Microsoft's CorpusMap boosts agent QA by 6.4-11.7 points while cutting input tokens 34-57%
dair_ai · x · 2026-10-06
Microsoft and collaborators introduce CorpusMap, a method for agents searching large document collections.
How it works:
- Recurring entities are resolved in advance; each entity gets a page linking to every document mentioning it, while original documents stay in place.
- Agents follow entity links between documents instead of re-searching the same evidence.
- The map can be built without LLM calls and updated incrementally as new documents arrive.
Results: across 7 models and 3 benchmarks, answer quality improves 6.4-11.7 points while input tokens drop 34-57%, beating an LLM Wiki layer and three other navigation approaches.
More from coding & agent
- Only-Knowing-Code Developers at Risk as the Agentic Software Factory Reshapes Engineering — Pavan_Belagatti · 2026-11-23
- Vibecoding cuts $5k, 4-week e-commerce store builds down to days — Tegadesigns · 2026-11-23
- Butler vs gardener: the two types AI agents are splitting into — hwchase17 · 2026-11-23
- MCP Tool Gateways Should Fail Loudly: A Plausible Answer From a Missing Dependency Is the Real Bug — Emergency-Tutor-7 · 2026-11-23
- Codex Can't Route PCB Traces: Devs Still Lack a Workable AI Tool for Hardware's Last Mile — goldvenetianmask · 2026-11-23
- Uncensored 26.4B model runs on a 12GB Mac at 85 tok/s with 8 parallel agents via Locals — SumitGup · 2026-11-23