arXiv AI
Federation over Text: Insight Sharing for Multi-Agent Reasoning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 16
Learning to Share: Selective Memory for Efficient Parallel Agentic Systems
arXiv:2602. 05965v2 Announce Type: replace-cross Abstract: Agentic systems solve complex tasks by coordinating multiple agents that iteratively reason, invoke tools, and exchange intermediate results.
arXiv AI
Jun 4
Adaptive Minds: Empowering Agents with LoRA-as-Tools
arXiv:2510. 15416v2 Announce Type: replace Abstract: We investigate a framework in which LoRA adapters are treated as callable tools that a base language model can dynamically select and invoke.
arXiv AI
Aug 24
Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning
The paper introduces a method to improve test-time scaling (TTS) for large language models by using multi-agent systems (MAS) to split long reasoning chains into manageable contexts. A new dataset, M500, containing 500 multi-agent collaborative reasoning traces, is used to fine‑tune open‑source models, enabling them to learn collaborative patterns and outperform their base versions. An adaptive scaling strategy with a "CEO" agent is proposed to dynamically guide reasoning depth, and experiments in the AgentVerse framework confirm the effectiveness of the approach.
arXiv Machine Learning
Jun 3
FederatedSkill: Federated Learning for Agentic Skill Evolution
arXiv:2606. 03143v1 Announce Type: new Abstract: Modern LLM agents increasingly rely on skill libraries to handle complex tasks, making skill evolution a primary driver of self-improvement.
arXiv AI
Sep 1
RACER: Reinforced Agent Collaboration for Explainable Reasoning on Knowledge Graphs
arXiv:2608.29263v1 Announce Type: new Abstract: Large Language Models (LLMs) often suffer from hallucination and struggle with complex reasoning tasks requiring multi-hop domain knowledge. While inte...
arXiv AI
Sep 10
AMA: Adaptive Memory via Multi-Agent Collaboration
The paper introduces AMA, a framework that uses multiple agents—Constructor, Retriever, Judge, and Refresher—to manage memory for large language model agents. AMA’s hierarchical memory design dynamically adjusts retrieval granularity to match task complexity, while the Judge and Refresher ensure relevance, consistency, and timely updates. Experiments on long-context benchmarks show AMA outperforms existing baselines and cuts token usage by about 80% compared to full-context approaches.