DualViewEval

Mentions · 7d0
Mentions · 30d0
All mentions1
First seenSep 16, 2026
Last mentionedSep 16, 2026

Timeline

1 articles · newest first

Beyond Outcomes: Dual-View Relational Learning for Efficient Agent Benchmarking

DualViewEval compresses agent benchmarks by jointly modeling outcome and process signals, achieving 24x-40x compression with only 20 tasks on APEX-Agents and BFCL.

arXiv cs.AI / cs.LG / cs.CLSep 16, 16:49 UTC · Sep 16, 2026AI research3 · 1 read

Appears with

APEX-Agentsproduct · 1
SWE-bench Verifiedproduct · 1
EssenceBenchproduct · 1
BFCLproduct · 1

Entities are extracted by the model from each article. First seen Sep 16, 2026, last mentioned Sep 16, 2026. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.