LLM Code Generation

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

17 papers in the last four weeks, up 42% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 196

Jun 3, 2026cs.CR

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration

Producing a labeled vulnerable code at scale is a recurring obstacle for learning-based vulnerability detection: mined corpora carry substantial label noise, and existing LLM-based augmentation propagates these inaccuracies because it transforms vulnerable seeds rather than synthesising vulnerabilities from a specification. A complementary route is to start from safe code and ask an instruction-tuned LLM to inject a specified CWE (which would shift the labeling burden from open-ended detection to bounded binary confirmation) but safety-aligned code LLMs systematically refuse such prompts. This paper is a preliminary feasibility study of abliteration, a low-rank weight edit that orthogonally projects out the refusal direction in the residual stream, as a tool to remove this barrier. We use Python and CWE-89 (SQL injection) as a case study, evaluating the Qwen2.5-Coder-Instruct family at 3B, 7B, and 14B parameters on safe samples drawn from PromSec and SafeCoder, replicated three times per condition. We find that (i) refusal on injection prompts is strongly size- and prompt-context-dependent: the 14B refuses 100% of prompts, the 7B refuses 73% of PromSec but only 5% of SafeCoder, whereas the 3B is essentially never blocked; (ii) abliteration reduces refusal to zero or near-zero across all sizes while leaving syntactic validity above 93%, supporting the view that, in this setting, refusal can be detached from measured code-generation capability; and (iii) the post-abliteration injection rate remains capacity-bound (88-97% on the 14B, 89-90% on the 7B, and 25-48% on the 3B) separating willingness, which abliteration unlocks, from capability, which scales with parameters. Vulnerability verdicts are produced by a three-tool detector ensemble (CodeQL, Semgrep, Bandit) followed by manual adjudication by two authors on detector-positive outputs.

Cristina Carleo, Pietro Liguori, Naghmeh Ivaki +1

University of Naples Federico II, Naples, Italy · University of Coimbra, CISUC/LASI, Coimbra, Portugal · University of North Carolina at Charlotte, Charlotte, NC, USA

LLM Safety Alignment LLMs for Cybersecurity LLM Code Generation

Jun 2, 2026cs.SE

FLARE: Fine-Grained Diagnostic Feedback for LLM Code Refinement

Large language models often generate code with bugs. Existing methods rely on feedback signals such as test failures and self-critiques to iteratively refine the generated code. Such signals are either too coarse-grained or too high-level, which is not sufficient to inform the model where to fix the bug. In this work, we present Flare, an iterative framework with a lightweight diagnostic model that predicts line-level suspiciousness signals for bug localization and code refinement. Given the inherent uncertainty of diagnostic predictions, Flare searches over the top-k suspicious regions and selects the best candidate according to execution outcomes. Experiments on LiveCodeBench and BigCodeBench with five base LLMs show that, even without candidate search (k=1), Flare outperforms the strongest baseline with an absolute improvement from 1.72% to 7.42%. Furthermore, searching over 10 candidates yields an average improvement of 8.50% compared with no candidate search. When evaluated in isolation, our lightweight diagnostic model achieves the best performance compared with recent fault localization methods, demonstrating that it can provide reliable fine-grained guidance for code refinement.

Yinsheng Yao, Hongxiang Zhang, Weixi Tong +1

Purdue University West Lafayette, IN, USA

LLM Self-Refinement Automated Program Repair Fault Localization LLM Code Generation Fault Diagnosis

Jun 2, 2026cs.AI

NovelAPIBench: Diagnosing How A Code LLM Learns to Use Novel APIs

Rapidly evolving software libraries require coding language models to use unfamiliar APIs. Yet failed solutions alone tell us little about what API knowledge models need or how to provide it. We present NovelAPIBench, an automated diagnostic framework that builds benchmarks around the API knowledge gaps of a target model. It identifies novel APIs, generates executable coding tasks with separately controllable knowledge components, and classifies failures into six categories. The framework can be rerun as models and libraries evolve. We study 21 libraries across five domains and six backbone models, with our primary benchmark comprising 1,670 tasks covering 856 APIs. Our experiments show that when supplied directly, usage examples provide the strongest standalone guidance for novel API acquisition, and combining them with signature descriptions approaches full-knowledge performance. Retrieving this knowledge from a pool of APIs yields lower accuracy than supplying only the target API's knowledge, even when retrieval finds the target. Fine-tuning on other APIs improves performance on unseen APIs mainly when external knowledge is supplied, helping models both select the target API and integrate it into the surrounding code. These findings highlight complementary roles for external API knowledge and the ability to apply it. By separating knowledge content, delivery, and use, NovelAPIBench helps diagnose what limits novel API use and guides adaptation to evolving libraries. Code and data are available at https://github.com/MAPS-research/NovelAPIBench.

Jinnuo Liu, Yue Peng, Jinhan Niu +1

NYU Shanghai

Knowledge Augmentation for Language Models LLM Fine-Tuning Code Language Models LLM Code Generation

Jun 2, 2026cs.SE

The Invisible Lottery: How Subtle Cues Steer Algorithm Choice in LLM Code Generation

Large language models (LLMs) now generate substantial production code, often for tasks with multiple valid algorithmic solutions. Incidental prompt cues, meaning contextual words or metadata outside the task specification, can steer which algorithm the model selects, even when all outputs pass the same tests. Prompt sensitivity is well studied as a tool to improve output quality. Here, output policy means algorithm choice under fixed correctness. We define algorithm steering as cue-induced shifts in algorithm-family distributions and run 46,535 controlled experiments across 11 tasks, 19 cue types (18 channels plus a memoization semantic-vs-surface ablation that preserves meaning while changing typography and punctuation), and 15 model configurations. We find large, systematic shifts in algorithm-family distributions (up to 100 pp), largely consistent with cue semantics, including in applied tasks such as rate limiting. Direct algorithm naming is the most reliable mitigation we tested. Accidental context therefore creates an "invisible lottery" over performance, security, and maintainability.

