works on
agent adaptation 1counterfactual reasoning 1dynamic tool integration 1reinforcement learning 1tool-augmented language models 1

From the 1 of 13 linked papers with an AI index.

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

ToolAnchor: Anchoring Counterfactual Context to Boost Agentic Tool-use Capability

Weiting Liu, Jieyi Bi, Wanqi Zhou +4

The paper introduces ToolAnchor, a method that injects counterfactual contexts to help large language model agents overcome reliance on familiar tools and adapt to new toolsets wit…