Accepted Papers

ICLR 2026 Workshop on Multi-Agent Learning and Generative AI

April 27, 2026 | Rio de Janeiro, Brazil

About
Call for Papers
Speakers
Schedule
Organizers
Accepted Papers

Oral Presentations

16 papers

1 EconAI: Dynamic Persona Evolution and Memory-Aware Agents in Evolving Economic Environments
2 GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory
3 AI Organizations Are More Effective but Less Aligned than Individual Agents
4 The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind
5 CooperBench: Benchmarking Cooperation in Coding Agents
6 ComplLLM: Fine-tuning LLMs to Discover Complementary Signals for Decision-making
7 AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization
8 Zero-Shot Coordination among LLM Agents
9 Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic
10 Evaluating Cooperation in LLM Social Groups through Self-Organizing Leadership
11 Group Distributionally Robust Optimization-Driven RL for LLM Reasoning
12 Expanding the Capabilities of Reinforcement Learning via Text Feedback
13 Team of Thoughts: Efficient Test-time Scaling of Agentic Systems through Orchestrated Tool Calling
14 ArchPilot: A Proxy-Guided Multi-Agent Approach for Machine Learning Engineering
15 Evaluating LLM Agents as Human Simulators in Climate Social Dilemmas
16 Build, Judge, Optimize: A Blueprint for Continuous Improvement of Multi-Agent Consumer Assistants

Poster Presentations

41 papers

1 Talk Before You Retrieve: Agent-Led Discussions for Better RAG in Medical QA
2 Multi-Agent Consensus Matrix Modeling for Medical Decision-Making: A Role-Specialized LLM Framework for Oncology MDT Consultations
3 AffectMind: Proactive Knowledge Grounding with Affective Multimodal Signals for Aligned Marketing Dialogue
4 Beyond Syntax: Action Semantics Learning for App Agents
5 Do Language Models Deceive? Strategic Behavior and Emergent Deception in Multi-Agent Auctions
6 Explanations are a Means to an End: Decision Theoretic Explanation Evaluation
7 Reasonably reasoning agents avoid game-theoretic failures in zero-shot, provably
8 EvoCF: Multi-Agent Collaboration via Agentic Memory-Driven Evolutionary Counterfactual Planning
9 Beyond Text-Passing: Shared Cognitive Substrates for Multi-Agent LLM Coordination
10 Let’s Talk, Not Type: An Oral-First Multi-Agent Architecture for Guarani
11 RPRA: Predicting an LLM-Judge for Efficient but Performant Inference
12 MetroRehearsal: Tool-Guided Multi-Agent Debate for Metro Emergency Planning
13 Can Small Agents Collaborate to Beat a Single Large Language Model?
14 JaxAHT: A JAX-Based Library for Ad Hoc Teamwork
15 Verified Multi-Agent Orchestration: A Plan-Execute-Verify-Replan Framework for Complex Query Resolution
16 MAPLE: Multi-Agent Prior Learning for Constructing Tree Ensembles
17 Heterogeneous Low-Bandwidth Pre-Training of LLMs
18 Not All Clients Are Equal: Collaborative Model Personalization on Heterogeneous Multi-Modal Clients
19 Self-Questioning Language Models
20 AI-BAAM: AI-Driven Bank Statement Analytics as Alternative Data for Malaysian MSME Credit Scoring
21 SkillTracer: Structural Failure Attribution and Refinement of Agentic Skills in Long-Horizon Web Tasks
22 Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems
23 Safe Test-Time Reinforcement learning for Imperfect Information Games
24 Asymptotic Universal Alignment: A New Alignment Framework via Test-Time Scaling
25 How Communication Modalities Shape Topology in Generative Multi-Agent Systems
26 Cattle Trade: A Multi-Agent Benchmark for LLM Bluffing, Bidding, and Negotiation
27 Learning the Preferences of a Learning Agent
28 UT-Evolve: An Evolutionary Agent for Unit Test Writing
29 Simulating Human Decision-Making During Disasters in Dynamic Environments
30 Outbidding and Outbluffing Elite Humans: Mastering Liar’s Poker via Self-Play and Reinforcement Learning
31 Scaling Inference-Time Computation via Opponent Simulation: Enabling Online Strategic Adaptation in Repeated Negotiation
32 Federation over Text
33 Divide-and-Conquer CoT: RL for Reducing Latency via Parallel Reasoning
34 Interpretable Multi-Agent Debate for Political Opinion Simulation
35 Novelty-Gated Experience Sharing for Multi-Agent Reinforcement Learning
36 LaneRoPE: Positional Encoding for Collaborative Parallel Reasoning and Generation
37 Self-Improvement of Language Models by Post-Training on Multi-Agent Debate
38 Assessing Sovereignty in Multi-Agent Collaborations
39 CORAL: Cooperative Multi-Agent Orchestration for LLM Adaptation Across Diverse Environments
40 MAGIC: Multi-Agent Generative Intention Coordination
41 Agent-as-a-Coach: Towards Fully Agentic, Stateful, and Tool-Augmented Process Rewards

© 2025-2026 ICLR Workshop on Multi-Agent Learning and Generative AI.