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
- Kimi K3 may be strong on cyber, but token efficiency keeps it off UK AISIS — teortaxesTex · 2026-07-27
- ARC AGI 3 should have stayed private, with no examples or public dataset — flowersslop · 2026-07-27
- ExploitGym may have only 60–70% solvable tasks, fueling the OpenAI cheating debate — max_paperclips · 2026-07-27
- RTX 5090 local tests show Qwen Q6 can drop to 15 tok/s at 80k context — LFAdvice7984 · 2026-07-27
- Noahpinion quotes Chollet: intelligence may hit a hard ceiling — binarybits · 2026-07-27
- Paper argues graph topology can become the core operating system for AI agents — theomitsa · 2026-07-27