DAI-25 Paper Sessions

Venue: King’s College London – Strand Campus

Registration Location

  • Registration takes place at the Reception Desk on the Ground Floor of the Strand Building, located to the right of the main entrance.

Building

  • King’s Building – Great Hall

Note

  • All paper sessions on Nov 23–24 take place in the Great Hall, King’s Building.

Room Number Format

Example: KIN G01

  • KIN – Building identification code (King’s Building)
  • G – Level indicator (LG1, G, 2, 4, 6, etc.)
  • 01 – Individual room number

Key Rooms (By Room Names)

Location Level Room
Council Room2KIN 214
Great HallGKIN G33
River Room2KIN 227
Small Committee RoomGKIN G21

Campus Map (Strand – King’s Building)

King's College London Strand Campus map - King's Building

Click the map to open the King’s Building visitor page on kcl.ac.uk.

Program At a Glance

  • Nov 21 (Fri) – Workshops & Tutorials
  • Nov 22 (Sat) – Workshops & Tutorials
  • Nov 23 (Sun) – DAI Paper Sessions & Invited Papers
  • Nov 24 (Mon) – DAI Paper Sessions & Invited Papers
For time slots and rooms, please refer to the full schedule using the buttons below.
For the full timetable of the conference, please see the schedule pages:
Conference Schedule (Nov 21–24) Workshops & Tutorials (Nov 21–22)

Subsession Catalog

23 Sun (DAI papers)

Session: Fundamental Methods for DAI

Chair: Roxana Radulescu
Location: Great Hall, King's Building
  1. Experimental Evaluation of a Decentralized Protocol for Emergent Heartbeat Synchronization 10:30 - 10:45
    Federico Bergenti and Stefania Monica
  2. SAC-B:Soft Actor-Critic with Bias for Suppressing Q-value Overestimation in Off-Policy Reinforcement Learning 10:45 - 11:00
    Han Wang, Wei Du, Yanyu Xu and Lizhen Cui
  3. Efficient Decision Sequence Modeling via Feature-Level Masking 11:00 - 11:15
    Xinzhi Zhang, Yifan Gao, Yaqing Hou, Xuechuan Liu, Zengyang Wang, Yi Cai, Bo An and Mengchen Zhao
  4. Learning Embodied Quadruped Agents for Posture-Aware Locomotion 11:15 - 11:30
    Xiangyu Miao, Jun Sun, Hang Lai, Xinpeng Di, Jiahang Cao, Yong Yu and Weinan Zhang

Session: Applications and LLMs

Chair: Yuanheng Zhu
Location: Great Hall, King's Building
  1. Towards Compliant and Trustworthy Data Markets for Distributed AI 11:45 - 12:00
    Soulmaz Gheisari, Jaime Osvaldo Salas and George Konstantindis
  2. Reasoning with Commonsense Knowledge and Decision Heuristics for Ad hoc Human-Agent Collaboration 12:00 - 12:15
    Hasra Dodampegama and Mohan Sridharan
  3. Incentivizing Permissionless Distributed Learning of LLMs 12:15 - 12:30
    Joel Lidin, Amir Sarfi, Evangelos Pappas, Samuel Dare, Eugene Belilovsky and Jacob Steeves
  4. Beyond GPT-5: Making LLMs Cheaper and Better via Performance–Efficiency Optimized Routing 12:30 - 12:45
    Yiqun Zhang, Hao Li, Jianhao Chen, Hangfan Zhang, Peng Ye, Lei Bai and Shuyue Hu

23 Sun (invited papers)

Session: Invited Papers: Game Theory and Cooperation 1

Chair: Ndidi Bianca Ogbo
Location: Great Hall, King's Building
  1. Co-Learning of Strategy and Structure Achieves Full Cooperation in Complex Networks with Dynamical Linking 16:00 - 16:15
    Xiaoqing Fan, Chin-wing Leung, Paolo Turrini
  2. Emergent Cooperation under Uncertain Incentive Alignment 16:15 - 16:30
    Nicole Orzan, Erman Acar, Davide Grossi, Roxana Rădulescu
  3. Convex Markov Games: A New Frontier for Multi-Agent Reinforcement Learning 16:30 - 16:45
    Ian Gemp, Andreas Haupt, Luke Marris, Siqi Liu, Georgios Piliouras