Akanksha Narula, Mofasshara Binte Rafique, Laurent Bindschaedler

Max Planck Institute for Software Systems (MPI-SWS), Saarbrücken, Germany · Independent Researcher, Switzerland.

Prompt Sensitivity LLM Prompting LLM Code Generation

Jun 2, 2026cs.LG

Synthetic Hallucinations, Real Gains: Hard Negatives from Frontier Models for FIM Hallucination Mitigation

Small open-source code models that power IDE autocomplete still emit hallucinated Fill-in-the-Middle (FIM) completions: syntactically natural calls to methods, parameters, variables, and imports that do not exist in the surrounding project. Existing mitigations either require per-language execution sandboxes that do not apply at mid-keystroke or preference-optimisation pipelines that need large human-labelled corpora. We propose an execution-free alternative: use frontier code models to synthesise plausible-but-wrong completions as hard negatives, then leverage the contrast between these synthetic hallucinations and the ground-truth developer edit as a supervised fine-tuning signal. Our pipeline scrapes multilingual FIM contexts from public GitHub across eight languages and asks a panel of three frontier generators to produce one hard negative per context for each of four hallucination types drawn from the Delulu taxonomy, a Docker-verified multilingual FIM hallucination benchmark, yielding a paired chosen/rejected dataset. Fine-tuning Qwen2.5-Coder-7B-Instruct on a 100K-row curated subset lifts Delulu exact match by +18.8 points and edit similarity by +0.22 on every language and every type, while also improving every HumanEval-Infilling split and every SAFIM subset. The same recipe at 3B lifts Delulu by +12.8 EM with a small, characterised general-FIM trade-off. Five-axis ablations (size, type mix, language coverage, base-model family, and a difficulty-aware fool rate) plus a head-to-head SFT vs. DPO/ORPO comparison map which design choices drive the gain. We release the full pipeline source code -- generation, fool-rate LLM judging, curation, and the FIM fine-tuning recipe -- so that the experiments in this paper can be reproduced end-to end on any permissively licensed corpus.

Mahdi Erfanian, Nelson Daniel Troncoso, Aashna Garg +4

University of Illinois Chicago · Microsoft

LLM Hallucination Mitigation Hard Negative Mining Synthetic Data Generation for Language Models LLM Code Generation

Jun 1, 2026cs.SE

CodegenBench: Can LLMs Write Efficient Code Across Architectures?

While large language models (LLMs) have been extensively evaluated on code generation tasks for general-purpose programming and GPU-accelerated environments (e.g., PyTorch, CUDA), their capabilities in CPU-oriented high-performance computing (HPC) across diverse architectures remain underexplored. To bridge this gap, we introduce CodegenBench, a comprehensive benchmark suite designed to evaluate the generation of efficient parallel code across three distinct hardware platforms: x86_64, Sunway, and Kunpeng. Our benchmark comprises 106 standard Basic Linear Algebra Subprograms (BLAS) routines establishing a fundamental baseline, alongside 20 specialized computational kernels adapted for each of the unique supercomputing architectures (LeetSunway and LeetKunpeng). Our extensive evaluation reveals that while state-of-the-art LLMs can generate optimized code for ubiquitous architectures like x86_64, they exhibit significant performance degradation on domain-specific architectures with limited public documentation and training data, highlighting critical limitations in cross-platform generalization. Furthermore, our analysis of factors influencing code quality such as implementation length and task complexity indicates that current LLMs are most effective for moderately difficult problems requiring concise code snippets. We open-source our dataset and automated evaluation infrastructure to facilitate future research in LLM-driven high-performance code generation. The resources are available at https://anonymous.4open.science/r/CodegenBench-EDE1/ and https://anonymous.4open.science/r/CodegenBenchDataset-2551.

Jie Li, Wenzhao Wu, Junqi Hu +5

1Sun Yat-sen University · 2National Supercomputing Center in Wuxi · 3National Supercomputing Center in Shenzhen +2

High-Performance Computing Code Generation Heterogeneous Computing Code Generation Benchmarks LLM Code Generation

Jun 1, 2026cs.CL

CRAFTQA: A Code-Driven Adaptive Framework for Complex Structured Data Reasoning

Real-world scenarios involve massive heterogeneous structured data (e.g., tables, knowledge graphs), making effective reasoning over such diverse data increasingly important. Unified structured data question answering has emerged as a prominent research trend, aiming to answer natural language questions across different structured data types within a single framework. However, existing unified methods share a common limitation: they rely on a set of predefined functions, which restricts their ability to perform complex reasoning beyond these predefined operations. To overcome this fundamental limitation, we propose CRAFTQA, a novel adaptive code-driven framework comprising two core modules, CodeSTEP and CRAFT. The CodeSTEP module is a paradigm that generates a complete executable Python code sequence, which contains step-by-step code-based reasoning operations based on the question. The CRAFT module dynamically generates custom code functions for operations beyond the predefined function set, and seamlessly integrates with CodeSTEP to significantly enhance flexibility in handling complex reasoning. Comprehensive experiments on multiple structured datasets demonstrate that CRAFTQA achieves remarkable improvements in complex reasoning scenarios compared to existing unified methods.

