Skip to main content
Search

# Tool Progress Reporting

1 related articles

Subscribe to updates
  1. arXiv

    Ask the Tool, Don't Guess: Agent Tool Calls Hold Their Progress, and the Serving System Should Read It

    The work proposes that running tool calls explicitly report their own progress (a fraction of work remaining or an accurate signal that the end is near), and through a census of four public agent corpora, a harness that recovers the signal without changing what the agent sees, a comparison against four published predictors, and an end-to-end evaluation plugged into vLLM through a few small hints, finds that the reported progress is between several times and an order of magnitude more accurate than the best published predictors at KV cache decision points and stays accurate when the environment changes, cutting p90 time to first token after a tool call by 20.7% (HBM only) and 20.8% (HBM + DRAM) against LRU, close to an oracle.

You’re all caught up