TRIM: Reducing AI-Generated CodeSlop via Agent Trajectory Minimization

2026-07-20

AI Summary

This work addresses the prevalence of non-functional redundancy—termed CodeSlop—in code generated by AI programming agents, which leads to code bloat and reduced maintainability. The paper presents the first formal characterization of the CodeSlop problem and introduces a novel paradigm that minimizes agent search trajectories rather than directly pruning generated code. Building on this insight, the authors propose TRIM, a trajectory-guided algorithm for identifying and eliminating redundancy without resorting to high-overhead debugging techniques such as Delta Debugging. Evaluated across multiple agent frameworks, TRIM reduces CodeSlop by 17.9%–32.9%, cuts validation costs by approximately 50%, and incurs negligible performance degradation.

Abstract

Coding agents are increasingly used to accelerate code generation in many downstream tasks, such as fixing bugs, building applications, and prototyping. However, despite their value as coding assistants, agent-generated code tends to be larger and more verbose than the corresponding human-written implementation. In this work, we show that the cause lies in the agent's own search process: while iterating toward a passing solution, an agent accumulates speculative edits, abandoned hypotheses, and temporary changes that persist into the final patch. This may seem harmless for a single patch, but the problem compounds as agents take responsibility for ever-larger portions of a codebase-a codebase that was once minimal and well-maintained slowly accumulates redundancy faster than it can be cleaned up, drifting to a state that is harder to maintain. Given the magnitude of this problem, we take a step towards alleviating this issue. First, we formally define this phenomenon as CodeSlop-the residual and functionally unnecessary edits commonly seen in AI-generated code. We then introduce our algorithm TRIM (Trajectory-guided Redundancy Identification and Minimization). Rather than minimizing CodeSlop directly, TRIM instead minimizes agent trajectories. As we show empirically, this indirect technique of minimizing CodeSlop is highly effective: TRIM cuts CodeSlop by 17.9%-32.9% across agentic scaffolds, with negligible performance regression. TRIM is also highly efficient, requiring roughly half the validation cost of algorithmic baselines such as Delta Debugging.

Problem

• CodeSlop
• AI-generated code
• code redundancy
• coding agents
• code maintainability

Innovation

• CodeSlop
• Agent Trajectory Minimization
• TRIM
• AI-generated code
• Redundancy Reduction