Overview

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

335 papers34 papers in the last four weeks, level with the four weeks before. 0.2% of all new papers.

Aug 23, 2026

Iteration Without Elaboration: A Simple ReAct Architecture Suffices for Text-to-SQL Generation

Modern text-to-SQL systems have become increasingly elaborate, relying on schema-linking modules, retrieval-augmented prompting, candidate generation, and multi-stage refinement pipelines. While effective, these additions introduce substantial latency and engineering overhead. To this end, we present ReAct-SQL, a simple yet effective zero-shot ReAct-style framework built solely on iterative reasoning and a constrained action space defined by a typed Domain-Specific Language (DSL) of 15 relational operations, rather than free-form SQL generation. The model incrementally issues DSL calls, observes compiled-SQL execution feedback, and revises its reasoning through interaction. On corrected BIRD mini-dev and EHR-SQL, ReAct-SQL achieves 84.5% and 73.9% accuracy, respectively, matching substantially more elaborate baselines while running up to 8×8\times faster. Incremental ablations further show that iteration primarily improves grounding, while the DSL improves compositional reliability.
Aug 23, 2026

Function-Level Execution Feedback for Code Preference Optimization

Process supervision has improved mathematical reasoning, where intermediate steps are naturally expressed as chains of thought. In code generation, however, process supervision remains underexplored because there is no standard notion of a step. Supervision can target lines, reasoning traces, or program states, making it unclear what to label and optimize. We propose STEP-KTODER, a framework for code preference optimization that defines steps as module-level functions in decomposed multi-function programs and assigns binary correctness labels via automatically generated unit tests. Our method provides a code-specific instantiation of stepwise KTO, combining function-level process supervision with outcome-level feedback on the full program. We evaluate on HumanEval(+), MBPP(+), BigCodeBench, and LiveCodeBench, showing that STEP-KTODER improves over outcome-only KTO and DPO. Further analysis shows that execution-based labels are essential: LLM-as-a-judge annotations systematically over-predict function failures, corrupt positive step labels, and degrade downstream preference optimization. Code is available at: https://github.com/inechnech/STEP-KTODER.
Aug 22, 2026

Architecture as Capability Equalizer for Coding Agents

LLM-based coding agents generate complete software systems from high-level descriptions, yet little is known about how the format of architecture specifications affects the quality of generated code or whether this effect depends on model capability. We present a controlled experiment comparing five informationally equivalent specification formats (informal prose, Mermaid diagrams with constraints and ADRs, OpenAPI, C4/Structurizr DSL, and TypeScript interface contracts with ArchUnit-style rules) across six models from three vendor families (Anthropic Claude, OpenAI GPT, Google Gemini). Across 90 multi-turn agent trials, specification format shows a strong format x model interaction. On the strongest models (Sonnet 4.6, GPT-5), format barely matters (quality spread 0.17-0.92). On weaker models, format produces spreads of 0.83-2.42 points, with code-proximate formats (OpenAPI, TypeScript contracts) recovering most of the capability gap. Mid-tier models can consume more tokens than frontier models for worse output when they enter compilation debugging loops that stronger models avoid. Self-validation rates collapse from 100% (Sonnet) to 0% (Gemini Flash) across the capability spectrum. TypeScript contracts triple API route coverage for the weakest model (33% to 100%). Structured architecture specifications serve as a capability equalizer, with value inversely proportional to model strength and the largest returns for cost-optimized deployments.
Aug 20, 2026

