Apple paper: structured selection-based reasoning cuts search agent latency by 90%
_reachsumit · x · 2026-10-02
- Apple researchers published SSR (Selection-based Structured Reasoning), which replaces free-form reasoning in multimodal search agents with selection from pre-specified, reusable natural-language reasoning candidates based on token likelihoods.
- Pre-defined reasoning traces enable parallel scoring via teacher-forced prefilling with a shared context KV cache, no auxiliary task head needed.
- Evaluated on seven multimodal search benchmarks with 2B and 4B models across RL objectives and SFT, SSR matches the success rate of leading same-scale search agents while cutting per-turn reasoning latency by over 90% and total per-question inference latency substantially.
More from Research
- New video traces how adversarial objectives evolved beyond GANs and self-play — manicman1999 · 2026-10-02
- Peer-reviewed paper questions whether gene expression model benchmarks are informative — simocristea · 2026-10-02
- Oxford VGG Unveils SynCity 3000, Generating Globally Coherent Scene-Scale 3D Worlds — rsasaki0109 · 2026-10-02
- Christian Szegedy revisits 2019 interview: his 'crazy' timelines for AI math and code — ChrSzegedy · 2026-10-02
- Omni-Embed-Mini: A 0.9B Embedder Adds Five Modalities Without Touching Text Weights — _reachsumit · 2026-10-02
- GrIS paper reframes Semantic IDs as recursive graph partitioning for generative recommendation — _reachsumit · 2026-10-02