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 Must Co-Train with Retrievers(3 posts)→
More from coding & agent
- Lindy Launches CC Scheduling: Just CC the AI Agent on Any Email Thread to Book Meetings — HeyToha · 2026-09-05
- Claude Code criticized: no full conversation history or search in VSCode — Birchlabs · 2026-09-05
- Tencent's 770B Hy4 preview builds a playable 3D game from one prompt in agent test — HeyToha · 2026-09-05
- Raspberry AI turns plain-English requests into fashion renders and tech packs on LangGraph — LangChain · 2026-09-05
- Perplexity CEO Declares the End of Markdown Files: Bitter Lesson Wins Again — AravSrinivas · 2026-09-05
- Codex rust-v0.153.3 Hotfix Adds GPT-6-Astra to Amazon Bedrock — github-actions[bot] · 2026-09-05