The authors propose converting the NL-to-Action problem into classification by constructing an on-device operation cache of parameterized operation idioms.
On-device caches convert natural language to actions with classification not generation
For Excel formula generation, the approach cuts cloud inference cost by 56 percent and latency by a factor of five on cache hits.
Big Tech
Moghis Fereidouni · Anthony Arnold · Sumit Gulwani · Mark Marron · A. B. Siddique
University of Kentucky · Microsoft
Research Digest··2 min read
Thread:Agent Harness Optimization
Fereidouni et al.
Why this paper
From Microsoft and University of Kentucky · Part of Agent Harness Optimization, now 90 papers
In one line
On-device operation caches reduce latency, cost, and privacy risks by converting NL-to-Action generation into a classification problem.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§