Session: Invited Papers: Safety in DAI

Chair: Ian Gemp
Location: Great Hall, King's Building
  1. Trust AI Regulation? Discerning Users are Vital to Build Trust and Effective AI Regulation 17:00 - 17:15
    Zainab Alalawi, Paolo Bova, Theodor Cimpeanu, Alessandro Di Stefano, Manh Hong Duong, Elias Fernández Domingos, The Anh Han, Marcus Krellner, Ndidi Bianca Ogbo, Simon T Powers, Filippo Zimmaro
  2. Learning to Be Cautious 17:15 - 17:30
    Montaser Mohammedalamen, Dustin Morrill, Alexander Sieusahai, Yash Satsangi, Michael Bowling
  3. Learning Collusion in Episodic, Inventory-Constrained Markets 17:30 - 17:45
    Paul Friedrich, Barna Pasztor, Giorgia Ramponi
  4. Secret Collusion among AI Agents: Multi-Agent Deception via Steganography 17:45 - 18:00
    Sumeet Ramesh Motwani, Mikhail Baranchuk, Martin Strohmeier, Vijay Bolina, Philip H.S. Torr, Lewis Hammond, Christian Schroeder de Witt

24 Mon (DAI papers)

Session: Game Theory

Chair: Bo An
Location: Great Hall, King's Building
  1. Stable Marriages via Social Relationship 10:30 - 10:45
    Miao Li, Xinwei Song and Dengji Zhao
  2. Direct Optimization of Portfolios of Counter Strategies 10:45 - 11:00
    Karolina Drabent and Viliam Lisý
  3. A Novel Sample-Based Best Response Dynamics for Solving Nash Equilibrium in Continuous Games 11:00 - 11:15
    Zhouming Wu, Xu Xia and Yifen Mu
  4. Evolution of Coordination Through Institutional Incentives: An Evolutionary Game Theory Approach 11:15 - 11:30
    Ndidi Bianca Ogbo, Zhao Song and The Anh Han

Session: Multiagent Reinforcement Learning

Chair: Christian Schroeder de Witt
Location: Great Hall, King's Building
  1. Orchestrating Human-AI Teams: The Manager Agent as a Unifying Research Challenge 11:45 - 12:00
    Charlie Masters, Advaith Vellanki, Jiangbo Shangguan, Bart Kultys, Alastair Moore and Stefano Albrecht
  2. AGOD: Enhancing Multi-Agent Generalization via Attribution-Guided Observation Dropout 12:00 - 12:15
    Wei Wei, Binchao Ma, Lin Li, Huizhong Song, Lijun Zhang and Fengjiao Li
  3. ARAC: Adaptive Regularized Multi-Agent Soft Actor-Critic in Graph-Structured Adversarial Games 12:15 - 12:30
    Ruochuan Shi, Runyu Lu, Yuanheng Zhu and Dongbin Zhao
  4. SIGMA: A Dual-Agent Reinforcement Learning-Optimized Framework for Graph Classification 12:30 - 12:45
    Xinbang Cheng, Haodong Qian, Yisen Gao, Xincheng Fu and Rongye Shi

24 Mon (invited papers)

Session: Invited Papers: Game Theory and Cooperation 2

Chair: The Anh Han
Location: Great Hall, King's Building
  1. Evolution Favours Positively Biased Reasoning in Sequential Interactions with High Future Gains 16:00 - 16:15
    Marco Saponara, Elias Fernández Domingos, Jorge M. Pacheco, Tom Lenaerts
  2. Learning Fair Cooperation in Mixed-Motive Games with Indirect Reciprocity 16:15 - 16:30
    Martin Smit, Fernando P. Santos
  3. On the Complexity of Learning to Cooperate with Populations of Socially Rational Agents 16:30 - 16:45
    Saptarashmi Bandyopadhyay, Mustafa Mert Çelikok, Robert Loftin

Session: Invited Papers: Novel DAI Approaches

Chair: Tianpei Yang
Location: Great Hall, King's Building
  1. AIArena: A Blockchain-Based Decentralized AI Training Platform 17:00 - 17:15
    Zhipeng Wang, Rui Sun, Elizabeth Lui, Tuo Zhou, Yizhe Wen, Jiahao Sun
  2. DICE: Data Influence Cascade in Decentralized Learning 17:15 - 17:30
    Tongtian Zhu, Wenhao Li, Can Wang, Fengxiang He
  3. Generative Agents for Multi-Agent Autoformalization of Interaction Scenarios 17:30 - 17:45
    Agnieszka Mensfelt, Kostas Stathis, Vince Trencsenyi
  4. Semantic Temporal Abstraction via Vision-Language Model Guidance for Efficient Reinforcement Learning 17:45 - 18:00
    Tian-Shuo Liu, Xu-Hui Liu, Ruifeng Chen, Lixuan Jin, Pengyuan Wang, Zhilong Zhang, Yang Yu