arXiv:2607. 06619v1 Announce Type: cross Abstract: Modern processor verification struggles to reach deep architectural states due to the inefficiencies of traditional mutation-based fuzzing.
arXiv:2606. 28403v1 Announce Type: cross Abstract: Vulnerability detection in C/C++ software remains a major security challenge due to code complexity, manual memory management, and the limitations of traditional static analysis.
arXiv:2609.06229v1 Announce Type: cross Abstract: Vulnerability discovery is becoming an important ability of large language model (LLM) agents: agents that silently miss real defects leave critical...
arXiv:2607. 25647v1 Announce Type: cross Abstract: As quantum computing continually improves, ensuring the reliability and correctness of quantum libraries has become increasingly critical.
arXiv:2609.38275v1 Announce Type: cross Abstract: Persistent memory helps LLM agents carry information across long interactions, but correct memory can still be used incorrectly when queries change o...
arXiv:2608. 01804v1 Announce Type: new Abstract: Post-training large language models (LLMs) via reinforcement learning (RL) has significantly advanced code generation capabilities.
LEGO-RL is a framework that connects native coding-agent harnesses with scalable policy‑gradient training without altering the harnesses’ internal flow. It achieves faithful optimization through in‑process LLM proxying, reliable execution via sandbox orchestration, and observable training with automated validation and a Live UI. Experiments show LEGO‑RL improves the Qwen3.5‑35B‑A3B model’s performance on three native harnesses while preserving high rollout‑training probability correlation.
arXiv:2608. 02712v1 Announce Type: cross Abstract: Kernel generation for hardware accelerators such as GPUs and NPUs has become a proving ground for large language models (LLMs), and state-of-the-art systems raise correctness through pipelines that couple LLMs with agentic reinforcement learning and evolutionary search.
The paper introduces a domain‑specific debugging agent for repairing near‑miss accelerator kernels, arguing that debugging is more efficient than regenerating kernels from scratch. It tackles knowledge scarcity, integrity, and cost control through pattern retrieval, anti‑cheat detection, and convergence safeguards. Empirical results show the debug agent achieves a 66.7% Pass@1 rate and uses 92.8% fewer tokens per success compared to traditional regeneration methods.
FrogNano is a 4B coding agent trained exclusively with reinforcement learning on about 1,500 synthetic software engineering environments. Its training leverages an online task synthesis pipeline that generates tasks at the current agent’s learnability frontier, improving performance without distilling from larger models. The report details the methodology, evaluates the agent across diverse environments, and analyzes its effectiveness as a lightweight coding agent for minimal hardware.
arXiv:2609.23889v1 Announce Type: cross Abstract: Automated kernel vulnerability reproduction is essential for bug triage, patch validation, and regression testing, but still lacks an effective and...
arXiv:2610.23195v1 Announce Type: new Abstract: Collecting and labeling diverse test datasets for evaluating Deep Neural Networks (DNNs) is costly and time-consuming. This has motivated coverage-guid...
arXiv:2608. 10090v1 Announce Type: new Abstract: Large language models (LLMs) have advanced code generation, where executable feedback provides a more reliable learning signal than textual imitation alone.