Format
CLaRAMAS is a 1-day workshop hosted by AAMAS’26 taking place on May 26th at the Coral Beach Hotel & Resort in the wonderful city of Paphos, Cyprus. Travel information is available from the dedicated AAMAS’26 page.
The workshop features the following activities:
- 1 invited talk by Prof. Emiliano Lorini, leading expert in causal reasoning and engineering of agent systems (morning)
- oral presentations for all the accepted full and short papers split into topic-based sessions spanning both the morning and the afternoon, and each followed by a Q&A window
- 2 poster sessions for papers accepted as extended abstracts (see the submission page), planned during the coffee breaks
- a working activity with focus groups assembled during the day, depending on participants’ interests (scheduled dynamically, but most probably at the end of the afternoon session)
The focus groups have separate, “hands-on” brainstorming sessions meant to pinpoint the most promising research directions to be pursued within the AAMAS community, the most pressing challenges to be dealt with, and the open issues still needing clarification, with the aim of collaboratively drafting a white paper on causal learning and reasoning in agents and MAS.
Schedule
The workshop takes place in room APHRODITE A.
The table below reports the bird’s-eye view schedule of the workshop, indicating the time slots during which the different activities will happen.
| When | Duration | What | Where |
|---|---|---|---|
| 8:45-9:00 | 👋 Opening | Aphrodite A | |
| 9:00-9:45 | (45’) | 👨🎓 Keynote (Prof. Emiliano Lorini) | Aphrodite A |
| 9:45-10:15 | (30’) | Short papers I | Aphrodite A |
| 10:15-11:00 | (45’) | Posters I 🏞️ (during coffee break ☕) | Aphrodite A |
| 11:00-11:15 | (15’) | Short papers II | Aphrodite A |
| 11:15-12:30 | (75’) | Full papers I | Aphrodite A |
| 12:30-14:00 | (90’) | 👩🏻🍳 Lunch break 🤌🏻 | Aphrodite A |
| 14:00-15:15 | (75’) | Full papers II | Aphrodite A |
| 15:15-15:30 | (15’) | Introduction to focus groups | Aphrodite A |
| 15:30-16:15 | (45’) | Posters II 🏞️ (during coffe break ☕) | Aphrodite A |
| 16:15-17:30 | (75’) | 🧠 Focus groups ✍ | Aphrodite A |
| 17:30 | Closing 👋 | Aphrodite A |
Every poster will be on display during every coffee break :)
- Causes and Strategies in Multiagent Systems, by Sylvia S. Kerkhove; Mehdi Dastani; Natasha Alechina
- Abstract Counterfactuals for Language Model Agents, by Edoardo Pona; Milad Kazemi; Yali Du; David Watson; Nicola Paoletti
- Risk Perspectives in Multi-agents AI Systems for High-Risk Processes in Complex Environments, by André Meyer-Vitali; Rodica Mihai
- Causal Expectations for Decentralised Coordination in Multi-Agent Systems, by John R. E. Mills; Peter R. Lewis
The table below further details which paper is allocated to which slot.
⚠️ Although PDFs of accepted papers and posters are already available on OpenReview, they will be linked here as soon as they are updated with author details. ⚠️
| Paper title | Session | Starting at | Paper authors |
|---|---|---|---|
| Multi-Agent Causal Reasoning Framework: Optimizing Advertising Incrementality via Daily Budget Allocation Under a Fixed Lifetime Budget | Short papers I | 9:45 | Paul Lo; Jing Pan; Jingxi Yu; Evelyn Wu; Erte Pan; Simon Hollands |
| Collaborative Causal Discovery in a Synthetic Environment: Empirical Evaluation of FLODO | Short papers I | 10:00 | André Meyer-Vitali; Matteo Gregorini |
| Causal Expectations for Decentralised Coordination in Multi-Agent Systems | Short papers II | 11:00 | John R. E. Mills; Peter R. Lewis |
| Causal Learning and Reasoning in Multi-Agent Systems: Goals, Issues, and Taxonomy | Full papers I | 11:15 | Stefano Mariani; Giovanni Briglia; André Meyer-Vitali; Matthias Klusch; Franco Zambonelli |
| From Implicit to Explicit Causal Models in BDI Agents: A Proof-of-Concept with Causal Discovery and Adaptive Policy | Full papers I | 11:40 | Meltem Gullusac; Baris Tekin Tezel; Moharram Challenger |
| Evolutionary Learning of Graphical Causal Models from Behavior | Full papers I | 12:05 | H. Van Dyke Parunak |
| Value Identifiable, Credit Not: A Credit-First Identifiability Frontier for Confounded Sequential Decision-Making | Full papers II | 14:00 | Teresa Zhang |
| Reproducing and Extending Counterfactual Data Augmentation: A Study on Causal Identifiability and Stability in Reinforcement Learning | Full papers II | 14:25 | Shilpa Noushad; Sajan Kumar; Pratyush uppuluri |
| CoACT: Coordination via Aligned Centralized Training in Multi-Agent Reinforcement Learning | Full papers II | 14:50 | Oussama Azizi; Frans A Oliehoek; Matthijs T. J. Spaan |