# Cross-domain benchmarks reveal when coordinated AI agents improve scientific inference from partial evidence

arXiv: https://arxiv.org/abs/2605.22300 · HTML: https://mlsanity.com/paper/2605.22300/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 40 references that are in the map.
- First posted on arXiv 21 May 2026.

## Builds on (most cited first, 13 of 13)

- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [Towards End-to-End Automation of AI Research](https://mlsanity.com/paper/2606.15497/) (2026)
- [Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities](https://mlsanity.com/paper/2409.03444/) (2024)
- [ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learning](https://mlsanity.com/paper/2402.04268/) (2024)
- [An AI system to help scientists write expert-level empirical software](https://mlsanity.com/paper/2509.06503/) (2025)
- [BioinspiredLLM: Conversational Large Language Model for the Mechanics of Biological and Bio-inspired Materials](https://mlsanity.com/paper/2309.08788/) (2023)
- [Accelerating Scientific Discovery with Generative Knowledge Extraction, Graph-Based Representation, and Multimodal Intelligent Graph Reasoning](https://mlsanity.com/paper/2403.11996/) (2024)
- [PRefLexOR: Preference-based Recursive Language Modeling for Exploratory Optimization of Reasoning and Agentic Thinking](https://mlsanity.com/paper/2410.12375/) (2024)
- [Autonomous Agents Coordinating Distributed Discovery Through Emergent Artifact Exchange](https://mlsanity.com/paper/2603.14312/) (2026)
- [GraphAgents: Knowledge Graph-Guided Agentic AI for Cross-Domain Materials Design](https://mlsanity.com/paper/2602.07491/) (2026)
- [AI for Science: An Emerging Agenda](https://mlsanity.com/paper/2303.04217/) (2023)
- [Learning the rules of peptide self-assembly through data mining with large language models](https://mlsanity.com/paper/2411.05421/) (2024)
- [Swarms of Large Language Model Agents for Protein Sequence Design with Experimental Validation](https://mlsanity.com/paper/2511.22311/) (2025)

## Abstract (arXiv)

Scientific evidence often spans instruments, databases, and disciplines, so no single source records the full phenomenon. This makes it difficult to determine when coordinated AI agents add value over simpler scientific workflows. We evaluate this question with a cross-domain benchmark spanning four scientific tasks: mapping molecular structure into musical representations, detecting historical paradigm shifts in science, identifying vector-borne disease emergence, and vetting transiting-exoplanet candidates. Each case uses a frozen evaluation panel, predefined scoring protocols, explicit baselines, ablations or null controls, and stated limitations. The results define three operating regimes. When different disciplines each capture only part of the phenomenon, cross-channel composites improve over single-channel baselines: climate-vector emergence reaches AUROC 0.944 and exoplanet vetting reaches AUROC 0.955. However, the exoplanet workflow is effectively tied with a strong combined-summary baseline, showing that decomposition does not always improve top-line performance. When one signal dominates, as in paradigm-shift detection, coordination mainly improves interpretation and traceability. For molecular sonification, the gain is representational rather than predictive. ScienceClaw x Infinite provides the auditable artifact and provenance layer for this evaluation. The benchmark therefore assigns value to coordination only when the corresponding performance, provenance, or representation claim is supported by explicit comparators.