# TRIM: Reducing AI-Generated CodeSlop via Agent Trajectory Minimization

arXiv: https://arxiv.org/abs/2607.18161 · HTML: https://mlsanity.com/paper/2607.18161/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 20 of its 35 references that are in the map.
- First posted on arXiv 20 Jul 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 20 of 20)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?](https://mlsanity.com/paper/2511.13646/) (2025)
- [Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling](https://mlsanity.com/paper/2507.23370/) (2025)
- [What's Wrong with Your Code Generated by Large Language Models? An Extensive Study](https://mlsanity.com/paper/2407.06153/) (2024)
- [SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks](https://mlsanity.com/paper/2603.24755/) (2026)
- [Speed at the Cost of Quality: How Cursor AI Increases Short-Term Velocity and Long-Term Complexity in Open-Source Projects](https://mlsanity.com/paper/2511.04427/) (2025)
- [Agentic AI Software Engineers: Programming with Trust](https://mlsanity.com/paper/2502.13767/) (2025)
- [Code Researcher: Deep Research Agent for Large Systems Code and Commit History](https://mlsanity.com/paper/2506.11060/) (2025)
- [KGym: A Platform and Dataset to Benchmark Large Language Models on Linux Kernel Crash Resolution](https://mlsanity.com/paper/2407.02680/) (2024)
- [Compressing Code Context for LLM-based Issue Resolution](https://mlsanity.com/paper/2603.28119/) (2026)
- [A Taxonomy of Inefficiencies in LLM-Generated Python Code](https://mlsanity.com/paper/2503.06327/) (2025)
- [Debloating Software through Piece-Wise Compilation and Loading](https://mlsanity.com/paper/1802.00759/) (2018)
- [Measuring AI "Slop" in Text](https://mlsanity.com/paper/2509.19163/) (2025)
- [What to Cut? Predicting Unnecessary Methods in Agentic Code Generation](https://mlsanity.com/paper/2602.17091/) (2026)
- [Why Agentic-PRs Get Rejected: A Comparative Study of Coding Agents](https://mlsanity.com/paper/2602.04226/) (2026)
- [Novice Developers Produce Larger Review Overhead for Project Maintainers while Vibe Coding](https://mlsanity.com/paper/2602.23905/) (2026)
- [Faster Code, Deeper Debt? A Multivocal Literature Review on Technical Debt and Its Early Signs in LLM-Assisted Software Development](https://mlsanity.com/paper/2606.14796/) (2026)
- [Outrunning LLM Cutoffs: A Live Kernel Crash Resolution Benchmark for All](https://mlsanity.com/paper/2602.02690/) (2026)

## Abstract (arXiv)

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.