# RIVO: Lightweight Adaptive Rerouting for Deep Research Agents

arXiv: https://arxiv.org/abs/2610.15910 · HTML: https://mlsanity.com/paper/2610.15910/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 37 of its 41 references that are in the map.
- First posted on arXiv 11 Oct 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 30 of 37)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale](https://mlsanity.com/paper/2406.17557/) (2024)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent](https://mlsanity.com/paper/2508.06600/) (2025)
- [Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents](https://mlsanity.com/paper/2311.00262/) (2023)
- [Open Deep Search: Democratizing Search with Open-source Reasoning Agents](https://mlsanity.com/paper/2503.20201/) (2025)
- [Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents](https://mlsanity.com/paper/2510.14967/) (2025)
- [Answer Convergence as a Signal for Early Stopping in Reasoning](https://mlsanity.com/paper/2506.02536/) (2025)
- [DeepRAG: Thinking to Retrieve Step by Step for Large Language Models](https://mlsanity.com/paper/2502.01142/) (2025)
- [OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis](https://mlsanity.com/paper/2603.20278/) (2026)
- [BiomedRAG: A Retrieval Augmented Large Language Model for Biomedicine](https://mlsanity.com/paper/2405.00465/) (2024)
- [DRBench: A Realistic Benchmark for Enterprise Deep Research](https://mlsanity.com/paper/2510.00172/) (2025)
- [Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design](https://mlsanity.com/paper/2603.28376/) (2026)
- [EvolveRouter: Co-Evolving Routing and Prompt for Multi-Agent Question Answering](https://mlsanity.com/paper/2604.05149/) (2026)
- [CancerLLM: A Large Language Model in Cancer Domain](https://mlsanity.com/paper/2406.10459/) (2024)
- [Benchmarking Retrieval-Augmented Large Language Models in Biomedical NLP: Application, Robustness, and Self-Awareness](https://mlsanity.com/paper/2405.08151/) (2024)
- [Agentic-R: Learning to Retrieve for Agentic Search](https://mlsanity.com/paper/2601.11888/) (2026)
- [LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent](https://mlsanity.com/paper/2604.17931/) (2026)
- [Understand the Dynamic World: An End-to-End Knowledge Informed Framework for Open Domain Entity State Tracking](https://mlsanity.com/paper/2304.13854/) (2023)
- [Logic-RAG: Augmenting Large Multimodal Models with Visual-Spatial Knowledge for Road Scene Understanding](https://mlsanity.com/paper/2503.12663/) (2025)
- [CaRT: Teaching LLM Agents to Know When They Know Enough](https://mlsanity.com/paper/2510.08517/) (2025)
- [GLEN-Bench: A Graph-Language based Benchmark for Nutritional Health](https://mlsanity.com/paper/2601.18106/) (2026)
- [Counterfactual Graph for Multi-Agent LLM Calibration](https://mlsanity.com/paper/2605.30653/) (2026)
- [Think in Parallel, Answer as One: Logit Averaging for Open-Ended Reasoning](https://mlsanity.com/paper/2512.02874/) (2025)
- [Logits are All We Need to Adapt Closed Models](https://mlsanity.com/paper/2502.06806/) (2025)
- [S1-DeepResearch: Beyond Search, Toward Real-World Long-Horizon Research Agents](https://mlsanity.com/paper/2606.15367/) (2026)
- [Steering Language Models Before They Speak: Logit-Level Interventions](https://mlsanity.com/paper/2601.10960/) (2026)

## Abstract (arXiv)

Deep Research agents rely on long-horizon reasoning and iterative tool use to solve complex information-seeking tasks. However, adaptive decision-making over these trajectories remains challenging, as agents may stop prematurely when further evidence is needed, continue unnecessarily after sufficient evidence has been gathered, or fail to redirect unproductive trajectories. Existing solutions either require costly model retraining and dense turn-level supervision, or rely on heuristic control rules that are not directly optimized for downstream research utility. This motivates a lightweight, utility-aware alternative for Deep Research control. We formulate adaptive rerouting in long-horizon Deep Research as a state-conditioned trajectory correction problem. Based on this view, we introduce RIVO, a lightweight plug-in framework for adaptive trajectory correction. The agent estimates its research state from lightweight signals and determines whether trajectory redirection is needed. Once triggered, the plug-in modifies the Host token logits to steer generation toward a more promising research direction. Theoretical analysis shows that, under a value-alignment condition and bounded local curvature, a sufficiently small logit intervention can locally improve expected downstream research utility. We further construct BrowseCore, a curated dataset with a paired local corpus, for efficient and controlled Deep Research experimentation. Building on this resource, the plug-in is trained from downstream outcomes, enabling it to learn corrections that improve subsequent research and final task performance. Extensive experiments across multiple Deep Research benchmarks and control settings demonstrate the effectiveness of our method, showing that lightweight logit intervention can improve long-horizon research without retraining the underlying Host model.