Dont Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914512775413760 |
|---|---|
| author | Choubey, Prafulla Kumar Huang, Kung-Hsiang Venkit, Pranav Narayanan Zhang, Jiaxin Vats, Vaibhav Li, Yu Peng, Xiangyu Wu, Chien-Sheng |
| author_facet | Choubey, Prafulla Kumar Huang, Kung-Hsiang Venkit, Pranav Narayanan Zhang, Jiaxin Vats, Vaibhav Li, Yu Peng, Xiangyu Wu, Chien-Sheng |
| contents | Enterprise deep research often fails to produce decision-ready reports due to uneven information coverage, context explosion, and premature stopping. We propose a scalable Enterprise Deep Research (EDR) architecture to address these failures. Our system (i) decomposes requests into coverage-driven objectives via outline generation with reflection, (ii) localizes context with dependency-guided execution and explicit information sharing, and (iii) enforces evidence-based completion criteria so agents iteratively collect information until sufficiency conditions are met. We evaluate on an internal sales enablement task and the public DeepResearch Bench benchmark, where our proposed system design achieves the strongest overall performance compared with competitive deep-research baselines. The results show that dependency-controlled context and explicit evidence sufficiency criteria reduce premature stopping and improve the consistency and depth of enterprise research outputs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_24978 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Dont Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination Choubey, Prafulla Kumar Huang, Kung-Hsiang Venkit, Pranav Narayanan Zhang, Jiaxin Vats, Vaibhav Li, Yu Peng, Xiangyu Wu, Chien-Sheng Computation and Language Software Engineering Enterprise deep research often fails to produce decision-ready reports due to uneven information coverage, context explosion, and premature stopping. We propose a scalable Enterprise Deep Research (EDR) architecture to address these failures. Our system (i) decomposes requests into coverage-driven objectives via outline generation with reflection, (ii) localizes context with dependency-guided execution and explicit information sharing, and (iii) enforces evidence-based completion criteria so agents iteratively collect information until sufficiency conditions are met. We evaluate on an internal sales enablement task and the public DeepResearch Bench benchmark, where our proposed system design achieves the strongest overall performance compared with competitive deep-research baselines. The results show that dependency-controlled context and explicit evidence sufficiency criteria reduce premature stopping and improve the consistency and depth of enterprise research outputs. |
| title | Dont Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination |
| topic | Computation and Language Software Engineering |
| url | https://arxiv.org/abs/2604.24978 |