[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

![webagentlab Avatar](https://lunarcrush.com/gi/w:24/cr:twitter::1857262354221957120.png) WebAgentlab@ICML25 ✈️ [@webagentlab](/creator/twitter/webagentlab) on x XXX followers
Created: 2025-07-04 02:26:26 UTC

LineRetriever: Planning-Aware Observation Reduction for Web Agents

LineRetriever is a novel method that enhances web agent performance by intelligently reducing observation size through planning-aware retrieval, allowing for more efficient navigation while maintaining decision-making effectiveness within context limits.

Imene Kerboua, Sahar Omidi Shayegan @sahar_shayegan , Megh Thakkar @Megh1211 , Xing Han Lù @xhluca , Massimo Caccia @MassCaccia , Véronique Eglin, Alexandre Aussem, Jérémy Espinas, Alexandre Lacoste @alex_lacoste_ 

INSA Lyon; Esker; ServiceNow Research; Mila AI Institute; McGill University; Université Claude Bernard Lyon 1; LIRIS



![](https://pbs.twimg.com/media/Gu-po1CbYAAjrRx.jpg)

XX engagements

![Engagements Line Chart](https://lunarcrush.com/gi/w:600/p:tweet::1940960364189102511/c:line.svg)

[Post Link](https://x.com/webagentlab/status/1940960364189102511)