Global Coherence: When Every Agent Is Right and the Team Is Still Wrong - A Local-to-Global Semantic Foundation for Multi-Agent Collaboration
cs.AI
Submitted: 2026-10-01
Updated: 2026-10-15
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Sheaf theory: from deep geometry to deep learning
- $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
- A Mathematical Theory of Co-Design
- Hypergraph Categories
- SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
- TeamBench: Evaluating Agent Coordination under Enforced Role Separation
- AgentBench: Evaluating LLMs as Agents
- GAIA: a benchmark for General AI Assistants
- Toolformer: Language Models Can Teach Themselves to Use Tools
- Functorial Data Migration
- OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
- ReAct: Synergizing Reasoning and Acting in Language Models
- WebArena: A Realistic Web Environment for Building Autonomous Agents
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems