Papers

Filtered to multi-agent · clear filter

Browse by term

continual learning 64reinforcement learning 34large language models 17benchmarking 12vision-language models 10generative models 8language models 8video generation 7multimodal models 6natural language processing 6robotics 6world models 6benchmarks 5diffusion models 5on-policy distillation 5policy optimization 5scalability 5self-distillation 5vision-language-action models 5autoregressive models 4computer vision 4diffusion transformers 4LLMs 4multimodal large language models 4verifiable rewards 4attention mechanisms 3embodied intelligence 3image editing 3long-term memory 3multimodal learning 3

Matching papers

StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents

51 upvotes · 24 JUL 2026 · Yan Yang, Xiangru Jian, Ziyang Luo et al.

This paper introduces a new approach to training computer-use agents by directly interacting with the underlying program state, rather than relying on visual perception. By doing so, agents can reason more effectively and make fewer mistakes, which can lead to significant improvements in performance.

code-firstmulti-agentstate-groundingcomputer-use agentsOSWorld

Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers

12 upvotes · 23 JUL 2026 · Sicheng Mo, Yuheng Li, Ziyang Leng et al.

This paper introduces a new method for generating videos in multi-agent environments, where each agent has its own view of the world. It's useful for applications like video games or simulations where multiple agents need to interact with each other and the environment.

multi-agentautoregressive diffusion modelsworld statevideo generationscene understanding