Chengtao Gan, Zhiqiang Liu, Long Jin +3

Zhejiang University · JIUTIAN Research, Beijing, China · Ant Group +1

Table QA LLM-Based Program Synthesis Algorithmic Reasoning LLM Code Generation

Jun 1, 2026cs.AR

EstRTL: Functional Estimation Guided RTL Code Generation

Optimizing register transfer level (RTL) code is of vital importance in hardware design. Large language models (LLMs) provide new methods for the automatic generation and optimization of RTL code, offering the potential to significantly accelerate the design process and reduce human effort. However, existing methods for generating RTL code often focus on model fine-tuning and the use of various expansion techniques to enhance the RTL code generation capabilities, lacking attention to the functional correctness. Ensuring that the generated RTL code not only compiles successfully but also behaves as intended in real hardware implementations remains a critical challenge. To address this issue, we propose EstRTL, an LLM-powered collaborative agent framework for RTL code generation based on static functional score estimation. EstRTL operates a three-stage paradigm: Generation, Estimation and Correction. During the stages, the functional estimation agent statically evaluates the generated code based on score and assessment results, and decides whether to output the code directly, return it for regeneration, or forward it to the code correction agent. This framework can be applied to various LLMs that designed for RTL code generation, further enhancing the correctness of the generated code. By providing quantitative scores and human-readable requirements comparisons, it improves the transparency of AI-assisted RTL code generation. Experiments show that EstRTL significantly improves the correctness of RTL code generation by generic LLM by 3.2%-9.0%, demonstrating the practical value of our system. The codes and experimental results are open-sourced at link: https://anonymous.4open.science/status/EstRTL-E200/.

Qi Xiong, Renzhi Chen, Bowei Wang +3

College of Computer Science and Technology, National University of Defense Technology, Changsha, China · Defense Innovation Institute, Academy of Military Science (AMS), Beijing, China · School of Computer Science and Technology, Shandong University, Qingdao, China +2

Code Generation Agentic Code Generation RTL Code Generation Code Generation Evaluation LLM Code Generation

May 29, 2026cs.SE

How Generation Architecture Shapes Code Complexity in Multi-Agent LLM Systems: A Paired Study on HumanEval

Large-language-model code generation has shifted from single-shot prompting to multi-agent orchestrations - analyst, coder, tester, and debugger pipelines - and is evaluated almost exclusively on functional correctness. Whether these architectures also affect the structural complexity of the code they produce, and which orchestration layers carry the cost, remains largely unexamined: prior work has documented prompt-level effects on code complexity, but the architecture-level question is open. We compare six widely-used multi-agent configurations (Basic, AC, ACT, Debugger, AC+Debugger, ACT+Debugger) under two models from the GPT-4o family across all 164 HumanEval tasks - 1,968 paired observations - using the five RADON complexity metrics (SLOC, cyclomatic complexity, and Halstead Volume, Difficulty, and Effort). We apply a paired non-parametric statistical pipeline (Friedman omnibus, Wilcoxon signed-rank post-hoc with Holm correction, Kendall's

W

and matched-pairs rank-biserial effect sizes) in both all-completions and passing-only conditions. The six architectures collapse into two indistinguishable complexity clusters separated by a 50-130% gap, the same partition in both models and under both conditions; among the architectural layers, the analyst-coder split inflates complexity, the runtime debugger does not - and on the analyst-coder background actively deflates it - and the tester re-inflates it. The heavy cluster's additional complexity buys no pass@1 advantage: the leanest architectures match or beat the heaviest on accuracy. Architectural elaboration in LLM code generation should therefore be justified by measured benefit on the dimensions that matter, not assumed.

Nazmus Ashrafi

Independent Researcher

Software Engineering Code Generation Evaluation Multi-Agent Coding LLM Code Generation

May 29, 2026cs.SE

Knowledge boundary probing and demand-guided intervention for LLM-based power system code generation

Large language models (LLMs) can turn grid-analysis requests into executable programs for power-system simulation, but utilities and research laboratories often require on-premise deployment. In this setting, first-pass failures frequently arise at an API-knowledge boundary, through hallucinated functions, misused parameters, and mishandled result tables. We present PowerCodeBench, a parameterised benchmark generator released as a frozen 2,000-task suite for pandapower, and a deployment-time workflow that requires no weight updates. Documentation-driven L0-L3 probes produce per-model API profiles for diagnosis, model comparison, documentation allocation, and backend calibration. A query-side demand estimator selects layered API evidence before generation, while execution feedback routes targeted repair. Across ten open-weight LLMs (1.5B-480B) and four mid-tier APIs, the validation-enabled workflow raises scalar-match accuracy by 32-56 percentage points after up to three repair rounds relative to an unassisted first pass, for every model of at least 7B and every API. Open-weight models in the 70B-120B range reach the four-vendor mid-tier accuracy range under matched no-tool conditions. Selective injection approaches the full-layer reference using 41% of its prompt tokens. Among model-item pairs passing numerical checks under both workflows, engineering review confirms the requested analysis in 88% of full-workflow outputs versus 66% under plain repair. Round-0 pilots on OpenDSS and PyPSA motivate staged onboarding from broad retrieval at cold start to calibrated selective injection. Measured throughput, latency, energy, and allocated GPU memory establish a practical on-premise serving envelope.

