arXiv AI
From Solo to Social Learning: Characterizing Recursive Social Improvement in LLMs
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 3
SAGE: A Quantitative Evaluation of Socialized Evolution in Agent Ecosystems
arXiv:2606. 03544v1 Announce Type: new Abstract: Self-improving language agents are typically evaluated in isolation: an agent attempts a task, receives feedback, and iteratively refines its own behavior.
arXiv AI
Aug 11
Social Gym and SPaRTan: Benchmarking and Improving LLM Social Reasoning via Multi-Agent Game Tournaments
arXiv:2608. 09128v1 Announce Type: cross Abstract: LLM agents are increasingly deployed in multi-agent social settings where they must cooperate, negotiate, and adapt to other agents.
arXiv AI
Jul 17
Collaborative Spatial Learning with Multi-LLM Agents in Networked Social Experiments
arXiv:2607. 14574v1 Announce Type: new Abstract: Collective problem solving often requires that group members consider the tradeoff between exploitation of known solutions and exploration for new ones, where information of known solutions can be disseminated among individual members through communication networks.
arXiv AI
4d ago
SelfSearch: Reward-Free Search for Self-Improving Agents
arXiv:2609. 37968v1 Announce Type: new Abstract: Advances in the coding capabilities of LLM agents allow them to inspect and modify their own instructions, tools, and execution procedures.
arXiv AI
Jul 7
MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution
arXiv:2607. 05297v1 Announce Type: new Abstract: Recent LLM agents tackle increasingly long-horizon, open-ended tasks, and external skills, reusable procedural knowledge supplied to the agent, further extend this capability.
arXiv AI
3d ago
CollabFlow: Recursive Self-Improvement of Agent Collaboration
CollabFlow introduces a recursive self‑improvement framework for multi‑agent collaboration in large language model systems. It trains a Collab‑Director to assemble teams of agents, uses a frozen executor to run them, and retrains the director each round based on outcomes. The system incorporates evidence‑conditioned communication protocols within collaboration graphs and a Collaborative Trajectory Balance objective to maintain diverse high‑performing teams across rounds, achieving superior performance on twelve datasets.