliang Yu ⋅ Daniel Jiang ⋅ Boris Vidolov ⋅ Paul Sajda ⋅ Yonathan Efroni ⋅ Kaveh Hassani
→ MetroRehearsal: Tool-Guided Multi-Agent Debate for Metro Emergency Planning
Jinlin Li ⋅ Xiao Zhou ⋅ Yingying Zhang ⋅ Xian Wu
→ RPRA: Predicting an LLM-Judge for Efficient but Performant Inference
Dylan Ashley ⋅ Gael Le Lan ⋅ Changsheng Zhao ⋅ Naina Dhingra ⋅ zhipeng cai ⋅ Ernie Chang ⋅ Mingchen Zhuge ⋅ Yangyang Shi ⋅ Vikas Chandra ⋅ Jürgen Schmidhuber
→ EconAI: Dynamic Persona Evolution and Memory-Aware Agents inEvolving Economic Environments
Yijin Chen ⋅ Ning Lyu ⋅ Shengning Lang ⋅ Hao Yan ⋅ Zhiguo Tao ⋅ Xiaotong Ding ⋅ Xiaotong Zhu
→ AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization
Genghan Zhang ⋅ Shaowei Zhu ⋅ Anjiang Wei ⋅ Zhenyu Song ⋅ Allen Nie ⋅ Zhen Jia ⋅ Nandita Vijaykumar ⋅ Yida Wang ⋅ Kunle Olukotun
→ EvoCF: Multi-Agent Collaboration via Agentic Memory-Driven Evolutionary Counterfactual Planning
Haotian Chi ⋅ Zeyu Feng ⋅ Xingrui Yu ⋅ Linbo Luo ⋅ Yew-Soon Ong ⋅ Ivor Tsang ⋅ Hechang Chen ⋅ Yi Chang ⋅ Haiyan Yin
→ AI Organizations Are More Effective but Less Aligned than Individual Agents
Judy Shen ⋅ Daniel Zhu ⋅ Siddarth Srinivasan ⋅ Henry Sleight ⋅ Lawrence Wagner ⋅ Morgan Matthews ⋅ Jascha Sohl-Dickstein ⋅ Erik Jones