Hui Wu, Xiaoyang Wang, Zhong Fan

Department of Engineering, University of Exeter · Department of Computer Science, University of Exeter

Automated Program Repair Code Generation Code Generation Benchmarks LLM Code Generation Language Model Probing

May 29, 2026cs.CL

Mellum2 Technical Report

We present Mellum 2, an open-weight 12B-parameter Mixture-of-Experts (MoE) language model with 2.5B active parameters per token. Mellum 2 is a general-purpose language model specialized in software engineering, spanning code generation and editing, debugging, multi-step reasoning, tool use and function calling, agentic coding, and conversational programming assistance, and it is the successor to the completion-focused 4B dense Mellum model. The architecture builds on the Mixture-of-Experts (64 experts, 8 active) and combines Grouped-Query Attention with 4 KV heads, Sliding Window Attention on three of every four layers, and a single Multi-Token Prediction head that doubles as both an auxiliary pre-training objective and a built-in draft model for speculative decoding; each choice was validated by ablation with inference efficiency on commodity GPUs as a design constraint. Pre-training spans approximately 10.6 trillion tokens through a three-phase curriculum that progressively shifts the mixture from diverse web data toward curated code and mathematical content, optimized with Muon under FP8 hybrid precision and a Warmup-Hold-Decay schedule with linear decay to zero. The pre-trained base is extended to a 128K context window via a layer-selective YaRN and then post-trained in two stages (supervised fine-tuning followed by RLVR), yielding two released variants: an Instruct model that answers directly and a Thinking model that emits an explicit reasoning trace before its final answer. Across code generation, math and reasoning, tool use, knowledge, and safety benchmarks, Mellum 2 is competitive with open-weight baselines in the 4B-14B range while running at the per-token compute of a 2.5B dense model. We release the base, instruct, and thinking checkpoints, together with this report on the architecture decisions, data pipeline, and training recipe behind them, under the Apache 2.0 license.

Marko Kojic, Ivan Bondyrev, Aral de Moor +6

1JetBrains · 2Constructor University, Bremen, Germany

Mixture-of-Experts Language Models Open-Weight Language Models LLM Training LLM Code Generation

May 28, 2026cs.AI

SchGen: PCB Schematic Generation with Semantic-Grounded Code Representations

Printed circuit board (PCB) schematic design defines nearly all electronic hardware, but it remains manual and expertise-intensive. While generative AI has advanced digital and analog IC design, PCB schematic generation from natural-language intent is largely unexplored. This paper presents SchGen, the first large language model that generates editable PCB schematics from natural-language requests. The key challenge lies in the lack of an LLM-suited representation and a large-scale dataset. Current schematic formats are dominated by verbose, tool-specific syntax and geometry-heavy descriptions, making them difficult to generate reliably. We introduce a semantically grounded code representation that encodes schematic editing primitives with relative placement and pin-name-based wiring, transforming a geometry-driven generation problem into a semantics-driven matching task amenable to LLMs. We further construct a large-scale dataset of PCB schematics paired with user prompts via a human-agent collaborative pipeline that converts open-source hardware designs into our representation. Experiments show that SchGen significantly outperforms alternative representations and even larger general-purpose LLMs on wire connectivity accuracy and functional correctness. Our results highlight the critical role of representation design in enabling generative models for complex hardware design tasks.

Qinpei Luo, Ruichun Ma, Xinyu Zhang +1

University of California, San Diego · Microsoft Research Asia · The University of Texas at Austin

Electronic Design Automation LLM Code Generation

May 28, 2026cs.SE

Projectional Decoding: Towards Semantic-Aware LLM Generation

Large language models (LLMs) are increasingly used to generate software artifacts across many software engineering (SE) tasks, yet ensuring the semantic validity of these artifacts remains a fundamental challenge. Existing constrained decoding techniques can enforce syntactic correctness and, in some cases, specific semantic rules, but lack a general representation that bridges LLM-generated text with the reasoning required for semantic validation in SE. In this paper, we propose projectional decoding, a novel conceptual framework that integrates domain semantics directly into the generation process by maintaining, alongside text, a partial graph model as the primary artifact representation throughout generation. This abstract representation enables incremental semantic validation by explicitly capturing uncertainty and natively supporting error detection, while guiding generation toward semantically valid outputs with provable guarantees. We present preliminary results on a program generation task which demonstrate the potential of this approach to improve the semantic validity of LLM-generated artifacts. We also discuss how projectional decoding can enable verifiable automation with LLMs across various SE activities.

Boqi Chen, José Antonio Hernández López, Aren A. Babikian

University of Ottawa · University of Murcia · University of Toronto

Language Model Decoding LLM-Based Program Synthesis LLM Code Generation

May 28, 2026cs.SE

CodeGolf Bench: A Multi-Language Benchmark for Evaluating Concise Code Generation Capabilities of Large Language Models

This paper introduces Code Bench, a benchmark capable of evaluating Large Language Models (LLMs) concise code generation abilities in 60 programming languages. Based on code golf, a recreational programming competition focused on minimal character or byte solutions, the benchmark provides a distinctive measure of LLMs ability to produce efficient, concise code. Unlike existing benchmarks limited by fixed problem sets and language coverage, CodeGolf Bench leverages the code.golf platform to provide new problems and live human performance baselines. Evaluation of nine LLMs on Python and C++ tasks demonstrates that reasoning models significantly outperform non-reasoning models, achieving best average percentile of 70.97%. This performance gap is particularly pronounced in C++, highlighting reasoning's importance for languages with strict syntax requirements. Non-reasoning models struggle more with efficiency optimization across both languages, with best percentiles significantly lower than reasoning counterparts. CodeGolf Bench offers a dynamic framework for evaluating LLM code generation capabilities against evolving human performance on code golf.

