The authors built a library of high-level reasoning candidates for recurring search situations, such as recognizing that an entity is known but a requested attribute still needs to be found.
Reusable reasoning choices make multimodal search agents substantially faster
SSR replaces free-form deliberation with parallel scoring of predefined reasoning candidates, preserving task performance while cutting inference latency.
Big Tech
Feiyu Gavin Zhu · Xiaoyu Zhu · Jiqi Yang · Rui Yang · Arnab Kumar Mondal · Yancheng Wang · +6 more
Apple · Carnegie Mellon University
Research Digest··3 min read
Zhu et al.
Why this paper
From Apple and Carnegie Mellon University
In one line
Selection-based Structured Reasoning replaces freeform reasoning with selection from pre-specified candidates, cutting reasoning latency by over 90%.
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.
§