avatar

Cheng DENG (Daven)

Research Fellow
Bayes Centre, CSE
University of Edinburgh
Module Lead, PLIN0072
Linguistics, UCL

davendw49 (at) gmail.com
My Blog · All Talks

Trust, Memory, and Reuse: Three Safety Primitives for Agent Systems

Invited talk, University of Oxford, Oxford, UK. October 2026.

← All talks · Homepage

Abstract

Agent systems fail quietly: a retrieval that returns the wrong memory, a cached context that is reused out of place, a tool result that is trusted without checking. This talk proposes three primitives that make such failures visible and controllable. Trust: deciding which inputs, tools, and memories an agent may act on, and at what confidence. Memory: evaluating memory systems jointly with the retrieval regime and backbone that use them, where rankings change with access strategy and instrumentation separates integration defects from capability gaps. Reuse: reusing context and computation across turns and sessions without reusing errors. I draw on MemoryCraft and ContextPilot and on agents deployed on edge devices and robots.

Slides

This is an executable talk in the edtrace format used by Stanford CS336: the Python program is the slide deck. Text lines are the narration, code lines run and can be stepped through, and inspected values appear inline.

Open the executable slides →


Powered by Jekyll and Minimal Light theme.