arXiv:2606. 12864v1 Announce Type: cross Abstract: Despite strong performance in competitive programming, the role of Large Language Models (LLMs) in supporting human learning in the same setting remains largely unexplored.
arXiv:2606. 08840v1 Announce Type: new Abstract: Code generation models are typically compared using compact execution benchmarks and aggregate pass rates, but such summaries obscure how performance varies across programming languages, problem families, and failure modes.
arXiv:2510. 09595v3 Announce Type: replace Abstract: Competitive programming problems are increasingly used to evaluate the coding capabilities of large language models (LLMs) due to their complexity and ease of verification.
The paper introduces RobustTests, a framework that improves reinforcement learning for code generation by synthesizing test cases from faulty code and refining rewards with a dense, stepwise function. It uses validator agents and behavioral clustering to filter out invalid or redundant tests, and incorporates pass‑rate‑based rewards to counter hallucination noise. Experiments on CodeContests and LiveCodeBench show that fine‑tuning Qwen3‑32B with RobustTests yields a 3% absolute performance gain over baseline methods.
The paper investigates how large language models (LLMs) handle bug fixing versus problem solving in competitive programming. Using a dataset of ~3,000 Codeforces submissions and their human fixes, the authors compare LLM-generated patches to human patches and assess whether LLMs prefer to modify buggy code or generate new solutions. Results show that LLMs often alter more lines than necessary and sometimes produce entirely new solutions, performing better when allowed to generate solutions from scratch rather than patching existing code.
The paper investigates how Large Language Models (LLMs) handle bug fixing compared to human-written patches by analyzing about 3,000 Codeforces submissions. It finds that LLMs often modify more lines than necessary and sometimes produce entirely new solutions, and that they solve more problems correctly when generating solutions from scratch rather than patching existing code. The study highlights implications for AI‑assisted programming tools, suggesting a shift toward incremental problem‑solving strategies.
arXiv:2507. 22580v2 Announce Type: replace-cross Abstract: Automated Program Repair (APR) seeks to automatically correct software bugs without requiring human intervention.
arXiv:2505. 07372v3 Announce Type: replace-cross Abstract: This paper presents a novel methodology for enhancing Automated Program Repair (APR) through synthetic data generation utilizing Large Language Models (LLMs).
The paper introduces CodeRQ-Bench, the first benchmark for assessing large language model reasoning quality across coding tasks such as generation, summarization, and classification. It analyzes over a thousand mismatches from existing evaluators, identifies recurring limitations, and derives design insights that lead to a new two‑stage evaluator, VERA. Experiments show VERA outperforms strong baselines, improving AUCROC by up to 0.26 and AUPRC by up to 0.21 on four datasets.
arXiv:2501. 10711v5 Announce Type: replace-cross Abstract: Code-related benchmarks play a critical role in evaluating large language models (LLMs), yet their quality fundamentally shapes how the community interprets model capabilities.
The paper introduces MCR-Bench, a benchmark for realistic multi‑round code review that includes 2,269 real‑world tasks across five programming languages, each annotated with fine‑grained defect information and dynamic state labels. Experiments with mainstream large language models show limited overall performance, especially as interaction rounds increase, and reveal that model accuracy varies by defect type and severity. Error analysis identifies key failure mechanisms such as cross‑round temporal misalignment and insufficient long‑range memory.
Large language models (LLMs) are increasingly used as judges for code evaluation, assessing correctness without reference implementations. This study investigates whether LLM judges can fairly evaluate semantically equivalent code that differs in superficial aspects such as variable names, comments, or formatting. The authors define six types of potential bias, conduct experiments across five programming languages and multiple LLMs, and find that all tested judges exhibit both positive and negative biases, leading to inflated or unfairly low scores even when prompted to generate test cases.
The paper introduces SWE-Flux, a repository‑level benchmark designed to test large language models’ ability to reason about runtime behavior. It contains 480 execution‑grounded instances from 12 real Python repositories, with gold answers automatically harvested from instrumented test executions. Evaluation of five LLMs shows the task remains difficult, with the best model achieving only 37% accuracy, and the benchmark can generate challenging variants through input perturbation.