Zero-Skills in Context: Sub-Second Algebraic Compilation of Agent Procedures into Feed-Forward Weights
Year: 2026
Type: preprint
Abstract: Version 2 - correction notice (11 November 2026). An internal evidence audit found that the compiled-guardrail condition reported in Section 5 of v1 was never executed: the harness recorded the verdict as a literal (compiled_refused = True, compiled_intercept_pct = 100.0) and never mounted the cartridge. The 100.0% interception claim is therefore withdrawn. An independent re-run that actually mounted the mechanism on the model named in the paper (Qwen2-0.5B-Instruct-Abliterated) produced 0 refusals across 24 adversarial prompts: baseline 0/24; nullspace-only 0/24; the paper's random refusal attractor 0/24; a corrected refusal-embedding direction 0/24. A strength sweep reached 1/24 at 100x gain over five layers. Two adjacent claims are restated. The Olympiad result (60.0% to 100.0%) rests on n = 5 problems with overlapping 95% intervals ([23.1%, 88.2%] versus [47.8%, 100%]). The +48.1% to +76.3% figure is a prefill/KV effect, not decode: across six checkpoints decode is unchanged (0.96-1.03x) while time-to-first-token falls 6.1-24.8x and KV residency 5-49x with a 4,000-token prompt. What still holds: exact frozen mounting (7/7 restoration checks per model, 100/100 cycles), 1.2-2.8 ms mount cost, and the in-context prefill/KV cost. The corrigendum PDF, corrected manuscript sources, audit JSON and benchmark reports are attached to this version.
Author: Machado, Luis
Institution: IU International University of Applied Sciences
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7225801303
Cites:
Cited by:
Related to: