AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents

ArXi:2603.27490v1 Announce Type: cross As large language models (LLMs) evolve into autonomous agents for long-horizon information-seeking, managing finite context capacity has become a critical bottleneck. Existing context management methods typically commit to a single fixed strategy throughout the entire trajectory. Such static designs may work well in some states, but they cannot adapt as the usefulness and reliability of the accumulated context evolve during long-horizon search. To formalize this challenge, we.