Weaver: Incremental Reasoning Over Conversation Memory for Personalized RAG
_reachsumit · x · 2026-11-06
- Paper Weaver (arXiv:2611.05900) targets personalized RAG, where preference evidence is scattered across long interaction histories and bound to specific temporal and situational contexts.
- It introduces a Dual-Layer Retrieval and Reasoning Graph: an upper Intent Dependency Graph tracks the information needed to answer the current request (Dependency Information Gap Tracking), while a lower Memory-Conditioned Retrieval Trajectory Graph performs incremental retrieval using established premises and clues.
- Scope-Aware Compositional Reasoning jointly interprets accumulated evidence to decide which preferences apply, identifying complementary, conflicting, or out-of-scope preferences.
More from coding & agent
- FastAPI creator tiangolo says he now uses voice-driven Codex way more after jxnlco's talk — jxnlco · 2026-11-06
- AWS WAF + Stripe lets sites charge AI agents via HTTP 402, with fiat payouts — jeff_weinstein · 2026-11-06
- The computable enterprise: capturing business logic that lives in employees' heads — vishalmisra · 2026-11-06
- Claude skills are useless — until you hook them to your actual business — aryanXmahajan · 2026-11-06
- Do you use MCP firewalls with Claude, Codex or Cursor in production? — vdobroskok · 2026-11-06
- Firecrawl launches Alexandria agent data layer with Benzinga, announces $75M Series B — devdigest · 2026-11-06