Evolve Together, Fall into Place: How Social Scaffolding Shapes Self-Evolving Multi-Agent Systems
cs.CL
Submitted: 2026-10-14
Updated: 2026-10-14
Comments: 35 pages, 27 tables, Figure 2
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Conformity and Social Impact on AI Agents
- Large Language Models Exhibit Normative Conformity
- Multi-Agent Evolve: LLM Self-Improve through Co-evolution
- Herd Behavior: Investigating Peer Influence in LLM-based Multi-Agent Systems
- An Empirical Study of Group Conformity in Multi-Agent Systems
- Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense
- Conformity Dynamics in LLM Multi-Agent Systems: The Roles of Topology and Self-Social Weighting
- Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems
- MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks
- Evolving Deeper LLM Thinking
- Meta-Harness: End-to-End Optimization of Model Harnesses
- SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
- Synthesizing Multi-Agent Harnesses for Vulnerability Discovery
- EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents
- AutoHarness: improving LLM agents by automatically synthesizing a code harness
- Three AI-agents walk into a bar . . . . `Lord of the Flies' tribalism emerges among smart AI-Agents
- OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning
- AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning
- Multi-Agent Teams Hold Experts Back
- Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering