Poster Type: Research Posters
Author: Izzet Yildirim (Illinois Institute of Technology), Xian-He Sun (Illinois Institute of Technology), Anthony Kougkas (Illinois Institute of Technology)
Abstract: Scientific workflows increasingly run as fleets of LLM agents analyzing 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 11.79× and makespan by 2.36×. 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.
Best Poster Finalist (BP): no
Poster: PDF
Poster Summary: PDF