Theory of Scene: Breaking the Symmetry Trap in Multi-Agent LLM Coordination
cs.LG, cs.CL, cs.MA
Submitted: 2026-09-26
Updated: 2026-09-26
Terminology
Sources
- Melting Pot 2.0
- Tacit Coordination of Large Language Models
- Ripple Effect Protocol: Coordinating Agent Populations
- AgentsNet: Coordination and Collaborative Reasoning in Multi-Agent LLMs
- Gated Coordination for Efficient Multi-Agent Collaboration in Minecraft Game
- TeamBench: Evaluating Agent Coordination under Enforced Role Separation
- Systematic Failures in Collective Reasoning under Distributed Information in Multi-Agent LLMs
- The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind
- Randomness is sometimes necessary for coordination
- Benchmarking Open-Ended Multi-Agent Coordination in Language Agents
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks