Back to AI Lab

Tool Use

Research papers, repositories, and articles about tool use

Showing 4 of 4 items

Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It

Shows that in tool-use RL, models often "forget" how to call tools because specific control tokens spike in probability, breaking format while the underlying skill stays. Interleaving supervised updates with RL and adding richer hints stabilizes training across formats and tasks. If your agent RL runs keep collapsing, this paper is a playbook. ([huggingface.co](https://huggingface.co/papers/2606.26027))

Yupu Hao, Zhuoran Jin

Heterogeneous Scientific Foundation Model Collaboration

Introduces Eywa, a framework that lets language models coordinate with domain‑specific scientific models across non-text data. Treats those models as tools inside an agent system and studies planning strategies across them. If you’re building AI for science, this shows how to wire specialized models into one reasoning loop. ([huggingface.co](https://huggingface.co/papers/2604.27351))

Zihao Li, Jiaru Zou

LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents

Adds a separate “ledger” of task state so customer-service agents stop forgetting rules and context between tool calls. If you deploy tool-calling agents in regulated domains, this is a ready-made design pattern.

Md Nayem Uddin, Amir Saeidi

LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents

Tracks customer data and policy state in a separate ledger so agents stop making forbidden tool calls. If you run support bots, this is directly actionable.

Md Nayem Uddin, Amir Saeidi