Code Generation

Follow this topic Ask about this topic

Code generation asks how models can turn requests, examples, images, or formal specifications into programs that work in real settings, from short functions to whole repositories and domain-specific software. Common approaches include prompting and fine-tuning, retrieval of relevant code or documentation, constrained decoding, and agents that iteratively run, test, and repair their outputs. Multimodal systems also use rendered interfaces, charts, and diagrams as input or feedback, while reinforcement learning can use execution tests, compilers, or formal verifiers as training signals. Benchmarks such as HumanEval, MBPP, LiveCodeBench, and repository-level tasks show progress, but passing tests or compiling does not guarantee that code meets its intended behavior, visual requirements, security needs, or deployment constraints.

Latest papers

313 papers42 papers in the last four weeks, up 68% on the four weeks before. 0.2% of all new papers.

Mar 16, 2026

SAGE: Multi-Agent Self-Evolution for LLM Reasoning

Reinforcement learning with verifiable rewards improves reasoning in large language models (LLMs), but many methods still rely on large human-labeled datasets. While self-play reduces this dependency, it often lacks explicit planning and strong quality control, limiting stability in long-horizon multi-step reasoning. We present SAGE (Self-evolving Agents for Generalized reasoning Evolution), a closed-loop framework where four agents: Challenger, Planner, Solver, and Critic, co-evolve from a shared LLM backbone using only a small seed set. The Challenger continuously generates increasingly difficult tasks; the Planner converts each task into a structured multi-step plan; and the Solver follows the plan to produce an answer, whose correctness is determined by external verifiers. The Critic scores and filters both generated questions and plans to prevent curriculum drift and maintain training signal quality, enabling stable self-training. Across mathematics and code-generation benchmarks, SAGE delivers consistent gains across model scales, improving the Qwen-2.5-7B model by 8.9% on LiveCodeBench and 10.7% on OlympiadBench.

Yulin Peng, Xinxin Zhu, Chenxing Wei +4

College of Computer Science and Software Engineering, Shenzhen University, China · Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), China · School of Information Technology, Carleton University, Canada

LLM Reasoning Self-Training for Language Models RL for Language Model Reasoning Multi-Agent LLMs Code Generation

Mar 15, 2026

CangjieBench: Benchmarking LLMs on a Low-Resource General-Purpose Programming Language

Large Language Models excel in high-resource programming languages but struggle with low-resource ones. Existing research related to low-resource programming languages primarily focuses on Domain-Specific Languages (DSLs), leaving general-purpose languages that suffer from data scarcity underexplored. To address this gap, we introduce CangjieBench, a contamination-free benchmark for Cangjie, a representative low-resource general-purpose language. The benchmark comprises 248 high-quality samples manually translated from HumanEval and ClassEval, covering both Text-to-Code and Code-to-Code tasks. We conduct a systematic evaluation of diverse LLMs under four settings: Direct Generation, Syntax-Constrained Generation, Retrieval-Augmented Generation (RAG), and Agent. Experiments reveal that Direct Generation performs poorly, whereas Syntax-Constrained Generation offers the best trade-off between accuracy and computational cost. Agent achieve state-of-the-art accuracy but incur high token consumption. Furthermore, we observe that Code-to-Code translation often underperforms Text-to-Code generation, suggesting a negative transfer phenomenon where models overfit to the source language patterns. We hope that our work will offer valuable insights into LLM generalization to unseen and low-resource programming languages. Our code and data are available at https://github.com/cjhCoder7/CangjieBench.

Junhang Cheng, Fang Liu, Jia Li +3

Beihang University, Beijing, China · Wuhan University, Wuhan, China

Code Generation LLM Code Generation Low-Resource Language Processing LLM Evaluation Code Translation

Mar 14, 2026

Coding with Eyes: Visual Feedback Unlocks Reliable GUI Code Generating and Debugging

Recent advances in Large Language Model (LLM)-based agents have shown remarkable progress in code generation. However, current agent methods mainly rely on text-output-based feedback (e.g. command-line outputs) for multi-round debugging and struggle in graphical user interface (GUI) that involve visual information. This is mainly due to two limitations: 1) GUI programs are event-driven, yet existing methods cannot simulate user interactions to trigger GUI element logic 2) GUI programs possess visual attributes, making it difficult for text-based approaches to assess whether the rendered interface meets user needs. To systematically address these challenges, we first introduce InteractGUI Bench, a novel benchmark comprising 984 commonly used real-world desktop GUI application tasks designed for fine-grained evaluation of both interaction logic and visual structure. Furthermore, we propose VF-Coder, a vision-feedback-based multi-agent system for debugging GUI code. By perceiving visual information and directly interacting with program interfaces, VF-Coder can identify potential logic and layout issues in a human-like manner. On InteractGUI Bench, our VF-Coder approach increases the success rate of Gemini-3-Flash from 21.68% to 28.29% and raises the visual score from 0.4284 to 0.5584, indicating the effectiveness of visual feedback in GUI debugging.