Vedant Padwal

Independent

Language Model Generation Evaluation Code Generation Code Generation Evaluation Code Generation Benchmarks LLM Code Generation Multilingual Code Generation

May 28, 2026cs.SE

Inferring Code Correctness from Specification

Large language models (LLMs) have become integral to modern software development, enabling automated code generation at scale. However, validating the correctness of LLM-generated code remains a critical and largely unsolved challenge. Existing approaches either rely on dynamic consensus across multiple code candidates - making them costly and difficult to scale - or on static reasoning that is susceptible to dynamic bugs and order bias. In this paper, we propose TRAILS~ (Targeted Reasoning Agreement via Inputs and Specifications), an approach that grounds LLM reasoning with concrete (input, output) pairs. TRAILS~ first generates diverse test inputs via category partitioning based on the specification, then executes them against the candidate code and prompts LLMs to assess whether the resulting input-output pairs conform to the specification - without ever reasoning over the code itself. Scores are aggregated across inputs, to determines whether the program is likely correct. We evaluate TRAILS~ on two datasets, LiveCodeBench and CoCoClaNeL, across three LLMs (Qwen3Coder-30B, Devstral-Small-24B, and Olmo3.1-Instruct), comparing against HoarePrompt and a Zero-Shot Chain-of-Thought baseline. TRAILS~ improves Matthew Correlation Coefficient by up to 39% relative to Zero-Shot COT and consistently outperforms HoarePrompt. Beyond accuracy, TRAILS~ demonstrates greater stability across seeded runs, reducing sensitivity to LLM non-determinism, and assigns correct labels to a larger set of unique code samples than competing approaches.

Tambon Florian, Papadakis Mike

University of Luxembourg Luxembourg, Luxembourg

Automated Software Testing Code Generation Evaluation LLM Code Generation

May 27, 2026cs.SE

Do LLMs Favor Their Providers? Measuring Vertical Integration Bias in Code Generation

Large Language Models (LLMs) have become an integral part of software development, especially with the advent of agentic capabilities. Yet, many frontier LLMs are affiliated with specific providers. This raises the question of whether generated code favors the provider's own ecosystem over comparable alternatives, potentially constraining developers' choices and increasing dependence on a single provider. We define this behavior as Vertical Integration Bias (VIB) and introduce \textsc{VIBench}, a benchmark for measuring VIB in direct and agentic code generation across

20

provider-selectable software-integration scenarios. Evaluating

10

frontier provider-affiliated models against

3

non-affiliated controls, we find positive VIB in direct generation, with six of ten affiliated models showing statistically significant effects up to

+18.8

percentage points (pp). Agentic workflows further amplify VIB, reaching

+39.2

pp. Moreover, early affiliated-ecosystem choices in agentic workflows can persist into conceptually decoupled downstream files, with persistence as high as

90.3\%

. These findings underscore the need to measure and account for VIB in code generation, especially as agentic capabilities become more prevalent.

Melih Catal, Alex Wolf, Tiago Ferreiro Matos +2

University of Zurich · University of Mannheim

Agentic Code Generation Algorithmic Bias Language Model Bias Evaluation Code Generation Benchmarks LLM Code Generation

May 27, 2026cs.CL

Functional Entropy: Predicting Functional Correctness in LLM-Generated Code with Uncertainty Quantification

Large language models have shown impressive capabilities in code generation, yet they often produce functionally incorrect code. Uncertainty quantification (UQ) methods have emerged as a promising approach for detecting hallucinations in natural language generation, but their effectiveness for code generation tasks remains underexplored. We systematically evaluate how UQ techniques transfer to code generation across three programming languages, five LLMs, and over 1,700 problems. We find that some token-probability-based methods generalize effectively without modification, while sampling-based methods relying on natural language inference (NLI) fail because NLI models cannot distinguish functionally different code, causing most responses to collapse into a single semantic cluster. To address this, we introduce functional equivalence methods, a family of code-specific methods that replace NLI-based semantic equivalence with an LLM-based functional equivalence assessment, including functional entropy, a code-specific analog of semantic entropy. Functional equivalence methods achieve top AUROC in 11 out of 15 model-benchmark combinations and the best calibration across most settings, consistently outperforming both NLI-based counterparts and all other methods evaluated.

Dylan Bouchard, Mohit Singh Chauhan, Zeya Ahmad +1

CVS Health®, Wellesley, MA, USA

Language Model Calibration LLM Uncertainty Estimation Automated Evaluation LLM Code Generation

May 27, 2026cs.AI

Efficient Post-training of LLMs for Code Generation With Offline Reinforcement Learning

Post-training using online reinforcement learning (RL) is an important training step for LLMs, including code-generating models. However, online RL for code generation involves LLM inference and verification of the generated output, which can take considerable time and resources. In this paper, we explore the application of offline RL to code-generating models by leveraging existing code datasets. Our experiments demonstrate that offline RL is an effective training strategy for improving LLM performance. We show that offline RL can be especially beneficial for small LLMs and challenging coding problems.

Mingze Wu, Abhinav Anand, Shweta Verma +1

Technische Universitat, Darmstadt, Germany · Hessian Center for Artificial Intelligence, Darmstadt, Germany · National Research Center for Applied Cybersecurity ATHENE

RL for Code Generation Offline RL LLM Post-Training LLM Code Generation

May 27, 2026cs.LG

Learning the Error Patterns of Language Models

When generating outputs for domains with specific validity constraints (e.g., a program should compile), LLMs often fail in a small number of focused ways: for example, by using Python function names when generating TypeScript. We observe that these error patterns can be represented using a small number of constraints that can be learned in practice. We propose \emph{prefix filters}, which are per-domain-and-LLM symbolic functions, as objects to capture the error patterns, Palla as an algorithm to learn prefix filters efficiently in practice, and implement Palla. Prefix filters learned by Palla i) help us quantitatively analyze the error patterns of LLMs, and ii) can be used to constrain the outputs of a model via constrained sampling algorithms. For example, Palla boosts compile rates for Qwen2.5-1.5B on TypeScript generation, by over 60%, allowing Qwen2.5-1.5B to achieve similar performance to Llama3.1-8B unconstrained.

