Tunable Tool-Call Rates in LLM Agents via Representation Steering
- Published
- Source
- arXiv
- Paper number
- 1036
- Field
- AI / General
- arXiv ID
- 2608.25198
Key points
- It extracted a linear direction governing whether to call tools from the model's own signals, without training.
- Adjusting the direction's strength changes the call rate monotonically from near 0% to 90% or higher (while preserving valid call formatting).
- Increasing the direction makes the model call tools specifically for questions it cannot answer on its own, while decreasing it reduces unnecessary calls.
- It transfers to unseen tools, and which tool to choose (selection) and whether to call a tool (decision) are separated into different directions.
- It raised QA accuracy from 0.29 to 0.56 in a real execution environment, and the same recipe worked for dense, MoE, and multimodal models.
Paper links
External research summaries. These are not HDATF publications or measured product results.