From Solo to Social Learning: Characterizing Recursive Social Improvement in LLMs
cs.MA, cs.AI, cs.LG
Submitted: 2026-09-29
Updated: 2026-10-01
Code: https://github.com/nanocoai/nanoclaw
Sources
- X-Armed Bandits
- The Gossiping Insert-Eliminate Algorithm for Multi-Agent Bandits
- Improving Factuality and Reasoning in Language Models through Multiagent Debate
- Physics of Agents: Statistical Mechanics Predicts Collective Behavior of AI Agents
- Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence
- Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
- GLM-5: from Vibe Coding to Agentic Engineering
- EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers
- MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
- Automated Design of Agentic Systems
- Tapes Together Strong: The Co-evolution of Computation and Cooperation
- DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
- Multi-Agent Transactive Memory
- Towards a Science of Scaling Agent Systems
- Multi-Armed Bandits in Metric Spaces
- Collaborative Learning of Stochastic Bandits over a Social Network
- Distributed Cooperative Decision-Making in Multiarmed Bandits: Frequentist and Bayesian Algorithms
- CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
- More Agents Is All You Need
- Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents
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