# ITER: Interaction-Aware Retrieval for Agentic Search

arXiv: https://arxiv.org/abs/2608.27912 · HTML: https://mlsanity.com/paper/2608.27912/

## Key facts

- Cited by 1 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 28 of its 42 references that are in the map.
- First posted on arXiv 28 Aug 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, 28 of 28)

- [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)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [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)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval](https://mlsanity.com/paper/2007.00808/) (2020)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [WebThinker: Empowering Large Reasoning Models with Deep Research Capability](https://mlsanity.com/paper/2504.21776/) (2025)
- [BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent](https://mlsanity.com/paper/2508.06600/) (2025)
- [Deep Research Agents: A Systematic Examination And Roadmap](https://mlsanity.com/paper/2506.18096/) (2025)
- [Task-aware Retrieval with Instructions](https://mlsanity.com/paper/2211.09260/) (2022)
- [Few-Shot Generative Conversational Query Rewriting](https://mlsanity.com/paper/2006.05009/) (2020)
- [Few-Shot Conversational Dense Retrieval](https://mlsanity.com/paper/2105.04166/) (2021)
- [Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction](https://mlsanity.com/paper/2605.05242/) (2026)
- [AgentIR: Reasoning-Aware Retrieval for Deep Research Agents](https://mlsanity.com/paper/2603.04384/) (2026)
- [Advancing the Search Frontier with AI Agents](https://mlsanity.com/paper/2311.01235/) (2023)
- [Agentic-R: Learning to Retrieve for Agentic Search](https://mlsanity.com/paper/2601.11888/) (2026)
- [Learning Contextual Retrieval for Robust Conversational Search](https://mlsanity.com/paper/2509.19700/) (2025)
- [Revisiting Text Ranking in Deep Research](https://mlsanity.com/paper/2602.21456/) (2026)
- [Towards Retrieving Interaction Spaces for Agentic Search](https://mlsanity.com/paper/2606.06880/) (2026)
- [NExT-Search: Rebuilding User Feedback Ecosystem for Generative AI Search](https://mlsanity.com/paper/2505.14680/) (2025)
- [Learning to Retrieve from Agent Trajectories](https://mlsanity.com/paper/2604.04949/) (2026)
- [Search, Inspect, Fetch: Exploiting Structure-Aware Boolean Retrieval for Deep-Search Agents](https://mlsanity.com/paper/2608.02751/) (2026)

## Built on by (most cited first, 1 of 1)

- [EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery](https://mlsanity.com/paper/2609.40340/) (2026)

## Abstract (arXiv)

Deep-research agents answer complex user questions through an iterative sequence of search steps, where the agent autonomously formulates sub-queries to retrieve the evidence needed at each stage. However, existing retriever training typically relies only on the sub-query and its corresponding search results at the current step as training signals, leaving the information accumulated from previous interactions largely underutilized. We introduce ITER, an agent interaction-aware dense retriever trained using agent trajectory learning signals. ITER represents each query by incorporating not only the current sub-query, but also the main question, the agent's pre-search reasoning, and preceding sub-queries, and is trained using trajectory-relative learning signals derived from the agent's interactions. Across six agent backbones from three model families, ITER consistently outperforms the existing agent-trajectory-trained dense retriever, LRAT, achieving an average relative improvement of 6.9% on InfoSeek-Eval and 15.4% on BrowseComp-Plus. At the matched 4B scale, ITER outperforms AgentIR on InfoSeek-Eval for five of six backbones while achieving a higher visit-to-search recall ratio on BrowseComp-Plus across all six backbones. Ablations further show that structured interaction history and pre-search reasoning provide complementary retrieval context, while previously visited and useful documents, used as redundancy negatives in subsequent searches, provide the strongest trajectory-relative supervision.