Component-Aware Feedback for Self-Evolving Programs

arXiv:2604.05013v1 Announce Type: cross Abstract: Current LLM coding agents are predominantly trained on composite benchmarks (e.g., bug fixing), which often leads to

arXiv:2603.18620v1 Announce Type: cross Abstract: We introduce Learning to Self-Evolve (LSE), a reinforcement learning framework that trains large language models (LLMs) to

arXiv:2605.26720v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong empirical gains as self-evolving agents for CUDA kernel generation, driven by

arXiv:2604.21950v1 Announce Type: cross Abstract: Small language models (1-3B) are practical to run locally, but individually limited on harder code generation tasks. We ask

arXiv:2604.04940v1 Announce Type: new Abstract: Designing effective heuristics for NP-hard combinatorial optimization problems remains a challenging and expertise-intensive task.

arXiv:2609.19526v1 Announce Type: new Abstract: Coding agents can recursively modify their own implementations, forming a loop of self-improvement. While prior work shows this can

arXiv:2609.29154v1 Announce Type: new Abstract: Large language model agents increasingly rely on natural-language skills to solve complex tool-use tasks. However, such tasks often

arXiv:2604.21018v1 Announce Type: new Abstract: While scaling test-time compute can substantially improve model performance, existing approaches either rely on static compute