Jinwoo Kim, Taylor Berg-KirkPatrick, Loris D'Antoni

Constrained Decoding Language Model Error Detection LLM Code Generation

May 27, 2026cs.HC

Robo-Blocks: Generative Scaffolding in End-User Design and Programming of Social Robots

Programming social robots is challenging for novice robot programmers due to required expertise in planning, interaction design, and programming. While large language models (LLMs) hold significant promise through code generation from natural-language descriptions, they can obscure critical elements of programming and supplant designer intent, eventually resulting in over-reliance instead of developing programming skills. In this paper, we explore how LLM-based social-robot-programming tools can support novice robot programmers through a Research through Design (RtD) process. We designed and prototyped Robo-Blocks, a block-based programming environment that leverages LLMs to offer novice robot programmers generative scaffolding through structured narratives that connect high-level ideas to executable robot behaviors. Through deployment with novices, we discovered emerging user personas and usage patterns for generative scaffolding and showed how this scaffolding shapes end-user design and programming strategies. We present design insights for the effective use of generative scaffolding and its integration into the practice of social-robot programming.

Arissa J. Sato, Callie Y. Kim, Nathan Thomas White +4

Department of Computer Sciences University of Wisconsin–Madison

Programming Education Robotics Human-Robot Interaction LLM Code Generation

May 27, 2026cs.PL

FPMoE: A Sparse Mixture-of-Experts Approach to Functional Code Generation

Despite rapid progress in LLM-based code generation, existing models are predominantly trained on imperative languages, leaving functional programming languages (FPLs) such as Haskell, OCaml, and Scala chronically underexplored, with even frontier models performing substantially worse on FPLs. Fine-tuning is a natural remedy, but our experiments show that per-language fine-tuning fails to capture shared functional abstractions, while merged multi-language fine-tuning introduces cross-language interference. To address this, we introduce FPMoE, a lightweight, open-source code generation model built on a sparse Mixture-of-Experts (MoE) architecture with three language-specific routed experts (one each for Haskell, OCaml, and Scala) and a shared expert that captures cross-language functional patterns such as monadic reasoning and type-directed programming. This design resolves both failure modes simultaneously: dedicated experts eliminate interference, while the shared expert preserves abstractions that per-language models miss. On FPEval, FPMoE substantially outperforms fine-tuned baselines and, with only 3B active parameters, matches the performance of much larger models including DeepSeek-Coder-6.7B, Qwen2.5-Coder-14B-Instruct, and Qwen3-Coder-30B-A3B.

Loc Pham, Lang Hong Nguyet Anh, Thanh Le-Cong

GreenNode AI, Singapore · Hanoi University of Science and Technology · Singapore University of Technology and Design

Mixture-of-Experts Language Models Code Generation LLM Code Generation

May 26, 2026cs.CR

Poison with Style: A Practical Poisoning Attack on Code Large Language Models

Code Large Language Models (CLLMs) serve as the core of modern code agents, enabling developers to automate complex software development tasks. In this paper, we present Poison-with-Style (PwS), a practical and stealthy model poisoning attack targeting CLLMs. Unlike prior attacks that assume an active adversary capable of directly embedding explicit triggers (e.g., specific words) into developers' prompts during inference, PwS leverages developers' code styles as covert triggers implicitly embedded within their prompts. PwS introduces a novel data collection method and a two-step training strategy to fine-tune CLLMs, causing them to generate vulnerable code when prompts contain trigger code styles while maintaining normal behavior on other prompts. Experimental results on Python code completion tasks show that PwS is robust against state-of-the-art defenses and achieves high attack success rates across diverse vulnerabilities, while maintaining strong performance on standard code completion benchmarks. For example, PwS-poisoned models generate CWE-20 vulnerable code in 95% of cases when the trigger code style is used, with less than a 5% drop in pass@1 performance on the HumanEval and MBPP benchmarks. Our implementation and dataset are here: https://github.com/khangtran2020/pws.

Khang Tran, Yazan Boshmaf, Issa Khalil +3

Department of Data Science, New Jersey Institute of Technology, New Jersey, U.S.A. · Qatar Computing Research Institute, HBKU, Doha, Qatar · Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates

LLM Backdoor Attacks Data Poisoning Attacks Code Language Models LLM Code Generation

May 26, 2026cs.SE

Strategies for Guiding LLMs to Use Software Design Patterns: A Case of Singleton

Large Language Models (LLMs) can generate functional source code from natural-language prompts, but often fail to consistently follow higher-level architectural structures or design patterns. Since LLMs are increasingly used in software engineering, their ability to apply established design principles to generated code is crucial to the long-term success of software products. Therefore, the goal of this paper is to identify strategies for guiding LLMs to incorporate design patterns into the generated source code. We designed a computational experiment to evaluate the ability of 13 LLMs to generate code that follows the Singleton design pattern, using four prompting strategies: instructions, binary automated feedback, extensive automated feedback, and extensive feedback with few-shot prompts, in 164 Java coding challenges from HumanEval-X. Our results shows that the optimal strategy to guide LLMs to include design patterns depends heavily on the type of model. Still, overall, iterative binary feedback provides the best alignment with Singleton while preserving or improving the code's functionality. With guiding with instructions, Llama 3.3 generated Singleton classes in 100% of cases and improved code functionality, increasing the number of tests passed by 34.1 percentage points. It achieved a similar result with guidance through instructions and binary feedback. Qwen 3 (8B) increased the alignment with Singleton to 99.2% and the functionality to 58.6% using binary feedback. Our result suggests that even simple strategies can be used to guide LLMs to use design patterns.