Zhilin Liu, Ye Huang, Ting Xie +3

Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China

Code Generation Code Generation Benchmarks Multi-Agent Coding

Mar 13, 2026

Visual-ERM: Reward Modeling for Visual Equivalence

Vision-to-code tasks require models to reconstruct structured visual inputs, such as charts, tables, and SVGs, into executable or structured representations with high visual fidelity. While recent Large Vision Language Models (LVLMs) achieve strong results via supervised fine-tuning, reinforcement learning remains challenging due to misaligned reward signals. Existing rewards either rely on textual rules or coarse visual embedding similarity, both of which fail to capture fine-grained visual discrepancies and are vulnerable to reward hacking. We propose Visual Equivalence Reward Model (Visual-ERM), a multimodal generative reward model that provides fine-grained, interpretable, and task-agnostic feedback to evaluate vision-to-code quality directly in the rendered visual space. Integrated into RL, Visual-ERM improves Qwen3-VL-8B-Instruct by +8.4 on chart-to-code and yields consistent gains on table and SVG parsing (+2.7, +4.1 on average), and further strengthens test-time scaling via reflection and revision. We also introduce VisualCritic-RewardBench (VC-RewardBench), a benchmark for judging fine-grained image-to-image discrepancies on structured visual data, where Visual-ERM at 8B decisively outperforms Qwen3-VL-235B-Instruct and approaches leading closed-source models. Our results suggest that fine-grained visual reward supervision is both necessary and sufficient for vision-to-code RL, regardless of task specificity.

Ziyu Liu, Shengyuan Ding, Xinyu Fang +7

Shanghai Jiao Tong University · Shanghai AI Laboratory · Fudan University +1

Reward Modeling RL for VLMs VLM Evaluation Large Vision-Language Models Code Generation

Mar 12, 2026

QAQ: Bidirectional Semantic Coherence for Selecting High-Quality Synthetic Code Instructions

Synthetic data has become essential for training code generation models, yet it introduces significant noise and hallucinations that are difficult to detect with current metrics. Existing data selection methods like Instruction-Following Difficulty (IFD) typically assess how hard a model generates an answer given a query (

A|Q

). However, this metric is ambiguous on noisy synthetic data, where low probability can distinguish between intrinsic task complexity and model-generated hallucinations. Here, we propose QAQ, a novel data selection framework that evaluates data quality from the reverse direction: how well can the answer predict the query (

Q|A

)? We define Reverse Mutual Information (RMI) to quantify the information gain about the query conditioned on the answer. Our analyses reveal that both extremes of RMI signal quality issues: low RMI indicates semantic misalignment, while excessively high RMI may contain defect patterns that LLMs easily recognize. Furthermore, we introduce a selection strategy based on the disagreement between strong and weak models to identify samples that are valid yet challenging. Experiments across three datasets spanning code generation (WarriorCoder, Magpie-Qwen2.5-Coder-Pro-300K) and math reasoning (OpenR1-Math-220k) demonstrate that selecting just 25% of data using stratified RMI matches full-data performance while being consistently competitive with or better than existing data selection methods. Our approach highlights the importance of bidirectional semantic coherence in synthetic data curation, offering a scalable pathway to reduce computational costs without sacrificing model capability. Code is available at https://github.com/XXSg559/QAQ.

Jiayin Lei, Ming Ma, Yunxi Duan +2

Beijing University of Technology, Beijing, 100124, China · Institute of Neuroscience, State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology, Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai, 200031, China · University of Chinese Academy of Sciences, Beijing, 100049, China +1

Instruction-Tuning Data Selection Code Generation Data Selection Training Data Selection Synthetic Data Generation for Language Models Synthetic Data Evaluation+1

Mar 12, 2026

CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges

The saturation of high-quality pre-training data has shifted research focus toward evolutionary systems capable of continuously generating novel artifacts, leading to the success of AlphaEvolve. However, the progress of such systems is hindered by the lack of rigorous, quantitative evaluation. To tackle this challenge, we introduce CreativeBench, a benchmark for evaluating machine creativity in code generation, grounded in a classical cognitive framework. Comprising two subsets -- CreativeBench-Combo and CreativeBench-Explore -- the benchmark targets combinatorial and exploratory creativity through an automated pipeline utilizing reverse engineering and self-play. By leveraging executable code, CreativeBench objectively distinguishes creativity from hallucination via a unified metric defined as the product of quality and novelty. Our analysis of state-of-the-art models reveals distinct behaviors: (1) scaling significantly improves combinatorial creativity but yields diminishing returns for exploration; (2) larger models exhibit ``convergence-by-scaling,'' becoming more correct but less divergent; and (3) reasoning capabilities primarily benefit constrained exploration rather than combination. Finally, we propose EvoRePE, a plug-and-play inference-time steering strategy that internalizes evolutionary search patterns to consistently enhance machine creativity.

Zi-Han Wang, Lam Nguyen, Zhengyang Zhao +4

Southern University of Science and Technology · Tsinghua University · Xi’an Jiaotong University +3

Computational Creativity Creativity Assessment Code Generation Benchmarks Code Generation Synthetic Benchmark Generation Inference-Time Search

Mar 12, 2026

DOne: Decoupling Structure and Rendering for High-Fidelity Design-to-Code Generation

While Vision Language Models (VLMs) have shown promise in Design-to-Code generation, they suffer from a "holistic bottleneck-failing to reconcile high-level structural hierarchy with fine-grained visual details, often resulting in layout distortions or generic placeholders. To bridge this gap, we propose DOne, an end-to-end framework that decouples structure understanding from element rendering. DOne introduces (1) a learned layout segmentation module to decompose complex designs, avoiding the limitations of heuristic cropping; (2) a specialized hybrid element retriever to handle the extreme aspect ratios and densities of UI components; and (3) a schema-guided generation paradigm that bridges layout and code. To rigorously assess performance, we introduce HiFi2Code, a benchmark featuring significantly higher layout complexity than existing datasets. Extensive evaluations on the HiFi2Code demonstrate that DOne outperforms exiting methods in both high-level visual similarity (e.g., over 10% in GPT Score) and fine-grained element alignment. Human evaluations confirm a 3 times productivity gain with higher visual fidelity.

