# From Solo to Social Learning: Characterizing Recursive Social Improvement in LLMs

arXiv: https://arxiv.org/abs/2609.38516 · HTML: https://mlsanity.com/paper/2609.38516/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 30 of its 61 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 30 of 30)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://mlsanity.com/paper/2505.22954/) (2025)
- [Generalizing Verifiable Instruction Following](https://mlsanity.com/paper/2507.02833/) (2025)
- [EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers](https://mlsanity.com/paper/2309.08532/) (2023)
- [More Agents Is All You Need](https://mlsanity.com/paper/2402.05120/) (2024)
- [Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents](https://mlsanity.com/paper/2404.16698/) (2024)
- [Language Agents as Optimizable Graphs](https://mlsanity.com/paper/2402.16823/) (2024)
- [Distributed Cooperative Decision-Making in Multiarmed Bandits: Frequentist and Bayesian Algorithms](https://mlsanity.com/paper/1606.00911/) (2016)
- [Emergent Social Learning via Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2010.00581/) (2020)
- [A Survey of In-Context Reinforcement Learning](https://mlsanity.com/paper/2502.07978/) (2025)
- [The Gossiping Insert-Eliminate Algorithm for Multi-Agent Bandits](https://mlsanity.com/paper/2001.05452/) (2020)
- [Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents](https://mlsanity.com/paper/2605.30621/) (2026)
- [Collaborative Learning of Stochastic Bandits over a Social Network](https://mlsanity.com/paper/1602.08886/) (2016)
- [Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence](https://mlsanity.com/paper/2410.11163/) (2024)
- [Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems](https://mlsanity.com/paper/2502.04510/) (2025)
- [Group size effects and collective misalignment in LLM multi-agent systems](https://mlsanity.com/paper/2510.22422/) (2025)
- [Social Learning: Towards Collaborative Learning with Large Language Models](https://mlsanity.com/paper/2312.11441/) (2023)
- [LLM-Based Multi-Agent Blackboard System for Information Discovery in Data Science](https://mlsanity.com/paper/2510.01285/) (2025)
- [Cultural evolution in populations of Large Language Models](https://mlsanity.com/paper/2403.08882/) (2024)
- [Social learning strategies modify the effect of network structure on group performance](https://mlsanity.com/paper/1606.00753/) (2016)
- [Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning](https://mlsanity.com/paper/2406.00392/) (2024)
- [Scaling Discovery through Test-Time Communication](https://mlsanity.com/paper/2609.21032/) (2026)
- [Physics of Agents: Statistical Mechanics Predicts Collective Behavior of AI Agents](https://mlsanity.com/paper/2608.16578/) (2026)
- [Interactive Restless Multi-armed Bandit Game and Swarm Intelligence Effect](https://mlsanity.com/paper/1503.03964/) (2015)

## Abstract (arXiv)

Large language models (LLMs) can now improve themselves by revising the instructions they follow, and LLM agents are increasingly orchestrated to work together on complex problems. However, self-improvement methods typically optimize one system at a time, and multi-agent frameworks often have every model work toward a shared goal. We ask a different question. When each agent pursues its own reward, can self-improving LLMs learn from one another well enough to improve the whole population? We call this capability recursive social improvement. We study populations that revise skill files and choose whether, when, and whom to copy from. Independent search, learning from peers, and acting all share one token budget. In controlled environments, established social-learning algorithms benefit from peers, but three LLMs do not. They earn less reward per token than solo learners, and explore too narrowly or run out of tokens before acting. We then let the models write and revise their own skills. Observing peers changes how they improve, helping one model find useful skills sooner and another spend less on private search. Neither, however, outperforms independent learners at the same cost. Skills are copied, revised, and passed on, so one discovery can seed further search. Yet these exchanges concentrate the population around fewer independent discoveries. Together, these results show that LLMs can make learning more efficient by copying from peers, but not yet more effective.