Viktor Kjellberg, Farnaz Fotrousi, Miroslaw Staron

University of Gothenburg and Chalmers University of Technology Gothenburg, Sweden

LLM Prompting Code Generation LLM Code Generation

May 25, 2026cs.SE

A Tertiary Review of Large Language Model-Based Code Generating Tasks: Trends, Challenges, and Future Directions

Context. Large language models (LLMs) are increasingly applied to code-generating tasks (CGTs) in software engineering. While reported results are promising, the broader effects of such application and their integration into real-world development remain insufficiently understood with existing tertiary studies provide little in this area. Objective. This tertiary study consolidates secondary evidence on LLM-based CGTs, synthesizing the publication landscape, effects, scenarios, integration challenges, and future research directions. Method. Following systematic review guidelines, we searched in related digital libraries, complemented by backward-and-forward snowballing and screening step. Study quality was assessed and extraction reliability was audited with inter-rater agreement statistics. Evidence was synthesized using SWEBOK knowledge areas and the HELM framework. Results. We identify 30 secondary studies published between 2017-2025, with rapid growth since 2023. Accuracy seems strong on benchmarks but weakly supported for real-world generalization; robustness is fragile across tasks and configurations; efficiency constraints are pervasive; toxicity and bias are under-reported. Dominant challenges concern economic feasibility, evaluation validity, and socio-technical integration. Future directions suggest domain-aware model improvement and the need for holistic, standardized evaluation. Conclusion. LLM-based CGTs represent a fast-maturing yet unevenly evaluated research area, highlighting the need for domain-aware model improvements and holistic, standardized evaluation, addressing efficiency and associated costs.

Muslim Chochlov, Michael English, Jim Buckley

University of Limerick, Ireland

Code Generation Evaluation Language Model Robustness LLM Code Generation

May 24, 2026cs.SE

Specification-Based Code-Text-Code Reengineering for LLM-Mediated Software Evolution

Direct Code2Code transformation remains challenging to control because it can preserve surface-level syntax while introducing semantic drift, hidden behavioral changes, loss of traceability, non-idiomatic target implementations, or incomplete reconstruction of domain logic. This paper proposes a specification-based Code2Text2Code reengineering framework for LLM-mediated software evolution. The central idea is to transform source code into a neutral textual specification that captures program behavior, identifiers, computational flow, conditions, side effects, data dependencies, and domain-specific intent without directly transferring the source language syntax. The proposed framework combines factual context extraction, Code2Text generation, iterative verification between source code and text specification, Text2Code generation, target code verification, retrieval-augmented grounding, and semantic-aware chunking, and transformation loss estimation. The knowledge representation layer integrates metadata derived from AST, graph-based dependency structures, neutral natural language specifications, technical documentation, business documentation, and architecture-level representations. The conducted experiments include a Code2Text2Code dataset built from multiple programming languages and SQL dialects, comparison of intermediate representations, retrieval evaluation, documentation transformation evaluation, and prompt tuning using DSPy. A graph formalization using structural preservation, reverse compatibility, interface stability, and total graph similarity is implemented to estimate transformation losses. The results support the interpretation of the Code2Text2Code approach not as a simple code transformation, but as a controlled specification-based reengineering process for LLM-mediated software evolution.

Oleg Grynets, Vasyl Lyashkevych, Arsen Dolichnyi +3

EPAM Systems McLean, Virginia, USA · EPAM Systems Lviv, Ukraine · EPAM Systems Kyiv, Ukraine

Software Engineering Code Translation Program Synthesis LLM Code Generation

May 22, 2026cs.LG

CoSPlay: Cooperative Self-Play at Test-Time with Self-Generated Code and Unit Test

Recently, Reinforcement Learning with Verifiable Rewards (RLVR) and Test-Time Scaling (TTS) have advanced LLM code generation through executable verification. Yet Ground-Truth Unit Tests (GT UTs) remain a bottleneck: SOTA RLVR methods require them for costly training, while existing TTS methods lose competitiveness without them. This motivates GT-free TTS, where existing methods directly use self-generated UTs to refine and select code candidates. Yet such UTs are often noisy or spuriously coupled with wrong code, and UT quality in turn cannot be validated without reliable code. The key challenge is therefore to jointly improve both. To this end, we present CoSPlay, a GT-free, training-free framework that jointly improves codes and UTs through cooperative self-play. It first explores diverse solution ideas and identifies their potential failure modes to produce discriminative UT ideas. It then uses bidirectional pass-count signals from the Code-UT execution matrix to iteratively prune or fix weak codes and refresh or replace unreliable UTs, letting the two pools co-evolve. Finally, when multiple codes remain tied at the highest pass count, it picks the final code from the largest output-consensus cluster, since correct codes agree on the same inputs while wrong codes diverge. Experiments on four challenging benchmarks show that CoSPlay on Qwen2.5-7B-Instruct improves average BoN from 22.1% to 33.2% and UT accuracy from 14.6% to 78.3%, matching or surpassing the RLVR model CURE-7B. When applied to CURE-7B, it further improves BoN by 5.7%. CoSPlay also generalizes across diverse backbones and outperforms GT-free TTS baselines under comparable token budgets, with continued gains as the budget scales up. These results suggest a scalable inference strategy for competitive code generation without any GT data.

