VLDB Talk: Deep Research Agents Need Co-Design with Retrievers, DR Tulu and AgentIR Show
CShorten30 · x · 2026-09-05
CShorten30 recaps AkariAsai's VLDB talk on Deep Research, covering two projects:
- DR Tulu: trains deep research agents with rubrics to choose between BM25 and vector search retrievers, with strong results
- AgentIR: trains a dedicated embedding model for the agent's intermediate reasoning and search queries — an insight the author calls brilliant
Key takeaway: Deep Research performance depends on co-designing agents and retrievers rather than optimizing either in isolation.
Related event: VLDB talk: Deep Research agents need co-designed retrievers(4 posts)→
More from coding & agent
- JSON prompting with MOSS Image 5B: bbox coordinates for exact multi-room layouts — cocktailpeanut · 2026-10-21
- Rewriting an agent skill: A/B challenge runs show skills should only add what agents don't know — jmschreiber91 · 2026-10-21
- Developer builds himself a 'Rork MoTS' agent on Grok Bot, aiming for full autonomy before GTA 6 — rudrank · 2026-10-21
- OpenAI Live API tip: control voice sessions from your backend via sideband WebSocket — pbbakkum · 2026-10-21
- OpenAI's MultiLangBench: PHP scores highest (91.3%) at building a database engine from scratch — ricklamers · 2026-10-21
- UserProof lets Claude Code watch your user session recordings and boost conversion for $29/mo — doooyle · 2026-10-21