ToolFuse: Provenance-Aware In-Flight Coalescing of Redundant Agent Tool Calls
Authors: I. Yildirim, X.-H. Sun, A. Kougkas
Date: November, 2026
Venue: The International Conference for High Performance Computing, Networking, Storage, and Analysis (SC'26)
Type: Poster
Abstract
Scientific workflows increasingly run as fleets of LLM agents analysing immutable datasets. Independent agents can issue equivalent expensive read-only tool calls simultaneously, before a completed-result cache has anything to reuse. ToolFuse addresses this cold-wave gap by coalescing active calls at a gateway between agents and tool handlers. Its contribution is a provenance-aware execution identity that establishes equivalence from versioned dependencies and execution context, rather than arguments alone. Under contention on an exclusive HPC node, 16 equivalent requests become one execution, reducing CPU time by 11.79x and makespan by 2.36x. Peak memory growth falls from 6.44 GiB to 0.53 GiB. Trace replay shows that sharing depends on call duration and arrival timing. For cheap calls, coalescing remains inactive with negligible overhead. ToolFuse admits only calls declared read-only, idempotent, deterministic, and closed-world, and prefers false misses over unsafe sharing.