# CoWeaver: A Bi-directional, Learnable and Explainable Matching Engine for Mixed Human-Agent Science Collaboration

arXiv: https://arxiv.org/abs/2607.15545 · HTML: https://mlsanity.com/paper/2607.15545/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 9 of its 19 references that are in the map.
- First posted on arXiv 17 Jul 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, 9 of 9)

- [Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View](https://mlsanity.com/paper/2310.02124/) (2023)
- [Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents](https://mlsanity.com/paper/2502.20073/) (2025)
- [AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction](https://mlsanity.com/paper/2506.17784/) (2025)
- [Selective KV-Cache Sharing to Mitigate Timing Side-Channels in LLM Inference](https://mlsanity.com/paper/2508.08438/) (2025)
- [Learning How to Use Tools, Not Just When: Pattern-Aware Tool-Integrated Reasoning](https://mlsanity.com/paper/2509.23292/) (2025)
- [AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller Transactions](https://mlsanity.com/paper/2602.06008/) (2026)
- [LM Agents for Coordinating Multi-User Information Gathering](https://mlsanity.com/paper/2502.12328/) (2025)
- [De-centering the (Traditional) User: Multistakeholder Evaluation of Recommender Systems](https://mlsanity.com/paper/2501.05170/) (2025)
- [Latency-Quality Routing for Functionally Equivalent Tools in LLM Agents](https://mlsanity.com/paper/2605.14241/) (2026)

## Abstract (arXiv)

LLM-based agents excel at writing articles, coding and information retrieval. However, they fail to form strong collaborations within the scientific community due to the bidirectional, dynamic nature of the problem and a high demand of decision interpretability. We proposed COWEAVER, a bidirectional, learnable and explainable algorithm to match scientists and form strong collaborations within a human-agent network. COWEAVER matches candidates and requesters through filling capability gaps and filters candidates through a two-stage ranking step. Finally, the model explores newcomers by maintaining uncertainty-aware capability estimates and updating them through requester's feedback. We show that the selection mechanism of combining both exploration (UCB) and greedy of COWEAVER exceeds the greedy-only mechanism - the analytical best solution - on 6 out of the 20 tasks and performed on par with the greedy-only mechanism in terms of selecting the best candidate. We compared COWEAVER baselines in terms of matching quality and efficiency. COWEAVER outperforms baselines on all metrics.