Xinhao Huang, Jinke Yu, Wenhao Xu +5

HKUST (Guangzhou), Guangzhou, China · Alibaba Group, Hangzhou, China · HKUST, Hong Kong, China +2

Code Generation Vision-Language Models

Mar 11, 2026

CodePercept: Code-Grounded Visual STEM Perception for MLLMs

When MLLMs fail at Science, Technology, Engineering, and Mathematics (STEM) visual reasoning, a fundamental question arises: is it due to perceptual deficiencies or reasoning limitations? Through systematic scaling analysis that independently scales perception and reasoning components, we uncover a critical insight: scaling perception consistently outperforms scaling reasoning. This reveals perception as the true lever limiting current STEM visual reasoning. Motivated by this insight, our work focuses on systematically enhancing the perception capabilities of MLLMs by establishing code as a powerful perceptual medium--executable code provides precise semantics that naturally align with the structured nature of STEM visuals. Specifically, we construct ICC-1M, a large-scale dataset comprising 1M Image-Caption-Code triplets that materializes this code-as-perception paradigm through two complementary approaches: (1) Code-Grounded Caption Generation treats executable code as ground truth for image captions, eliminating the hallucinations inherent in existing knowledge distillation methods; (2) STEM Image-to-Code Translation prompts models to generate reconstruction code, mitigating the ambiguity of natural language for perception enhancement. To validate this paradigm, we further introduce STEM2Code-Eval, a novel benchmark that directly evaluates visual perception in STEM domains. Unlike existing work relying on problem-solving accuracy as a proxy that only measures problem-relevant understanding, our benchmark requires comprehensive visual comprehension through executable code generation for image reconstruction, providing deterministic and verifiable assessment. Code is available at https://github.com/TongkunGuan/Qwen-CodePercept.

Tongkun Guan, Zhibo Yang, Jianqiang Wan +10

MoE Key Lab of Artificial Intelligence, AI Institute, School of Computer Science, Shanghai Jiao Tong University · Qwen Team · Beijing Institute of Technology +2

Image-to-Code Generation Visually Grounded Reasoning Fine-Grained Visual Perception VLM Evaluation Code Generation

Mar 10, 2026

EsoLang-Bench: Evaluating Genuine Reasoning in Large Language Models via Esoteric Programming Languages

Large language models achieve near-ceiling performance on code generation benchmarks, yet most of the programming languages used by popular benchmarks such as SWE-bench and HumanEval (e.g. Python, JavaScript) are squarely in-distribution. They appear at scale in pre-training corpora and are heavily reinforced during post-training. To study LLM performance on unfamiliar programming languages, we introduce EsoLang-Bench, a benchmark using five esoteric programming languages (Brainfuck, Befunge-98, Whitespace, Unlambda, and Shakespeare). All five of our chosen esoteric languages are Turing-complete, so the same algorithmic problems that are solvable in Python or JavaScript are in principle solvable in each of them. Yet, they are unfamiliar to LLMs which makes them a good proxy for evaluating out-of-distribution performance. The unfamiliarity of esoteric languages comprises of: (i) the hard-by-design primitives comprising the language; (ii) substantially less representation in pre-training corpora (340x to over 60,000x fewer public GitHub repositories than Python); (iii) negligible deployment value, which makes targeted inclusion in post-training data economically irrational. We evaluate five frontier models across five prompting strategies and find a dramatic capability gap. The same 80 problems expressed in Python or JavaScript reach 100% accuracy on top frontier models, while the equivalent esoteric versions score only 0-11%. Few-shot learning and self-reflection also fail to close this gap. EsoLang-Bench therefore provides a contamination-resistant testbed for measuring how well frontier models generalise algorithmic problem-solving to programming languages outside their training distribution.

Aman Sharma, Paras Chopra

Lossfunk

LLM Evaluation LLM Code Generation OOD Generalization Code Generation

Mar 9, 2026

Text to Automata Diagrams: Comparing TikZ Code Generation with Direct Image Synthesis

Diagrams are widely used in teaching computer science courses. They are useful in subjects such as automata and formal languages, data structures, etc. These diagrams, often drawn by students during exams or assignments, vary in structure, layout, and correctness. This study examines whether current vision-language and large language models can process such diagrams and produce accurate textual and digital representations. In this study, scanned student-drawn diagrams are used as input. Then, textual descriptions are generated from these images using a vision-language model. The descriptions are checked and revised by human reviewers to make them accurate. Both the generated and the revised descriptions are then fed to a large language model to generate TikZ code. The resulting diagrams are compiled and then evaluated against the original scanned diagrams. We found descriptions generated directly from images using vision-language models are often incorrect and human correction can substantially improve the quality of vision language model generated descriptions. This research can help computer science education by paving the way for automated grading and feedback and creating more accessible instructional materials.

