ICLR 2026PastAgentsGenerative models
Workshop on Multi-Agent Learning and Its Opportunities in the Era of Generative AI
MALGAI
- Submission deadline
- Feb 11, 2026, 11:59 UTCOpenReview-synced 2026-02-11 11:59 UTC (as of 2026-06-23) — extensions on OpenReview are applied automatically; verify on the website.
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (57)
Fetched from OpenReview (v2) on 2026-06-10.
AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization
AffectMind: Proactive Knowledge Grounding with Affective Multimodal Signals for Aligned Marketing Dialogue
Agent-as-a-Coach: Towards Fully Agentic, Stateful, and Tool-Augmented Process Rewards
AI Organizations Are More Effective but Less Aligned than Individual Agents
AI-BAAM: AI-Driven Bank Statement Analytics as Alternative Data for Malaysian MSME Credit Scoring
ArchPilot: A Proxy-Guided Multi-Agent Approach for Machine Learning Engineering
Assessing Sovereignty in Multi-Agent Collaborations
Asymptotic Universal Alignment: A New Alignment Framework via Test-Time Scaling
Beyond Reasoning: RL-Policy Guided LLM Inference for Efficient Strategy in Liar’s Poker
BEYOND SYNTAX: ACTION SEMANTICS LEARNING FOR APP AGENTS
Beyond Text-Passing: Shared Cognitive Substrates for Multi-Agent LLM Coordination
Build, Judge, Optimize: A Blueprint for Continuous Improvement of Multi-Agent Consumer Assistants
Can Small Agents Collaborate to Beat a Single Large Language Model?
CATTLE TRADE: A MULTI-AGENT BENCHMARK FOR LLM BLUFFING, BIDDING, AND NEGOTIATION
ComplLLM: Fine-tuning LLMs to Discover Complementary Signals for Decision-making
CooperBench: Benchmarking Cooperation in Coding Agents
CORAL: Cooperative Multi-Agent Orchestration for LLM Adaptation Across Diverse Environments
Divide-and-Conquer CoT: RL for Reducing Latency via Parallel Reasoning
Do Language Models Deceive? Strategic Behavior and Emergent Deception in Multi-Agent Auctions
Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems
EconAI: Dynamic Persona Evolution and Memory-Aware Agents inEvolving Economic Environments
Evaluating Cooperation in LLM Social Groups through Elected Leadership
Evaluating LLM Agents as Human Simulators in Climate Social Dilemmas
EvoCF: Multi-Agent Collaboration via Agentic Memory-Driven Evolutionary Counterfactual Planning
Expanding the Capabilities of Reinforcement Learning via Text Feedback
Explanations are a Means to an End: Decision Theoretic Explanation Evaluation
Federation over Text
Group Distributionally Robust Optimization-Driven RL for LLM Reasoning
GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory
Heterogeneous Low-Bandwidth Pre-Training of LLMs
Hierarchical Generative Agents for Simulating Sequential Human Behavior
How Communication Modalities Shape Topology in Generative Multi-Agent Systems
Interpretable Multi-Agent Debate for Political Opinion Simulation
JaxAHT: A JAX-Based Library for Ad Hoc Teamwork
LaneRoPE: Positional Encoding for Collaborative Parallel Reasoning and Generation
Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic
Learning the Preferences of a Learning Agent
Let’s Talk, Not Type: An Oral-First Multi-Agent Architecture for Guarani
MAGIC: Multi-Agent Generative Intention Coordination
MAPLE: Multi-Agent Prior Learning for Constructing Tree Ensembles
MetroRehearsal: Tool-Guided Multi-Agent Debate for Metro Emergency Planning
Multi-Agent Consensus Matrix Modeling for Medical Decision-Making: A Role-Specialized LLM Framework for Oncology MDT Consultations
Not All Clients Are Equal: Collaborative Model Personalization on Heterogeneous Multi-Modal Clients
Novelty-Gated Experience Sharing for Multi-Agent Reinforcement Learning
Reasonably reasoning agents avoid game-theoretic failures in zero-shot, provably
RPRA: Predicting an LLM-Judge for Efficient but Performant Inference
Safe Test-Time Reinforcement learning for Imperfect Information Games
Scaling Inference-Time Computation via Opponent Simulation: Enabling Online Strategic Adaptation in Repeated Negotiation
Self-Improvement of Language Models by Post-Training on Multi-Agent Debate
Self-Questioning Language Models
SkillTracer: Structural Failure Attribution and Refinement of Agentic Skills in Long-Horizon Web Tasks
Talk Before You Retrieve: Agent-Led Discussions for Better RAG in Medical QA
Team of Thoughts: Efficient Test-time Scaling of Agentic Systems through Orchestrated Tool Calling
The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind
UT-Evolve: AN EVOLUTIONARY AGENT FOR UNIT TEST WRITING
Verified Multi-Agent Orchestration: A Plan-Execute-Verify-Replan Framework for Complex Query Resolution
Zero-Shot Coordination among LLM Agents