# The LLM Proposes, the Executive Disposes: A Self-Verifying Agent Instrument that Dissociates Commitment Drift from Binding Drift in Long-Horizon Agents

arXiv: https://arxiv.org/abs/2608.04066 · HTML: https://mlsanity.com/paper/2608.04066/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 7 of its 8 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 7 of 7)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs](https://mlsanity.com/paper/2410.14641/) (2024)
- [Inherited Goal Drift: Contextual Pressure Can Undermine Agentic Goals](https://mlsanity.com/paper/2603.03258/) (2026)
- [A Categorical Analysis of Large Language Models and Why LLMs Circumvent the Symbol Grounding Problem](https://mlsanity.com/paper/2512.09117/) (2025)
- [Explore Before You Solve: The Speed--Depth Trade-off in Epistemic Agents for ARC-AGI-3](https://mlsanity.com/paper/2605.25931/) (2026)
- [Sensi: Learn One Thing at a Time -- Curriculum-Based Test-Time Learning for LLM Game Agents](https://mlsanity.com/paper/2603.17683/) (2026)

## Abstract (arXiv)

How do you verify a long-horizon agent when its own state and self-reports are exactly what you cannot trust? We present an agent instrument built so that verification is structural rather than post-hoc. A deterministic Executive owns all belief; a language model may only file typed proposals, and a claim is admitted only when a prediction pre-registered before acting is matched against observation by code. Two properties make the instrument a verifier of its own science, not just of the agent: every run invalidates itself when per-organ write-error, render-size, or salted-canary-echo floors are breached (four of the first eight architecture runs were invalidated, each localizing a real defect); and a render-invisible shadow reference compiles the plan the full system would have committed in every ablation cell, so drift metrics are defined even where the mechanism under test has been removed. Using this instrument we report a clean, single-variable result on a failure every long-horizon agent suffers: ablating the commitment mechanism flips goal-abandonment from 0.00 to 1.00 while binding error stays flat at 0.00 (three seeds per cell, up to 394 reference beats per run, every run gated valid). The binding channel, by contrast, does not reappear as per-beat drift when its repair is ablated -- because binding is code-owned, the failure class is structurally absorbed, its only residue appearing one layer upstream as a collapse in hypothesis formation. We report these under full disclosure that task efficacy is null (zero level completions across 52 gated runs on ARC-AGI-3), pre-registered as a structural defeater. The contribution is a verification methodology for agent development and the drift decomposition it makes measurable.