Ethan Young, Zichun Wang, Aiden Taylor +6

Marshall University · West Virginia State University

Code Generation VLM Evaluation

Mar 8, 2026

A Novel Multi-Agent Architecture to Reduce Hallucinations of Large Language Models in Multi-Step Structural Modeling

Large language models (LLMs) such as GPT and Gemini have demonstrated remarkable capabilities in contextual understanding and reasoning. The strong performance of LLMs has sparked growing interest in leveraging them to automate tasks traditionally dependent on human expertise. Recently, LLMs have been integrated into intelligent agents capable of operating structural analysis software (e.g., OpenSees) to construct structural models and perform analyses. However, existing LLMs are limited in handling multi-step structural modeling due to frequent hallucinations and error accumulation during long-sequence operations. To this end, this study presents a novel multi-agent architecture to automate the structural modeling and analysis using OpenSeesPy. First, problem analysis and construction planning agents extract key parameters from user descriptions and formulate a stepwise modeling plan. Node and element agents then operate in parallel to assemble the frame geometry, followed by a load assignment agent. The resulting geometric and load information is translated into executable OpenSeesPy scripts by code translation agents. The proposed architecture is evaluated on a benchmark of 20 frame problems over ten repeated trials, achieving 100% accuracy in 18 cases and 90% in the remaining two. The architecture also significantly improves computational efficiency and demonstrates scalability to larger structural systems.

Ziheng Geng, Jiachen Liu, Ran Cao +3

Department of Civil and Architectural Engineering, University of Miami, Coral Gables, FL 33146, USA · HBC Engineering Company, Miami, FL 33178, USA · College of Civil Engineering, Hunan University, Changsha, 410082, China +3

Structural Engineering Multi-Agent LLM Systems LLM Hallucination Mitigation Code Generation

Mar 8, 2026

KCoEvo: A Knowledge Graph Augmented Framework for Evolutionary Code Generation

Code evolution is inevitable in modern software development. Changes to third-party APIs frequently break existing code and complicate maintenance, posing practical challenges for developers. While large language models (LLMs) have shown promise in code generation, they struggle to reason without a structured representation of these evolving relationships, often leading them to produce outdated APIs or invalid outputs. In this work, we propose a knowledge graph-augmented framework that decomposes the migration task into two synergistic stages: evolution path retrieval and path-informed code generation. Our approach constructs static and dynamic API graphs to model intra-version structures and cross-version transitions, enabling structured reasoning over API evolution. Both modules are trained with synthetic supervision automatically derived from real-world API diffs, ensuring scalability and minimal human effort. Extensive experiments across single-package and multi-package benchmarks demonstrate that our framework significantly improves migration accuracy, controllability, and execution success over standard LLM baselines. The source code and datasets are available at: https://github.com/kangjz1203/KCoEvo.

Jiazhen Kang, Yuchen Lu, Chen Jiang +6

Southeast University, Nanjing, China · ByteDance Ltd., China · Monash University, Melbourne, Australia

Code Generation Graph Retrieval-Augmented Generation

Mar 5, 2026

SEA-TS: Self-Evolving Agent for Autonomous Code Generation of Time Series Forecasting Algorithms

Accurate time series forecasting underpins decision-making in many domains, yetconventional ML development often faces data scarcity, distribution shift, anddiminishing returns from manual iteration. We propose Self-Evolving Agent forTime Series Algorithms (SEATS), a framework that autonomously generates, val-idates, and optimizes forecasting algorithm code through an iterative self-evolutionloop. Our design combines three mechanisms: (1) Metric-Advantage MCTS(MA-MCTS), which replaces fixed rewards with a statistically normalized advan-tage score for search guidance, (2) code review with running prompt refinement,so every successfully executed solution is reviewed and the running prompt encodescorrective patterns for later iterations, and (3) global steerable reasoning, whichcompares each evaluated node to global best- and worst-performing solutions forcross-trajectory transfer. A MAP-Elites archive maintains architectural diversity.Across four datasets and two metrics, SEATS wins seven of eight comparisonsagainst strong baselines TimeMixer, Timer, and SEMixer

Longkun Xu, Xiaochun Zhang, Qiantu Tuo +1

Ecoflow Inc.

Time Series Forecasting Code Generation Monte Carlo Tree Search Automated Machine Learning Self-Evolving Agents

Mar 4, 2026

Python Bindings for a Large C++ Robotics Library: The Case of OMPL

Python bindings are a critical bridge between high-performance C++ libraries and the flexibility of Python, enabling rapid prototyping, reproducible experiments, and integration with simulation and learning frameworks in robotics research. Yet, generating bindings for large codebases is a tedious process that creates a heavy burden for a small group of maintainers. In this work, we investigate the use of Large Language Models (LLMs) to assist in generating nanobind wrappers, with human experts kept in the loop. Our workflow mirrors the structure of the C++ codebase, scaffolds empty wrapper files, and employs LLMs to fill in binding definitions. Experts then review and refine the generated code to ensure correctness, compatibility, and performance. Through a case study on a large C++ motion planning library, we document common failure modes, including mismanaging shared pointers, overloads, and trampolines, and show how in-context examples and careful prompt design improve reliability. Experiments demonstrate that the resulting bindings achieve runtime performance comparable to legacy solutions. Beyond this case study, our results provide general lessons for applying LLMs to binding generation in large-scale C++ projects.

