# BioResearcher: Scenario-Guided Multi-Agent for Translational Medicine

arXiv: https://arxiv.org/abs/2605.05985 · HTML: https://mlsanity.com/paper/2605.05985/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 31 references that are in the map.
- First posted on arXiv 7 May 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 12 of 12)

- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making](https://mlsanity.com/paper/2404.15155/) (2024)
- [BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biology](https://mlsanity.com/paper/2503.00096/) (2025)
- [Matching Patients to Clinical Trials with Large Language Models](https://mlsanity.com/paper/2307.15051/) (2023)
- [ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learning](https://mlsanity.com/paper/2402.04268/) (2024)
- [TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools](https://mlsanity.com/paper/2503.10970/) (2025)
- [BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments](https://mlsanity.com/paper/2405.17631/) (2024)
- [KARMA: Leveraging Multi-Agent LLMs for Automated Knowledge Graph Enrichment](https://mlsanity.com/paper/2502.06472/) (2025)
- [LIDDIA: Language-based Intelligent Drug Discovery Agent](https://mlsanity.com/paper/2502.13959/) (2025)
- [Benchmarking AI scientists for omics data driven biological discovery](https://mlsanity.com/paper/2505.08341/) (2025)
- [NOVA: An Agentic Framework for Automated Histopathology Analysis and Discovery](https://mlsanity.com/paper/2511.11324/) (2025)
- [Language Model Powered Digital Biology with BRAD](https://mlsanity.com/paper/2409.02864/) (2024)

## Abstract (arXiv)

Translational medicine turns underspecified development goals into evidence synthesis that must combine literature, trials, patents, and quantitative multi-omics analysis while preserving identifiers, uncertainty, and retrievable provenance. General-purpose foundation models and off-the-shelf tool-augmented or multi-agent systems are not built for this: they tend to produce single-shot answers or run open-endedly, and fall short on the auditable, scenario-specific workflows that heterogeneous biomedical sources demand. This paper introduces Ingenix BioResearcher, a scenario-guided multi-agent system that maps queries to versioned research playbooks, delegates to specialized subagents over 30+ tools and machine-learning endpoints, mixes structured database access with sandboxed code for genome-scale analyses, and applies claim-level multi-model reconciliation before editorial assembly. We evaluate BioResearcher across unit-level capabilities, open-ended biomedical reasoning, and end-to-end clinical discovery. It leads evaluated baselines on 109 single-step tests (83.49% pass rate; 0.892 average score), achieves strong biomedical benchmark performance (89.33% on BixBench-Verified-50 and the top 0.758 mean score on BaisBench Scientific Discovery), and leads on a 30-query clinical end-to-end benchmark with the highest positive hit rate (74.7% ± 3.3%) and negative clear rate (96.8% ± 0.2%). These results show broad, competitive performance across unit-level, open-ended, and end-to-end clinical evaluations.