TL;DR
It is argued that without principled governance, agent-oriented documentation risks undermining both human comprehension and agent reliability, and a proposed foundational directions for restoring coherence are proposed.
A pipeline promoting an AI system publishes records claiming the thing evaluated is the thing deployed and that the evidence licensed the transition, and measures whether those records can express that claim and whether it holds where declared.
Operating systems must evolve continuously. Yet their development remains code-centric and largely manual: even a localized change can require recovering implicit assumptions, coordinating multiple subsystems, and repeatedly building, booting, testing, and debugging the complete system. General-purpose coding agents au...
Tracekit is an open-source, dependency-free system that captures three channels for every agent session: what the human asked (intent), what the model said of its reasoning (self-report), and what it actually executed (actions).
Repo2Skill-Evo casts each release transition as a skill-maintenance task: given a V1 skill set and the official V1-to-V2 patch, an agent must update obsolete skill content while preserving guidance that remains valid.
This survey examines agentic artifact creation, which is defined as stateful construction in which an AI system materially constructs or revises a deliverable and intermediate observations redirect later work, and formulate principles for keeping commitments and responsibility explicit, turning feedback into targeted r...
Preference and instruction contamination---persistent, lacking self-correction, and poorly captured by standard monitoring---represent a particularly concerning attack surface for deployed agent systems.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
