TL;DR
A production-derived, white-box code-audit workflow whose instructions, edited files, tool logs, and expected checks are observable is examined, showing how a few omitted requirements can invalidate an otherwise complete artifact.
Experiments on guideline-following and artifact-generation tasks show that specifications can serve not merely as behavioral guidance, but as authority over compliant execution and completion.
A novel and scalable framework that rewrites a coding agent's context as the repository changes rather than as the context grows, and can achieve a higher resolve rate in all experiments spanned by six coding agents and three edit-heavy benchmarks with little computational overhead.
Across three models, two reasoning regimes, and two domains, four findings hold without per-turn reasoning: displaying accurate state is unreliable, an unverified ledger the agent writes itself beats an accurate checklist it is shown, directives help in proportion to the model's obedience, and enforcement needs no obed...
Long-horizon agentic workflows require models to sustain repeated state-dependent actions all while the context grows, sub-task complexity changes, and new data arrives. Each situation represents an independent axis along which an agent may fail. An agent reconciling a long ledger, for example, must repeatedly read its...
Evidence-Carrying Termination (ECT): an agent may return COMPLETE only when a typed certificate binds every required answer claim to valid, in-scope trace evidence and a deterministic replay reconstructs the claimed value.
Which component matters more depends on the loss assigned to erroneous acceptance: at low liability the planning gain dominates; at high liability the verifier's avoided false passes dominate; and a standalone verifier captures nearly all the false-pass benefit of the full planning-plus-verification stack at a fraction...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
