CollabFlow: Recursive Self-Improvement of Agent Collaboration
cs.MA, cs.AI
Submitted: 2026-09-29
Updated: 2026-09-29
Sources
- Evaluating Large Language Models Trained on Code
- Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops
- COLLATOR: Compositional Multi-Agent Orchestration with Counterfactual Reinforcement Learning
- What Do Agents Communicate? Characterizing Information Exchange in Multi-Agent Systems
- Improving Factuality and Reasoning in Language Models through Multiagent Debate
- Dynamic Trust-Aware Sparse Communication Topology for LLM-Based Multi-Agent Consensus
- MOC: Multi-Order Communication in LLM-based Multi-Agent Systems
- MANTA: Multi-Agent Network Topology Adaptation for Self-Evolving Multi-Agent Systems
- When Evidence Shapes Collaboration: Knowledge-Conditioned Topology Generation for Multi-Agent Systems
- Beyond Mode Collapse: Distribution Matching for Diverse Reasoning
- Beyond tokens: a unified framework for latent communication in LLM-based multi-agent systems
- A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration
- Multi-Agent Debate Strategies: Survey, Taxonomy, and Challenges
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
- Response-Conditioned Parallel-to-Sequential Orchestration for Multi-Agent Systems
- AgentConductor: Topology Evolution for Multi-Agent Competition-Level Code Generation
Related papers
- Highway Congestion Reduction through Reinforcement Learning Based Eulerian Headway Control
- ORACLE-SWE: Quantifying the Contribution of Critical Information Signals on SWE Agents
- You Only Align Once: Propagating Cooperative Behaviors in Multi-Agent Systems through Seed Agents
- Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems
- MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization
- PeroMAS: A Multi-agent System of Perovskite Material Discovery