CMU guest lecture covers deep research agents: eval, RL, and new retrieval paradigm
AkariAsai · x · 2026-10-20
Akari Asai gave an invited lecture on deep research agents for CMU's AI Agents course, covering:
- Evaluation beyond simple factoid QA
- RL for open-ended tasks
- A new retrieval paradigm for deep research agents
The lecture materials are publicly available.
More from coding & agent
- SharePoint MCP Server gives AI assistants search over company docs via Graph API — modelcontextprotocol · 2026-10-20
- Census MCP connector pipes U.S. Census Bureau housing APIs into AI agents — modelcontextprotocol · 2026-10-20
- Open source isn't obsolete in the agent era, says maintainer changing how he contributes — charles_irl · 2026-10-20
- Dev proposes 'background codemode': strongly typed, inspectable agent workflows — lucasmeijer · 2026-10-20
- Builders ditch LangChain: why more devs roll their own agent harness — raftconsensus · 2026-10-20
- Anonymous audits of public MCP servers find read-only tools that can write and spend — Suncly_com · 2026-10-20