Mohit Bansal's Northwestern lecture: fixing agent trust, world discovery, and long-horizon memory
ManlingLi_ · x · 2026-11-07
Mohit Bansal (UNC Chapel Hill) delivers a Distinguished Lecture at Northwestern CS on Nov 9: "AI Challenges: Trustworthy Collaboration, World Discovery, and Long-Horizon Memory."
- Trustworthy collaboration: speaker-listener confidence calibration in social/pragmatic multi-agent interaction, balancing positive and negative persuasion, and multi-agent AI safety via compositional attacks, theory-of-mind, and belief-steering.
- Skills & world models: discovering reusable programmatic skills, weakness-driven adaptive data/environment generation, structured world model discovery and inference.
- Long-horizon memory: planning memory for multi-step reasoning and generation over evolving, conflicting, scattered information.
Spans math, commonsense, coding, tool-use, computer use, embodied actions; text/image/video/audio/gaze/layout modalities; applications in early medical diagnosis and classroom engagement.
More from coding & agent
- Google team confirms Hacktron AI submitted high-impact vulns, expands partnership — ithilgore · 2026-11-07
- Stardock CEO: orchestrators miss the point—teams need exhibits and shared agent data — draginol · 2026-11-07
- Researcher uses Claude to auto-fix LaTeX figure offsets: "ridiculously painless" — alfcnz · 2026-11-07
- vmfunc shows off Reflet, a fully native disassembler for Mach-O/AArch64 — amplifiedamp · 2026-11-07
- Agentic robot assembles autonomously for 2.5 hours, one gadget every 7 minutes — ihorbeaver · 2026-11-07
- Agentic robot control demo: 2.5 hours autonomous assembly at one gadget per 7 minutes — ihorbeaver · 2026-11-07