Revisiting Observation Reduction for Web Agents: Comprehensive Evaluation with a Lightweight Framework 事件

Revisiting Observation Reduction for Web Agents: Comprehensive Evaluation with a Lightweight Framework arXiv:2605.29397v1 Announce Type: new Abstract: HTML observations in LLM-based web agents are extremely long, and while many reduction methods have been proposed, it remains unclear which methods reduce overall agent latency while maintaining performance. The main obstacle is the high cost of end-to-end evaluation: in our experiments, evaluating 11 methods across 32 configurations on 33 tasks