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 CODE SLOP—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 CODE SLOP directly, TRIM instead minimizes agent trajectories. As we show empirically, this indirect technique of minimizing CODE SLOP is highly effective: TRIM cuts CODE SLOP 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.
Coverage
- The Inference Weekly Trim the Slop: How Trajectory-Guided Redundancy Minimization Makes AI-Generated Code Cleaner
- Scan AI Slop CodeSlop: Why AI Coding Agents Leave Abandoned Edits Behind
- AgentPatterns.ai CodeSlop: Search-Trajectory Residue in Agent Patches