BlockSearch: Research on Million-Token Context Retrieval
dair_ai · x · 2026-07-06
dairai shared a study that systematically investigates context retrieval at a one-million-token corpus scale, reflecting the real-world challenge faced by retrievers, and evaluates length generalization far beyond training limits.
The paper introduces BlockSearch, a 0.6B-parameter LM retriever. Through architectural and training improvements, it outperforms previous LM baselines and extends its length generalization capabilities to over 10 times its training length.
More from Research
- Skyfall GS Uses Flux to Refine Gaussian Splatting, Accepted at ECCV 2026 — ducha_aiki · 2026-09-11
- Could 10k agents discover learning methods beyond backprop, or just tweak existing ones? — SeunghyunSEO7 · 2026-09-11
- Apodex Launches TRACES, First Benchmark for Evaluating 'Discoverative AI' on Real-World Problems — Faheem_uh · 2026-09-11
- TRACES grades the process, not the answer: six-dimension eval for open-ended AI science — Faheem_uh · 2026-09-11
- Apodex launches TRACES, a benchmark grading AI on open-ended discovery instead of known answers — Faheem_uh · 2026-09-11
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11