Weihang Guo, Theodoros Tyrovouzis, Lydia E. Kavraki

Department of Computer Science, Rice University, Houston TX, USA · Ken Kennedy Institute at Rice University

Code Generation LLM Code Generation

Mar 4, 2026

CONCUR: Benchmarking LLMs for Concurrent Code Generation

Leveraging Large Language Models (LLMs) for code generation has increasingly emerged as a common practice in the domain of software engineering. Relevant benchmarks have been established to evaluate the code generation capabilities of LLMs. However, existing benchmarks focus primarily on sequential code, lacking the ability to effectively evaluate LLMs on concurrent code generation. Compared to sequential code, concurrent code exhibits greater complexity and possesses unique types of bugs, such as deadlocks and race conditions, that do not occur in sequential code. Therefore, a benchmark for evaluating sequential code generation cannot be useful for evaluating concurrent code generation with LLMs. To address this gap, we designed a benchmark CONCUR specifically aimed at evaluating the capability of LLMs to generate concurrent code. CONCUR consists of a base set of 43 concurrency problems derived from a standard concurrency textbook, together with 72 validated mutant variants, resulting in 115 total problems. The base problems serve as the semantic core of the benchmark, while the mutants expand linguistic and structural diversity. We conducted an evaluation of a range of LLMs on CONCUR, highlighting limitations of current models. Overall, our work provides a novel direction for evaluating the capability of LLMs to generate code with focus on concurrency.

Jue Huang, Tarek Mahmud, Corina Pasareanu +1

The University of Queensland · Texas A&M University - Kingsville · Carnegie Mellon University

Code Generation Evaluation Code Generation Benchmarks LLM Code Generation Code Generation

Mar 3, 2026

Act-Observe-Rewrite: Multimodal Coding Agents as In-Context Policy Learners for Robot Manipulation

Can a multimodal language model learn to manipulate physical objects by reasoning about its own failures-without gradient updates, demonstrations, or reward engineering? We argue the answer is yes, under conditions we characterise precisely. We present Act-Observe-Rewrite (AOR), a framework in which an LLM agent improves a robot manipulation policy by synthesising entirely new executable Python controller code between trials, guided by visual observations and structured episode outcomes. Unlike prior work that grounds LLMs in pre-defined skill libraries or uses code generation for one-shot plan synthesis, AOR makes the full low-level motor control implementation the unit of LLM reasoning, enabling the agent to change not just what the robot does, but how it does it. The central claim is that interpretable code as the policy representation creates a qualitatively different kind of in-context learning from opaque neural policies: the agent can diagnose systematic failures and rewrite their causes. We validate this across three robosuite manipulation tasks and report promising results, with the agent achieving high success rates without demonstrations, reward engineering, or gradient updates.

Vaishak Kumar

General Bionix, Inc.

Code Generation for Robotics Robot Policy Learning ICL for Robotics Robotic Manipulation VLMs for Robotics Code Generation

Mar 3, 2026

BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?

Current code-agent benchmarks primarily evaluate localized issue resolution within a single target repository, leaving under-tested many software engineering tasks that require external knowledge or broader repository-level changes. We introduce BeyondSWE, a 500-instance benchmark drawn from 246 real-world GitHub repositories to evaluate code agents beyond single-repository bug fixing. BeyondSWE covers four representative settings: cross-repository issue resolution, domain-specific issue resolution, dependency-driven migration, and document-to-repository generation, spanning both broader knowledge scope and broader resolution scope. Our evaluation shows that BeyondSWE remains far from saturated: the best OpenHands-based agent reaches 46.12 average score, while the strongest Codex harness with GPT-5.4 (xhigh) reaches 56.65 under a search-aware prompt. To study whether external information access closes this gap, we use SearchSWE as a controlled diagnostic baseline for search-augmented coding. Search access improves most models and substantially helps some tasks, but the gains remain limited and uneven, showing that current agents still struggle to convert retrieved information into precise, version-compatible, and locally actionable code changes. These results suggest that deep search for coding remains an open problem: progress requires agents that can reliably combine external evidence with repository-local reasoning and execution-based verification.

Guoxin Chen, Fanzhe Meng, Jiale Zhao +12

Retrieval-Augmented Code Generation Software Engineering Benchmarks LLM Agent Evaluation Code Generation Benchmarks Code Generation

Mar 3, 2026

An Initial Exploration of Contrastive Prompt Tuning to Generate Energy-Efficient Code

Although LLMs are capable of generating functionally correct code, they also tend to produce less energy-efficient code in comparison to human-written solutions. As these inefficiencies lead to higher computational overhead, they are in direct conflict with Green Software Development (GSD) efforts, which aim to reduce the energy consumption of code. To support these efforts, this study aims to investigate whether and how LLMs can be optimized to promote the generation of energy-efficient code. To this end, we employ Contrastive Prompt Tuning (CPT). CPT combines Contrastive Learning techniques, which help the model to distinguish between efficient and inefficient code, and Prompt Tuning, a Parameter-Efficient Fine Tuning (PEFT) approach that requires only a fraction of the cost of traditional fine tuning. This study evaluates CPT on Python, Java and C++ coding problems across three different models to provide a comprehensive evaluation. The method achieves consistent improvements in code accuracy for two models but efficiency gains vary by model, language and task complexity, indicating that improvements are not uniformly reliable.

Sophie Weidmann, Fernando Castor

University of Twente, Enschede, The Netherlands

Code Generation LLM Code Generation Prompt Tuning

Mar 3, 2026

ParEVO: Synthesizing Code for Irregular Data: High-Performance Parallelism through Agentic Evolution

