Papers

Filtered to multi-agent systems · clear filter

Browse by term

continual learning 91reinforcement learning 43vision-language models 18benchmarking 12benchmarks 11robotics 11large language models 10language models 9world models 9video generation 6generative models 5multimodal models 5natural language processing 5recursive self-improvement 5video world models 5agents 4dialogue systems 4diffusion models 4foundation models 4multimodal large language models 4on-policy distillation 4reasoning 4self-distillation 4self-supervised learning 4conversational AI 3evaluation benchmarks 3human-computer interaction 3LLMs 3multi-agent systems 3policy optimization 3

Matching papers

DynaFlow: Learning Free-Form Multi-Agent Orchestration

182 upvotes · 25 OCT 2026 · Ruhao Liu, Qi Li, Shizun Wang et al.

This paper introduces DynaFlow, a framework that enables multi-agent systems to adapt to diverse task requirements by learning to orchestrate sub-agents in a free-form way. Practitioners might care about DynaFlow because it can improve the flexibility and performance of multi-agent systems in real-world applications.

reinforcement learningmulti-agent systemsworkflow synthesisexecutable programmingaction spacetask orchestration

Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design

123 upvotes · 10 AUG 2026 · Qing Zong, Jiayu Liu, Junhao Shen et al.

This paper explores how agentic systems can improve on their own through co-evolution, where multiple agents and their environment adapt to each other, and discusses the challenges and benefits of building such systems that can learn beyond human design.

agentic systemsco-evolutionself-directed evolutioncontinual learningmulti-agent systemsadaptive pressure

AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems

92 upvotes · 8 SEP 2026 · Jaewon Chu, Jinwoo Seo, Jaewon Cho et al.

This paper proposes a method to optimize prompts for multi-agent systems by identifying which agent's modification resolves a failure, and then using that agent's output as supervision to extract a fine-grained gradient. Practitioners might care because it could improve the performance of large language model-based multi-agent systems.

multi-agent systemsprompt optimizationtextual gradient methodscontinual learningbenchmarks