TOTAL framework: reusable thought templates fix long-context multi-hop reasoning
burkov · x · 2026-10-19
burkov breaks down an article on a key gap in long-context LLMs: they read hundreds of thousands of tokens but don't connect evidence scattered across documents, so multi-hop QA stays weak. Stuffing more documents or standard RAG improves recall but not reasoning; the missing piece is a reusable way to structure evidence. TOTAL tests whether reusable thought templates close that gap.
More from Research
- RFD4-Proteina's 'underrated' docs detail partial diffusion for protein redesign — AllThingsApx · 2026-10-23
- MPI-Sec PhD Thesis on Vulnerability Detection Benchmarks Includes Pre-LLM Classic "Top Score on the Wrong Exam" — mboehme_ · 2026-10-23
- LiveNerf's 29-day data finds no nerfing of Claude Opus 5.5 — TheOnlyVibemaster · 2026-10-23
- New paper makes 9 falsifiable predictions toward a major AI-enabled terror attack by 2027-2028 — StephenLCasper · 2026-10-23
- HumanoidPose recovers humanoid robots' full-body joint states from RGB video alone — cholz · 2026-10-23
- Sophont's Holon-S1 predicts genes and biomarkers from routine pathology slides — iScienceLuvr · 2026-10-23