Rethinking Deep Research from the Perspective of Web Content Distribution Matching
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911495752777728 |
|---|---|
| author | Yu, Zixuan Tang, Zhenheng Liu, Tongliang Zhang, Chengqi Chu, Xiaowen Han, Bo |
| author_facet | Yu, Zixuan Tang, Zhenheng Liu, Tongliang Zhang, Chengqi Chu, Xiaowen Han, Bo |
| contents | Despite the integration of search tools, Deep Search Agents often suffer from a misalignment between reasoning-driven queries and the underlying web indexing structures. Existing frameworks treat the search engine as a static utility, leading to queries that are either too coarse or too granular to retrieve precise evidence. We propose WeDas, a Web Content Distribution Aware framework that incorporates search-space structural characteristics into the agent's observation space. Central to our method is the Query-Result Alignment Score, a metric quantifying the compatibility between agent intent and retrieval outcomes. To overcome the intractability of indexing the dynamic web, we introduce a few-shot probing mechanism that iteratively estimates this score via limited query accesses, allowing the agent to dynamically recalibrate sub-goals based on the local content landscape. As a plug-and-play module, WeDas consistently improves sub-goal completion and accuracy across four benchmarks, effectively bridging the gap between high-level reasoning and low-level retrieval. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07241 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Rethinking Deep Research from the Perspective of Web Content Distribution Matching Yu, Zixuan Tang, Zhenheng Liu, Tongliang Zhang, Chengqi Chu, Xiaowen Han, Bo Machine Learning Information Retrieval Despite the integration of search tools, Deep Search Agents often suffer from a misalignment between reasoning-driven queries and the underlying web indexing structures. Existing frameworks treat the search engine as a static utility, leading to queries that are either too coarse or too granular to retrieve precise evidence. We propose WeDas, a Web Content Distribution Aware framework that incorporates search-space structural characteristics into the agent's observation space. Central to our method is the Query-Result Alignment Score, a metric quantifying the compatibility between agent intent and retrieval outcomes. To overcome the intractability of indexing the dynamic web, we introduce a few-shot probing mechanism that iteratively estimates this score via limited query accesses, allowing the agent to dynamically recalibrate sub-goals based on the local content landscape. As a plug-and-play module, WeDas consistently improves sub-goal completion and accuracy across four benchmarks, effectively bridging the gap between high-level reasoning and low-level retrieval. |
| title | Rethinking Deep Research from the Perspective of Web Content Distribution Matching |
| topic | Machine Learning Information Retrieval |
| url | https://arxiv.org/abs/2603.07241 |