The transition from sequential to parallel computing is essential for modern high-performance applications but is hindered by the steep learning curve of concurrent programming. This challenge is magnified for irregular data structures (such as sparse graphs, unbalanced trees, and non-uniform meshes) where static scheduling fails and data dependencies are unpredictable. Current Large Language Models (LLMs) often fail catastrophically on these tasks, generating code plagued by subtle race conditions, deadlocks, and sub-optimal scaling. We bridge this gap with ParEVO, a framework designed to synthesize high-performance parallel algorithms for irregular data. Our contributions include: (1) The Parlay-Instruct Corpus, a curated dataset of 13,820 tasks synthesized via a "Critic-Refine" pipeline that explicitly filters for empirically performant algorithms that effectively utilize Work-Span parallel primitives; (2) specialized DeepSeek, Qwen, and Gemini models fine-tuned to align probabilistic generation with the rigorous semantics of the ParlayLib library; and (3) an Evolutionary Coding Agent (ECA) that improves the "last mile" of correctness by iteratively repairing code using feedback from compilers, dynamic race detectors, and performance profilers. On the ParEval benchmark, ParEVO achieves an average 106x speedup (with a maximum of 1103x) across the suite, and a robust 13.6x speedup specifically on complex irregular graph problems, outperforming state-of-the-art commercial models. Furthermore, our evolutionary approach matches state-of-the-art expert human baselines, achieving up to a 4.1x speedup on specific highly-irregular kernels. Source code and datasets are available at https://github.com/WildAlg/ParEVO.

Liu Yang, Zeyu Nie, Andrew Liu +4

Department of Computer Science, Yale University, New Haven, CT, USA · Google DeepMind, Mountain View, CA, USA

High-Performance Computing Code Generation LLM-Based Program Synthesis Program Synthesis

Feb 28, 2026

Test-Driven Agentic Framework for Reliable Robot Controller

In this work, we present a test-driven, agentic framework for synthesizing a deployable low-level robot controller for navigation tasks. Given a 2D map with an image of an ultrasonic sensor-based robot, or a 3D robotic simulation environment, our framework iteratively refines the generated controller code using diagnostic feedback from structured test suites to achieve task success. We propose a dual-tier repair strategy to refine the generated code that alternates between prompt-level refinement and direct code editing. We evaluate the approach across 2D navigation tasks and 3D navigation in the Webots simulator. Experimental results show that test-driven synthesis substantially improves controller reliability and robustness over one-shot controller generation, especially when the initial prompt is underspecified. The source code and demonstration videos are available at: https://shivanshutripath.github.io/robotic_controller.github.io.

Shivanshu Tripathi, Reza Akbarian Bafghi, Maziar Raissi

Department of Electrical and Computer Engineering, University of California, Riverside · Department of Computer Science, University of Colorado, Boulder · Department of Mathematics, University of California, Riverside

Robotic Control Code Generation Robot Navigation

Feb 27, 2026

Steerable Instruction Following Coding Data Synthesis with Actor-Parametric Schema Co-Evolution

Interpreting and following human instructions is a critical capability of large language models (LLMs) in automatic programming. However, synthesizing large-scale instruction-paired coding data remains largely unexplored and is particularly challenging when ensuring logical compatibility among multiple constraints. In this study, we propose IFCodeEvolve, an actor-schema co-evolution framework for instruction following coding data generation. By representing instructions as parametric function schema, we construct a library that covers the vast instruction space via dynamic constraint instantiation. Building upon this, Monte Carlo Tree Search (MCTS) sampler is applied to efficiently navigate this space, utilizing actor model feedback as a dynamic termination signal. Furthermore, to progressively explore challenging problems, we introduce a co-evolving paradigm that iteratively advances both the actor model and the schema library, via schema composition and mutation, based on sampler statistics. Empirical results demonstrate that IFCodeEvolve significantly boosts base model performance, with our 32B model achieving parity with proprietary SOTA models. Additionally, we contribute IFCodeBench, a comprehensive human-verified benchmark equipped with solutions and robust AST-based verification.

Tinglin Huang, Bo Chen, Xiao Zhang +2

Yale University · ByteDance Seed

Synthetic Data Generation for Language Models Code Generation LLM Code Generation Code Generation Benchmarks

Feb 24, 2026

ManiBench: A Benchmark for Testing Visual-Logic Drift and Syntactic Hallucinations in Manim Code Generation

Traditional benchmarks like HumanEval and MBPP test logic and syntax effectively, but fail when code must produce dynamic, pedagogical visuals. We introduce ManiBench, a specialized benchmark evaluating LLM performance in generating Manim CE code, where temporal fidelity and version-aware API correctness are critical. ManiBench targets two key failure modes: Syntactic Hallucinations (valid Python referencing non-existent or deprecated Manim APIs) and Visual-Logic Drift (generated visuals diverging from intended mathematical logic through timing errors or missing causal relationships). The benchmark comprises 150-200 problems across five difficulty levels spanning calculus, linear algebra, probability, topology, and AI, grounded in analysis of 3Blue1Brown's ManimGL source (53,000 lines, 143 scene classes). Evaluation uses a four-tier framework measuring Executability, Version-Conflict Error Rate, Alignment Score, and Coverage Score. An open-source framework automates evaluation across multiple models and prompting strategies. Code, data and benchmark suite are available at https://github.com/nabin2004/ManiBench. and the dataset is hosted on https://huggingface.co/datasets/nabin2004/ManiBench.

Nabin Oli

Sunway College Kathmandu, Birmingham City University

Citation Hallucination Code Generation Code Generation Benchmarks Code Generation Evaluation Hallucination in Language Models

Feb 24, 2026

From Prompts to Performance: Evaluating LLMs for Task-based Parallel Code Generation

Large Language Models (LLM) show strong abilities in code generation, but their skill in creating efficient parallel programs is less studied. This paper explores how LLMs generate task-based parallel code from three kinds of input prompts: natural language problem descriptions, sequential reference implementations, and parallel pseudo code. We focus on three programming frameworks: OpenMP Tasking, C++ standard parallelism, and the asynchronous many-task runtime HPX. Each framework offers different levels of abstraction and control for task execution. We evaluate LLM-generated solutions for correctness and scalability. Our results reveal both strengths and weaknesses of LLMs with regard to problem complexity and framework. Finally, we discuss what these findings mean for future LLM-assisted development in high-performance and scientific computing.

