Abstract:Large Language Models (LLMs) have revolutionized various domains, including natural language processing, data analysis, and software development, by enabling automation. In software engineering, LLM-powered coding agents have garnered significant attention due to their potential to automate complex development tasks, assist in debugging, and enhance productivity. However, existing approaches often struggle with sub-optimal decision-making, requiring either extensive manual intervention or inefficient compute scaling strategies. To improve coding agent performance, we present Dynamic Action Re-Sampling (DARS), a novel inference time compute scaling approach for coding agents, that is faster and more effective at recovering from sub-optimal decisions compared to baselines. While traditional agents either follow linear trajectories or rely on random sampling for scaling compute, our approach DARS works by branching out a trajectory at certain key decision points by taking an alternative action given the history of the trajectory and execution feedback of the previous attempt from that point. We evaluate our approach on SWE-Bench Lite benchmark, demonstrating that this scaling strategy achieves a pass@k score of 55% with Claude 3.5 Sonnet V2. Our framework achieves a pass@1 rate of 47%, outperforming state-of-the-art (SOTA) open-source frameworks.
Abstract:Autoencoder (AE) is a neural network (NN) architecture that is trained to reconstruct an input at its output. By measuring the reconstruction errors of new input samples, AE can detect anomalous samples deviated from the trained data distribution. The key to success is to achieve high-fidelity reconstruction (HFR) while restricting AE's capability of generalization beyond training data, which should be balanced commonly via iterative re-training. Alternatively, we propose a novel framework of AE-based anomaly detection, coined HFR-AE, by projecting new inputs into a subspace wherein the trained AE achieves HFR, thereby increasing the gap between normal and anomalous sample reconstruction errors. Simulation results corroborate that HFR-AE improves the area under receiver operating characteristic curve (AUROC) under different AE architectures and settings by up to 13.4% compared to Vanilla AE-based anomaly detection.