arXiv:2606. 28438v1 Announce Type: cross Abstract: Recursive self-training can degrade neural generative models when generated data is reused without fresh human data or external quality control.
arXiv:2607. 13091v1 Announce Type: cross Abstract: LLM-based coding agents repeat the same classes of mistakes across sessions because they lack a mechanism to retain corrections from human review feedback.
arXiv:2607. 29516v1 Announce Type: cross Abstract: AI coding agents are generating code at volumes that exceed the capacity of traditional peer review.
arXiv:2606. 08676v1 Announce Type: cross Abstract: AI coding assistants have significantly improved developer productivity by automatically suggesting code that aligns with user intent, and many of these tools are now integrated directly into Integrated Development Environments (IDEs).
arXiv:2608. 14659v1 Announce Type: new Abstract: Large language models for code generation often produce incorrect solutions without reliable indicators of failure.
arXiv:2606. 26294v1 Announce Type: cross Abstract: Self-improving agents are state-of-the-art (SOTA) on agentic coding benchmarks and have recently been extended to general domains.
arXiv:2608. 04439v1 Announce Type: cross Abstract: Large language models (LLMs) have made notable progress in code generation, but they still struggle on challenging tasks that require sophisticated algorithms or complex implementations.
arXiv:2605. 17548v2 Announce Type: replace-cross Abstract: Code review has evolved for decades, from informal peer checking to today's pull request (PR) workflows, yet it remains a largely manual and cognitively demanding process.
arXiv:2604. 01527v4 Announce Type: replace-cross Abstract: Production deployment of AI coding agents requires fast, reproducible evaluation signals.
arXiv:2608. 05179v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly used across the scientific research lifecycle: ideation, literature search, experiment design and execution, analysis, manuscript drafting, and review.
arXiv:2606. 12117v1 Announce Type: cross Abstract: Benchmark scores often misrepresent a large language model's (LLM's) knowledge, because they rely, e.
arXiv:2607. 05541v1 Announce Type: cross Abstract: Reinforcement Learning is commonly used to train large language models using environmental feedback.
arXiv:2605. 30208v2 Announce Type: replace-cross Abstract: AI-assisted coding tools have altered software production.