Linus Bantel, Moritz Strack, Alexander Strack +1

Institute for Parallel and Distributed Systems, University of Stuttgart, Stuttgart, Germany

Code Generation LLM Code Generation Code Generation Evaluation High-Performance Computing

Feb 23, 2026

CodeGENCAT: Generative Computerized Adaptive Testing for Open-ended Coding Problems

Existing Computerized Adaptive Testing (CAT) frameworks typically select questions based on the predicted likelihood that the student will answer correctly. This design ignores information contained in students' open-ended responses, especially in domains such as programming education, where code structures and bugs contain rich information on student knowledge. In this work, we propose Code GENerative CAT (CodeGENCAT), a generative CAT framework that selects questions using predicted student code responses. First, we develop a Generative Item Response Theory (GIRT) model that generates code responses conditioned on estimated student knowledge, trained with supervised fine-tuning followed by direct preference optimization for knowledge-response alignment. Second, we introduce three question-selection algorithms that measure uncertainty, coding style diversity, and information from predicted student code responses. Experiments on two real-world programming education datasets show that CodeGENCAT outperforms all CAT baselines, achieving an AUC improvement of up to 4.32% over the strongest baseline in the early stages of adaptive testing.

Wanyong Feng, Alexander Scarlatos, Ruochen Sun +1

University of Massachusetts Amherst · Independent Researcher

Computerized Adaptive Testing Educational Assessment Item Response Theory Computer Science Education Code Generation

Feb 22, 2026

VectorGym: A Multi-Task Benchmark for SVG Code Generation, Sketching and Editing

We introduce VectorGym, a comprehensive benchmark suite for Scalable Vector Graphics (SVG) that spans generation from text and sketches, complex editing, and visual understanding. VectorGym addresses the lack of realistic, challenging benchmarks aligned with professional design workflows. Our benchmark comprises four tasks with expert human-authored annotations: the novel Sketch2SVG task (VG-Sketch); a new SVG editing dataset (VG-Edit) featuring complex, multi-step edits with higher-order primitives; Text2SVG generation (VG-Text); and SVG captioning (VG-Cap). Unlike prior benchmarks that rely on synthetic edits, VectorGym provides gold-standard human annotations that require semantic understanding and design intent. We also provide a multi-task reinforcement learning baseline that jointly optimizes across all four tasks using rendering-based rewards. This baseline, built on GRPO with curriculum learning, trains a Qwen3-VL 8B model that achieves state-of-the-art performance among open-source models, surpassing much larger models including Qwen3-VL 235B and matching GPT-4o. We also introduce a VLM-as-a-Judge metric for SVG generation, validated through human correlation studies. Our evaluation of frontier VLMs reveals significant performance gaps, positioning VectorGym as a rigorous framework for advancing visual code generation.

Joan Rodriguez, Haotian Zhang, Abhay Puri +14

Mila, Quebec AI Institute · ÉTS Montréal · QuiverAI +11

VLM Evaluation Code Generation Image Editing Code Generation Benchmarks Vector Graphics Generation Text-to-SVG Generation

Feb 20, 2026

GraphSkill: Documentation-Guided Hierarchical Retrieval-Augmented Coding for Complex Graph Reasoning

The growing demand for automated graph algorithm reasoning has attracted increasing attention in the large language model (LLM) community. Recent LLM-based graph reasoning methods typically decouple task descriptions from graph data, generate executable code augmented by retrieval from technical documentation, and refine the code through debugging. However, we identify two key limitations in existing approaches: (i) they treat technical documentation as flat text collections and ignore its hierarchical structure, leading to noisy retrieval that degrades code generation quality; and (ii) their debugging mechanisms focus primarily on runtime errors, yet ignore more critical logical errors. To address them, we propose {\method}, an agentic hierarchical retrieval-augmented coding framework that exploits the document hierarchy through top-down traversal and early pruning, together with a self-debugging coding agent that iteratively refines code using automatically generated small-scale test cases. To enable comprehensive evaluation of complex graph reasoning, we introduce a new dataset, {\dataset}, covering small-scale, large-scale, and composite graph reasoning tasks. Extensive experiments demonstrate that our method achieves higher task accuracy and lower inference cost compared to baselines\footnote{The code is available at blue{https://github.com/FairyFali/GraphSkill}.}.

Fali Wang, Chenglin Weng, Xianren Zhang +3

The Pennsylvania State University, University Park, Pennsylvania, USA · Michigan State University, East Lansing, Michigan, USA

LLM Reasoning with Graphs Graph Reasoning Graph Retrieval-Augmented Generation Algorithmic Reasoning Code Generation

Feb 20, 2026

1D-Bench: A Benchmark for Iterative UI Code Generation with Visual Feedback in Real-World

Design-to-code translates high-fidelity UI designs into executable front-end implementations, but progress remains hard to compare due to inconsistent datasets, toolchains, and evaluation protocols. We introduce 1D-Bench, a benchmark grounded in real e-commerce workflows, where each instance provides a reference rendering and an exported intermediate representation that may contain extraction errors. 1D is short for one day, representing the efficient completion of design-to-code tasks in less than one day. Models take both as input, using the intermediate representation as structural cues while being evaluated against the reference rendering, which tests robustness to intermediate representation defects rather than literal adherence. 1D-Bench requires generating an executable React codebase under a fixed toolchain with an explicit component hierarchy, and defines a multi-round setting in which models iteratively apply component-level edits using execution feedback. Experiments on commercial and open-weight multimodal models show that iterative editing generally improves final performance by increasing rendering success and often improving visual similarity. We further conduct a pilot study on post-training with synthetic repair trajectories and reinforcement learning based editing, and observe limited and unstable gains that may stem from sparse terminal rewards and high-variance file-level updates. The data and scripts used in this study are available in an anonymized repository at https://anonymous.4open.science/r/d2c-benchmark-A9C4/.

