# IterResearch: Rethinking Long-Horizon Agents with Interaction Scaling

arXiv: https://arxiv.org/abs/2511.07327 · HTML: https://mlsanity.com/paper/2511.07327/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 35 of its 44 references that are in the map.
- First posted on arXiv 10 Nov 2025.

## 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 35)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [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)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [Search-o1: Agentic Search-Enhanced Large Reasoning Models](https://mlsanity.com/paper/2501.05366/) (2025)
- [Scaling Relationship on Learning Mathematical Reasoning with Large Language Models](https://mlsanity.com/paper/2308.01825/) (2023)
- [R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.05592/) (2025)
- [WebThinker: Empowering Large Reasoning Models with Deep Research Capability](https://mlsanity.com/paper/2504.21776/) (2025)
- [DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments](https://mlsanity.com/paper/2504.03160/) (2025)
- [Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions](https://mlsanity.com/paper/2507.05257/) (2025)
- [MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent](https://mlsanity.com/paper/2507.02259/) (2025)
- [MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents](https://mlsanity.com/paper/2506.15841/) (2025)
- [Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning](https://mlsanity.com/paper/2508.19828/) (2025)
- [WebSailor: Navigating Super-human Reasoning for Web Agent](https://mlsanity.com/paper/2507.02592/) (2025)
- [RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs](https://mlsanity.com/paper/2407.02485/) (2024)
- [WebDancer: Towards Autonomous Information Seeking Agency](https://mlsanity.com/paper/2505.22648/) (2025)
- [Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL](https://mlsanity.com/paper/2508.07976/) (2025)
- [BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese](https://mlsanity.com/paper/2504.19314/) (2025)
- [MemOS: A Memory OS for AI System](https://mlsanity.com/paper/2507.03724/) (2025)
- [WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization](https://mlsanity.com/paper/2507.15061/) (2025)
- [InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales](https://mlsanity.com/paper/2406.13629/) (2024)
- [SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models](https://mlsanity.com/paper/2506.01062/) (2025)
- [WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents](https://mlsanity.com/paper/2509.13309/) (2025)
- [Click: Controllable Text Generation with Sequence Likelihood Contrastive Learning](https://mlsanity.com/paper/2306.03350/) (2023)

## Built on by (most cited first, 23 of 23)

- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents](https://mlsanity.com/paper/2602.06052/) (2026)
- [BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?](https://mlsanity.com/paper/2603.03194/) (2026)
- [Learning Agent-Compatible Context Management for Long-Horizon Tasks](https://mlsanity.com/paper/2605.30785/) (2026)
- [LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents](https://mlsanity.com/paper/2605.05191/) (2026)
- [SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent](https://mlsanity.com/paper/2605.24468/) (2026)
- [All-Mem: Agentic Lifelong Memory via Dynamic Topology Evolution](https://mlsanity.com/paper/2603.19595/) (2026)
- [Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baseline](https://mlsanity.com/paper/2603.05484/) (2026)
- [ET-Agent: Incentivizing Effective Tool-Integrated Reasoning Agent via Behavior Calibration](https://mlsanity.com/paper/2601.06860/) (2026)
- [What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents](https://mlsanity.com/paper/2607.08032/) (2026)
- [DeepTutor: Towards Agentic Personalized Tutoring](https://mlsanity.com/paper/2604.26962/) (2026)
- [ACE: Pluggable Adaptive Context Elasticizer across Agents](https://mlsanity.com/paper/2606.31564/) (2026)
- [A Task-State Representation for Long-Horizon Mobile GUI Agents](https://mlsanity.com/paper/2607.00502/) (2026)
- [Fetch-then-Explore: Decoupling Selection from Extraction over a Persistent Workspace for Search Agents](https://mlsanity.com/paper/2608.02097/) (2026)
- [Learning from Environmental Feedback: Credit Assignment across Multiple Timescales for Agentic Reinforcement Learning](https://mlsanity.com/paper/2608.08255/) (2026)
- [Self-Correcting Long-Horizon Search Agents via Tree-Structured Memory](https://mlsanity.com/paper/2608.10676/) (2026)
- [TreeSeeker: Tree-Structured Trial, Error, and Return in Deep Search](https://mlsanity.com/paper/2606.11662/) (2026)
- [R2-Searcher: Calibrating Retrieval and Reasoning Boundaries for Agentic Search](https://mlsanity.com/paper/2606.28566/) (2026)
- [NeSyFS: A Neuro-symbolic Fast-Slow Thinking Framework for LLM Agent under Partial Observability](https://mlsanity.com/paper/2607.28942/) (2026)
- [PI-Mem: Pushing Long-Context Reasoning to 3.6M Tokens with Parallel-Iterative Memory](https://mlsanity.com/paper/2608.03048/) (2026)
- [Intent-Driven Situation Tracking for User-Centric Multi-Turn Agents](https://mlsanity.com/paper/2608.15755/) (2026)
- [IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis](https://mlsanity.com/paper/2609.29444/) (2026)
- [SCAD: Structured Credit Assignment and Distillation for Long-Horizon Agents](https://mlsanity.com/paper/2610.03372/) (2026)

## Abstract (arXiv)

Recent advances in deep-research agents have shown promise for autonomous knowledge construction through dynamic reasoning over external sources. However, existing approaches rely on a mono-contextual paradigm that accumulates all information in a single, expanding context window, leading to context suffocation and noise contamination that limit their effectiveness on long-horizon tasks. We introduce IterResearch, a novel iterative deep-research paradigm that revisits long-horizon research through the lens of Interaction Scaling. Instead of relying on linear context accumulation, we adopt an MDP-inspired architecture with strategic workspace reconstruction. By maintaining an evolving report as memory and periodically synthesizing insights, our approach preserves consistent reasoning capacity across arbitrary exploration depths. To effectively train this paradigm, we employ Efficiency-Aware Policy Optimization (EAPO), a training strategy that adapts geometric reward discounting to incentivize efficient exploration and utilizes adaptive downsampling for stable distributed training. Extensive experiments demonstrate that IterResearch achieves substantial improvements over existing open-source agents with average +14.5pp across six benchmarks and narrows the gap with frontier proprietary systems. Remarkably, our paradigm exhibits unprecedented interaction scaling, extending to 2048 interactions with dramatic performance gains (from 3.5% to 42.5%), and serves as an effective prompting strategy, improving frontier models by up to 19.2pp over ReAct on long-horizon tasks. These findings position IterResearch as a versatile solution for long-horizon reasoning, effective both as a trained agent and as a prompting paradigm for frontier models.