Efficient Tree-Structured Deep Research with Adaptive Resource Allocation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915895866032128 |
|---|---|
| author | Nie, Lunyiu Lipka, Nedim Rossi, Ryan A. Chaudhuri, Swarat |
| author_facet | Nie, Lunyiu Lipka, Nedim Rossi, Ryan A. Chaudhuri, Swarat |
| contents | Deep research agents, which synthesize information across diverse sources, are significantly constrained by the sequential nature of reasoning. This bottleneck results in high latency, poor runtime adaptability, and inefficient resource allocation, making today's deep research systems impractical for interactive applications. To overcome this, we introduce ParallelResearch, a novel framework for efficient deep research that transforms sequential processing into parallel, runtime orchestration by dynamically decomposing complex queries into tree-structured sub-tasks.
Our core contributions are threefold: (1) an adaptive planner that dynamically allocates computational resources based on query complexity; (2) a runtime orchestration layer that prunes redundant paths to reallocate resources and enables speculative execution; and (3) a fully-asynchronous execution infrastructure that enables concurrency across both research breadth and depth. Experiments on two benchmarks show up to 5x speedups with comparable final report quality, and consistent quality improvements with the same time budgets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_05145 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Efficient Tree-Structured Deep Research with Adaptive Resource Allocation Nie, Lunyiu Lipka, Nedim Rossi, Ryan A. Chaudhuri, Swarat Distributed, Parallel, and Cluster Computing Artificial Intelligence Multiagent Systems Deep research agents, which synthesize information across diverse sources, are significantly constrained by the sequential nature of reasoning. This bottleneck results in high latency, poor runtime adaptability, and inefficient resource allocation, making today's deep research systems impractical for interactive applications. To overcome this, we introduce ParallelResearch, a novel framework for efficient deep research that transforms sequential processing into parallel, runtime orchestration by dynamically decomposing complex queries into tree-structured sub-tasks. Our core contributions are threefold: (1) an adaptive planner that dynamically allocates computational resources based on query complexity; (2) a runtime orchestration layer that prunes redundant paths to reallocate resources and enables speculative execution; and (3) a fully-asynchronous execution infrastructure that enables concurrency across both research breadth and depth. Experiments on two benchmarks show up to 5x speedups with comparable final report quality, and consistent quality improvements with the same time budgets. |
| title | Efficient Tree-Structured Deep Research with Adaptive Resource Allocation |
| topic | Distributed, Parallel, and Cluster Computing Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2510.05145 |