Zhangyi Hu, Chenhui Liu, Tian Huang +6

1The Hong Kong University of Science and Technology (Guangzhou) · Institute of Deep Perception Technology, JITRI, Wuxi, China

LLM Self-Refinement Execution-Guided Code Generation Code Generation Test-Time Scaling Automated Test Generation LLM Code Generation

May 21, 2026cs.SE

Security of LLM-generated Code: A Comparative Analysis

The majority of software developers use or are planning to use Artificial Intelligence (AI) tools in their development processes. Their top reasons include improving productivity and faster learning. In fact, Large Language Model (LLM)-generated code is currently in production, including in major tech companies. However, concerns were raised about the risks associated with the use of AI tools to generate code. In this paper, we focus our attention on the risks to software security. We empirically evaluate the security of code generated by seven popular LLMs. We build upon previous work to mimic the behaviours of developers when using LLMs to generate code. Our results show that all seven LLMs that we have evaluated generate code that contains vulnerabilities, the majority of which are of critical or high severity.

Srivathsan G Morkonda, Mahmoud Selim, Hala Assal

Carleton University, Ottawa, ON, Canada

Software Security LLM Security Code Generation Evaluation Secure Code Generation LLM Code Generation

May 21, 2026cs.LG

VeriScale: Adversarial Test-Suite Scaling for Verifiable Code Generation

As large language models (LLMs) are increasingly deployed for software engineering, constructing high-quality benchmarks is crucial for evaluating not just the functional correctness, but also the formal verifiability of generated code. However, existing benchmarks are limited by the quantity and quality of positive and negative test cases, leading to an overestimation of model capabilities in generating specifications and implementations. To address this, we propose VeriScale, a novel framework driven by the adversarial implementations. It consists of two stages: test-suite expansion to construct diverse and challenging test cases, and test-suite reduction to distill them into compact yet discriminative suites. While VeriScale is general, we instantiate it on Verina to construct VerinaPlus, which expands the original test suites by over 83

\times

, and VerinaLite, a lightweight 14

\times

variant. Our experiments across eight state-of-the-art LLMs demonstrate that VerinaPlus exposes substantial model weaknesses hidden by the original benchmark, evidenced by sharp score drops on both SpecGen and CodeGen tasks, whereas VerinaLite maintains this discriminative power at a fraction of the evaluation cost. The enhanced benchmarks and source code are publicly available at https://github.com/XiaoyangLiu-sjtu/VeriScale.

Yifan Bai, Xiaoyang Liu, Zihao Mou +7

School of Mathematical Sciences, Shanghai Jiao Tong University · School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen · School of Mathematics, Jilin University +5

Code Generation Synthetic Benchmark Generation Code Generation Benchmarks LLM Code Generation

May 20, 2026cs.SE

Stdlib or Third-Party? Empirical Performance and Correctness of LLM-Assisted Zero-Dependency Python Libraries

Third-party Python libraries introduce dependency management overhead, supply chain risk, and deployment friction in constrained environments. A natural question is how much of this ecosystem can be replicated using only Python's standard library -- and at what correctness and performance cost. We address this empirically through zerodep, a growing collection of single-file Python modules, each a stdlib-only reimplementation of a popular third-party library, developed with LLM assistance under strict constraints: no external imports, single file, drop-in API compatibility, and mandatory correctness validation against the reference library. Spanning over 40 modules across 12 categories -- including serialization, networking, cryptography, agent protocols, and text processing -- zerodep provides a controlled testbed for two interrelated questions: (1) Where does the stdlib suffice? and (2) Can LLMs effectively generate correct, performant code under tight symbolic constraints? Systematic benchmarking shows that stdlib-only implementations achieve performance parity (within 2x of the reference) in the majority of cases. The primary performance cliff is C-extension-backed computation (image processing, binary serialization, low-level crypto), not the inherent overhead of pure-Python third-party libraries. Conversely, many widely-used libraries carry architectural overhead that LLM-generated stdlib reimplementations avoid, yielding 5--115x speedups in several categories. We characterize the stdlib capability boundary across complexity tiers and library categories, discuss where LLM-assisted development succeeds and where it requires iterative human correction, and examine implications for dependency-free software engineering at scale. zerodep is open-source at https://github.com/Oaklight/zerodep.

Peng Ding, Rick Stevens

University of Chicago · Argonne National Laboratory

Code Generation LLM-Based Program Synthesis Code Generation Benchmarks LLM Code Generation

May 19, 2026cs.AI

What Really Improves Mathematical Reasoning: Structured Reasoning Signals Beyond Pure Code

Code has become a standard component of modern foundation language model (LM) training, yet its role beyond programming remains unclear. We revisit the claim that code improves reasoning through controlled pretraining experiments on a 10T-token corpus with fine-grained domain separation. Our findings are threefold. First, when code is restricted to standalone executable programs and Code-NL data are controlled for, code substantially improves programming ability but does not act as a general reasoning enhancer; instead, it competes with knowledge-intensive tasks, especially complex mathematical reasoning. Second, the reasoning gains often attributed to code are better explained by cross-domain structured reasoning traces, such as code-text and math-text mixtures, rather than by executable code alone. Third, increasing the density of structured math-domain samples within a fixed math budget yields substantial gains on difficult mathematical reasoning while largely preserving programming performance, suggesting that cognitive scaffolds offer a targeted way to mitigate cross-domain trade-offs. Finally, routing analyses show that data-composition effects are reflected in expert-activation patterns, providing mechanism-level evidence for competitive and synergistic interactions across domains. Our results clarify which data characteristics transfer across capability dimensions and point to more precise data-centric optimization strategies.

Yuze Zhao, Junpeng Fang, Lu Yu +6

State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China, Hefei, China · Individual Researcher · Institute of Artificial Intelligence, Hefei Comprehensive National Science Center +1

Structured Reasoning LLM Code Generation LLM Mathematical Reasoning