Paper page - Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents

Source: https://huggingface.co/papers/2606.13174 Authors:

,

,

,

,

,

,

,

,

,

Abstract

TRACE is a skill-layer pipeline that mines user corrections to create runtime checks, significantly reducing preference violations in interactive LLM agents.

InteractiveLLM agentsare becoming part of daily work, but they do not reliably become easier to work with over time: a correction remembered in one session may still be violated in the next. We study this gap between preference access andpreference compliance. In tasks derived from anonymized real-user friction cases, Mem0 memory still leaves 57.5% of applicable preference checks violated. We introduce Test-timeRule AcquisitionandCompiled Enforcement(TRACE), a drop-in skill-layer pipeline for coding-agent runtimes that minesuser corrections, rewrites them as atomic rules, and compiles them intoruntime checksthat must pass before an agent completes future tasks. Unlikeruntime checkswritten ahead of time by developers, TRACE skills come from the user’s own chat corrections. We evaluate TRACE with simulated user-in-the-loop experiments on ClawArena coding-agent tasks and MemoryArena-derived memory-intensive tasks. On ClawArena, TRACE reduces held-out preference violation from 100.0% to 37.6% onin-distributiontasks and from 100.0% to 2.0% onout-of-distributiontasks. On MemoryArena-derived tasks, TRACE reducesin-distributionviolation from 100.0% to 60.5% while matching or exceeding the strongest memory baseline ontask pass. These results suggest that compiling corrections into runtime enforcement can address a repeated-friction failure mode that memory alone does not reliably solve, reducing the need for users to restate the same correction across future sessions. Experiment code is available at https://github.com/YujunZhou/TRACE_exp, and the deployable skill is available at https://github.com/YujunZhou/tellonce.

View arXiv pageView PDFGitHubAdd to collection

Get this paper in your agent:

hf papers read 2606\.13174

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.13174 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.13174 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.13174 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.