As Code Large Language Models (LLMs) become central to modern software engineering, their inherent stochasticity poses significant real-world risks, where even minor errors can lead to severe functional, security, or safety consequences. Reliable automation, therefore, demands the ability to distinguish between confident, well-supported predictions and stochastic guessing.
The paper introduces PolyHuman, a dataset of human-written programs in C++, Java, and Python, to test whether large language models can judge functional equivalence across languages. Using this dataset, the authors evaluate several open-weight and proprietary LLMs, finding that models struggle more with harder problems, show language-specific biases, and rely partly on superficial similarity cues. They also observe run‑to‑run instability in GPT‑o4‑mini, concluding that current LLMs do not reliably capture functional equivalence within or across programming languages.
By Hui Sun, Anderson Uch\^oa, Rohit Gheyi, Wesley K. G. Assun\c{c}\~ao
arXiv:2508. 16131v3 Announce Type: replace-cross Abstract: Code completion entails the task of providing missing tokens given a surrounding context.
By Zoe Kotti, Konstantina Dritsa, Diomidis Spinellis, Panos Louridas
arXiv:2606. 09577v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as code generators, where silently wrong programs pose real safety and reliability risks.
By Yuling Shi, Caiqi Zhang, Yuexian Li, Haopeng Wang, Yeheng Chen, Nigel Collier, Xiaodong Gu
The thesis explores Introspective Uncertainty Estimation (IUE) for large language models (LLMs) in code generation, aiming to determine whether hidden-state representations can indicate functional correctness at both response and line levels. Using LiveCodeBench and BigCodeBench, the study finds that hidden states provide a strong signal for overall correctness, with static single-token probes performing best, while dynamic strategies offer no consistent advantage. Although line-level fault localization is more challenging, a conditional Top‑K ranking approach remains effective, suggesting a two‑stage workflow that first screens responses for risk and then prioritizes line‑level checks.
By Thomas Klassert
arXiv:2606. 09800v1 Announce Type: cross Abstract: Multi-agent code generation offers a promising paradigm for autonomous software development by simulating the human software engineering lifecycle.
By Shizhe Lin, Ladan Tahvildari