Get Started
Research questionHow can agent runtimes avoid context poisoning and latency from growing histories during long-horizon skill execution?Long-running agents often append observations, actions, and intermediate reasoning to their conversation history. As that history grows, execution becomes slower and earlier context can interfere with later decisions.
AI Agents
AI Memory
Inference Optimization
Latest papersRecent research connected to this question, newest first.SKILL.state: Scalable Long-Horizon Agent SkillsThe source concerns LLM-based autonomous agents performing long-running procedural skills and reports evidence across diverse datasets, models, and execution environments, including task accuracy and cumulative token consumption.research paper · Sep 2, 2026
Related questions
How can LLM agents reuse procedural skills across diverse long-horizon tasks without generic or instance-bound memory?How can LLM agents jointly adapt reasoning policies and hierarchical skill libraries during reinforcement learning?How can LLM agents retrieve relevant skills from large, noisy libraries under context and latency constraints?How can LLM agents reuse execution traces without losing temporal and outcome-dependent behavior?
Home
Topics
Search
Library