Get Started
Research questionHow can long-horizon LLM agents learn when to group actions without overcommitting?Long-horizon agents can spend many decisions executing routine sequences, but poorly learned chunk lengths can either waste decisions or carry out too many actions before adapting.
AI
AI Agents
Reinforcement Learning
Latest papersRecent research connected to this question, newest first.Act More, Decide Less: Skill-Guided Adaptive Action Chunking for Long-Horizon LLM AgentsThe evidence comes from experiments with LLM agents on ALFWorld and ScienceWorld, measuring task success and average LLM decision rounds. Broader environments and deployment conditions are not specified.research paper · Sep 2, 2026
Related questions
How can policy optimization for long-horizon LLM agents preserve useful transitions across updates when rollout groups are small?How can long-horizon LLM agents preserve answer quality under tight prompt-token budgets?How can multimodal language-model agents coordinate hidden prerequisites during long-horizon open-world exploration?How can LLM orchestrators preserve continuous state when collaborating with non-language agents?
Home
Topics
Search
Library