# Don't Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination

arXiv: https://arxiv.org/abs/2604.24978 · HTML: https://mlsanity.com/paper/2604.24978/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 31 references that are in the map.
- First posted on arXiv 27 Apr 2026.

## Builds on (most cited first, 15 of 15)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [WebThinker: Empowering Large Reasoning Models with Deep Research Capability](https://mlsanity.com/paper/2504.21776/) (2025)
- [DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents](https://mlsanity.com/paper/2506.11763/) (2025)
- [WebSailor: Navigating Super-human Reasoning for Web Agent](https://mlsanity.com/paper/2507.02592/) (2025)
- [WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization](https://mlsanity.com/paper/2507.15061/) (2025)
- [CRMArena: Understanding the Capacity of LLM Agents to Perform Professional CRM Tasks in Realistic Environments](https://mlsanity.com/paper/2411.02305/) (2024)
- [Open Deep Search: Democratizing Search with Open-source Reasoning Agents](https://mlsanity.com/paper/2503.20201/) (2025)
- [LiveResearchBench: A Live Benchmark for User-Centric Deep Research in the Wild](https://mlsanity.com/paper/2510.14240/) (2025)
- [SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents](https://mlsanity.com/paper/2509.06283/) (2025)
- [Benchmarking Deep Search over Heterogeneous Enterprise Data](https://mlsanity.com/paper/2506.23139/) (2025)
- [Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analytics](https://mlsanity.com/paper/2510.17797/) (2025)
- [Beyond ReAct: A Planner-Centric Framework for Complex Tool-Augmented LLM Reasoning](https://mlsanity.com/paper/2511.10037/) (2025)
- [AgentKit: Structured LLM Reasoning with Dynamic Graphs](https://mlsanity.com/paper/2404.11483/) (2024)
- [DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence](https://mlsanity.com/paper/2509.04499/) (2025)
- [W&D:Scaling Parallel Tool Calling for Efficient Deep Research Agents](https://mlsanity.com/paper/2602.07359/) (2026)

## Built on by (most cited first, 4 of 4)

- [Redesigning and Auditing Deep Research Writing for Faithful Reports](https://mlsanity.com/paper/2608.28643/) (2026)
- [MNIST-PRO: MNIST is Back as a Partially Observable World for AI Agents](https://mlsanity.com/paper/2608.31022/) (2026)
- [LongCat-DeepResearch Technical Report](https://mlsanity.com/paper/2609.36071/) (2026)
- [What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents](https://mlsanity.com/paper/2609.39989/) (2026)

## Abstract (arXiv)

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.