Qiao Xu, Yipeng Yu, Chengxiao Feng +1

Taobao & Tmall Group of Alibaba

Benchmark Design Execution-Guided Code Generation Code Generation Code Generation Benchmarks

Feb 17, 2026

TAROT: Test-driven and Capability-adaptive Curriculum Reinforcement Fine-tuning for Code Generation with Large Language Models

Large Language Models (LLMs) are changing the coding paradigm, known as vibe coding, yet synthesizing algorithmically sophisticated and robust code still remains a critical challenge. Incentivizing the deep reasoning capabilities of LLMs is essential to overcoming this hurdle. Reinforcement Fine-Tuning (RFT) has emerged as a promising strategy to address this need. However, most existing approaches overlook the heterogeneous difficulty and granularity inherent in test cases, leading to an imbalanced distribution of reward signals and consequently biased gradient updates during training. To address this, we propose Test-driven and cApability-adaptive cuRriculum reinfOrcement fine-Tuning (TAROT). TAROT systematically constructs, for each problem, a four-tier test suite (basic, intermediate, complex, edge), providing a controlled difficulty landscape for curriculum design and evaluation. Crucially, TAROT decouples curriculum progression from raw reward scores, enabling capability-conditioned evaluation and principled selection from a portfolio of curriculum policies rather than incidental test-case difficulty composition. This design fosters stable optimization and more efficient competency acquisition. Extensive experimental results reveal that the optimal curriculum for RFT in code generation is closely tied to a model's inherent capability, with less capable models achieving greater gains with an easy-to-hard progression, whereas more competent models excel under a hard-first curriculum. TAROT provides a reproducible method that adaptively tailors curriculum design to a model's capability, thereby consistently improving the functional correctness and robustness of the generated code. All code and data are released to foster reproducibility and advance community research at https://github.com/deep-diver/TAROT.

Chansung Park, Juyong Jiang, Fan Wang +4

Electronics and Telecommunications Research Institute · The Hong Kong University of Science and Technology (Guangzhou) · The Hong Kong University of Science and Technology +2

LLM Code Generation RL for Code Generation Code Generation Curriculum RL RL Fine-Tuning Curriculum Learning

Feb 13, 2026

An Online Reference-Free Evaluation Framework for Flowchart Image-to-Code Generation

Vision-Language Models (VLMs) are increasingly used in document processing pipelines to convert flowchart images into structured code (e.g., Mermaid). In production, these systems process arbitrary inputs for which no ground-truth code exists, making output quality difficult to assess. We propose a reference-free evaluation framework that monitors flowchart image-to-code generation quality at inference time, using only the input image and the generated output. The framework introduces two automated metrics:

\text{Recall}{\text{OCR}}

, which estimates content coverage by extracting text from the input image via OCR as a proxy reference, and

\text{Precision}{\text{VE}}

, which detects hallucinated elements through Visual Entailment against the original image. Their harmonic mean,

\text{F1}{\text{OCR-VE}}

, provides a unified quality score. Validation on the FlowVQA dataset shows strong agreement with ground-truth metrics (average Pearson's

r = 0.97

,

0.91

, and

0.94

for Recall, Precision, and F1, respectively), confirming the framework's reliability as a practical, reference-free alternative for continuous quality monitoring in production settings.

Giang Son Nguyen, Zi Pong Lim, Sarthak Ketanbhai Modi +2

Nanyang Technological University · VinUniversity · AUMOVIO Singapore

VLM Evaluation Code Generation Reference-Free Evaluation Automated Evaluation Image-to-Code Generation

Feb 5, 2026

A Theoretical Analysis of Test-Driven Code Generation

Code assistants are increasingly utilized in test-driven software development, yet the theoretical mechanisms behind their environment-interaction strategies remain underexplored. We provide a probabilistic framework for two dominant paradigms: code selection after generation using the execution environment, and code generation conditioned on environment feedback. First, we formalize several well-established selection heuristics as environment-aware estimators of code correctness. We theoretically prove that estimators based on fuzzy functional similarity add an inductive bias and strictly dominate estimators based on functional equivalence in terms of signal-to-noise ratio. Second, we frame backprompting as an in-context approximation of Thompson sampling. We derive a novel regret bound for reward functions with unobservable components, theoretically explaining why the effectiveness of backprompting is limited by the ambiguity of the informal task description (an irreducible regret). Using seven state-of-the-art open weight models, we corroborate these findings across BigCodeBenchHard, LeetCodeDataset, QiskitHumanEvalSim, and SWE-bench Verified. Our formalization also suggests how to improve task descriptions effectively, leading to an improved benchmark for LLM-assisted quantum programming, QiskitHumanEvalSimX.

Nicolas Menet, Michael Hersche, Andreas Krause +1

Execution-Guided Code Generation Code Generation Code Generation Evaluation