The authors assembled HM-Router-Bench from 12 public agent benchmarks, covering 293 model-harness routes, 73 models, and 25 harnesses.
Jointly routing models and harnesses improves agent performance under sparse data
HM-Router uses shared component representations to select compatible model and agent-harness pairs, including combinations absent from its training outcomes.
Big Tech
Hao Mark Chen · Royson Lee · Yasuyuki Okoshi · Dimitris Anastasiou · Wayne Luk · Hongxiang Fan
Imperial College London · Samsung · Institute of Science Tokyo
Research Digest··2 min read
Chen et al.
Why this paper
From Samsung and 2 others · Released code
In one line
Jointly routing models and harnesses per query using shared representations improves routing accuracy by 7.3 points over the best learned baseline.
What it released
Code
What we could check
- ✓Code link in the paper (github.com)
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks (2 benchmarks)
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§