# Rethinking Agentic Search with Pi-Serini: Is Lexical Retrieval Sufficient?

arXiv: https://arxiv.org/abs/2605.10848 · HTML: https://mlsanity.com/paper/2605.10848/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 15 of its 26 references that are in the map.
- First posted on arXiv 11 May 2026.

## Placed in

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

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

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models](https://mlsanity.com/paper/2506.05176/) (2025)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent](https://mlsanity.com/paper/2508.06600/) (2025)
- [BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese](https://mlsanity.com/paper/2504.19314/) (2025)
- [ReasonIR: Training Retrievers for Reasoning Tasks](https://mlsanity.com/paper/2504.20595/) (2025)
- [Tongyi DeepResearch Technical Report](https://mlsanity.com/paper/2510.24701/) (2025)
- [Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction](https://mlsanity.com/paper/2605.05242/) (2026)
- [Deep Research: A Systematic Survey](https://mlsanity.com/paper/2512.02038/) (2025)
- [AgentIR: Reasoning-Aware Retrieval for Deep Research Agents](https://mlsanity.com/paper/2603.04384/) (2026)
- [Coding Agents are Effective Long-Context Processors](https://mlsanity.com/paper/2603.20432/) (2026)
- [Rerank Before You Reason: Analyzing Reranking Tradeoffs through Effective Token Cost in Deep Search Agents](https://mlsanity.com/paper/2601.14224/) (2026)
- [SAGE: Benchmarking and Improving Retrieval for Deep Research Agents](https://mlsanity.com/paper/2602.05975/) (2026)
- [Revisiting Text Ranking in Deep Research](https://mlsanity.com/paper/2602.21456/) (2026)

## Built on by (most cited first, 10 of 10)

- [Towards Retrieving Interaction Spaces for Agentic Search](https://mlsanity.com/paper/2606.06880/) (2026)
- [Dr-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion](https://mlsanity.com/paper/2606.14885/) (2026)
- [A New Role for Relevance: Guiding Corpus Interaction in Agentic Search](https://mlsanity.com/paper/2607.24223/) (2026)
- [Question's Gambit: The First Move Matters in Agentic Deep Search](https://mlsanity.com/paper/2609.14412/) (2026)
- [Latent Terms: Dense Retrievers Contain Trivially Extractable BM25-ready Zipfian Vocabularies](https://mlsanity.com/paper/2605.29384/) (2026)
- [EMBL AI Librarian: Life-Sciences Knowledge Layer for AI Agents](https://mlsanity.com/paper/2607.28229/) (2026)
- [Projecting BrowseComp-Plus onto ClimbMix: Toward More Realistic Corpora for Agentic Search](https://mlsanity.com/paper/2608.20317/) (2026)
- [Small Agents with Semantic Search: Efficient Multilingual Code Localization](https://mlsanity.com/paper/2610.05099/) (2026)
- [Project Greenhouse: Progress Toward Fully Open and Sovereign Agentic Search](https://mlsanity.com/paper/2610.11922/) (2026)
- [JevGPT: Thinking Fast and Slow in Autonomous Research](https://mlsanity.com/paper/2610.18272/) (2026)

## Abstract (arXiv)

Does a lexical retriever suffice as large language models (LLMs) become more capable in an agentic loop? This question naturally arises when building deep research systems. We revisit it by pairing BM25 with frontier LLMs that have better reasoning and tool-use abilities. To support researchers asking the same question, we introduce Pi-Serini, a search agent equipped with three tools for retrieving, browsing, and reading documents. Our results show that, on BrowseComp-Plus, a well-configured lexical retriever with sufficient retrieval depth can support effective deep research when paired with more capable LLMs. Specifically, Pi-Serini with gpt-5.5 achieves 83.1% answer accuracy and 94.7% surfaced evidence recall, outperforming released search agents that use dense retrievers. Controlled ablations further show that BM25 tuning improves answer accuracy by 18.0% and surfaced evidence recall by 11.1% over the default BM25 setting, while increasing retrieval depth further improves surfaced evidence recall by 25.3% over the shallow-retrieval setting. Source code is available at https://github.com/justram/pi-serini.