Repo0: Design-Driven Zero-to-All Code Generation

Large language model agents have made substantial progress in code generation, yet most existing systems assume a predefined repository architecture. This assumption does not hold in zero-to-all code generation, where an agent must construct an entire software project directly from natural-language requirements while maintaining a modular repository architecture throughout development. We present Repo0, a continuous structural evolution framework for zero-to-all code generation. Repo0 maintains an explicit architectural state instantiated as a Dual-Directed-Acyclic-Graph (Dual-DAG), consisting of a requirement-level DAG, a component-level DAG, and their alignment relation. Starting from natural-language requirements, it iteratively evolves component boundaries through structural actions guided by modularity metrics until structural convergence, after which the converged architecture guides test-driven development code generation. We evaluate Repo0 on six real-world repositories from RepoCraft using GPT-5 mini and DeepSeek V3.2. Repo0 achieves the highest Functionality Coverage and Pass Rate across all settings. Compared with RPG, the strongest repository-planning baseline, Repo0 improves Functionality Coverage by up to 20.08 percentage points and Pass Rate by up to 29.74 percentage points. Ablation and structural-evolution analyses further demonstrate the importance of the Dual-DAG architectural state, modularity-guided structural evolution, and explicit structural convergence.
Aug 17, 2026

VLCP: Vision Language Control Policy Closed-Loop Code Replanning for Robot Manipulation

Turning a frontier vision-language model into a robot policy usually means fine-tuning it to emit an action representation it never saw in pretraining, which throws away much of the reasoning that made the model worth reaching for. We go the other way and keep the VLM frozen. It writes the policy as a short Python control function, with no demonstrations and no fine-tuning. Writing that code once is open-loop, though. Existing closed-loop methods react at the wrong level: they retry a fixed policy or pick a different subtask, but never rewrite the code that failed. VLCP closes the loop where the failure actually lives, on the control code, within a single episode. Every KK steps the VLM re-observes the scene from multi-view RGB, proprioceptive state, and a state delta, then rewrites the control function from what it just saw, so a failure is caught before it compounds. We evaluate on a 57-task MuJoCo/RoboVerse sweep. This training-free policy reaches 35.1%35.1\% pooled success, against 3.5%3.5\% for the identical system queried once per episode. That tenfold gap holds with non-overlapping confidence intervals in every scene family. The gain traces to a 27.3%27.3\% within-episode recovery rate on failed grasps: a miss an open-loop controller would carry to the end of the episode gets re-observed and fixed at the next replan. And the loop stays cheap. A median 84%84\% of input tokens hit cache, an episode needs only about 1010 compact queries, and control blocks written during any replan persist to a cross-episode skill library reused in later prompts.
Aug 17, 2026

TDD-Agent: Test-Driven Reasoning for Code Generation

Large Language Models (LLMs) have achieved remarkable progress in code generation, yet ensuring correctness in complex, repository-level tasks remains challenging. Existing approaches often use generated tests as static post-hoc validators, which limits their ability to guide implementation and may introduce misleading feedback when the tests themselves are incomplete or incorrect. In this paper, we introduce TDD-Agent, which operationalizes the test-driven development paradigm for code generation. TDD-Agent first prompts the model to generate executable tests, encouraging it to clarify expected behaviors before implementation, and then performs iterative dual-track refinement over both the generated code and tests using execution feedback. We first isolate the effect of test-first reasoning through a prompt variant TDD-prompt on LiveCodeBench, where it consistently improves upon reasoning-based prompting baselines. Building on this finding, we evaluate the full TDD-Agent framework on RepoEval, a repository-level benchmark, and show that it consistently outperforms retrieval-based and agent-based baselines. Additional analyses show that iterative refinement improves not only code correctness but also the effectiveness of the generated tests, yielding higher pass rates, coverage, and mutation scores, suggesting that tests can serve as evolving reasoning artifacts rather than fixed validators. Our source code is available at https://anonymous.4open.science/r/TDD-Agent-Framework-6370/.
Aug 16, 2026

PLSQLBench: Benchmarking LLM Systems for Executable Procedural Database Programming

We present PLSQLBench, to our knowledge the first benchmark for evaluating whether LLMs can write executable PL/SQL programs, with correctness measured through execution-based tests. Existing LLM evaluations largely target general-purpose code generation or declarative text-to-SQL, leaving procedural database programming underexplored. PLSQLBench contains 2,865 instances: 2,594 single-turn tasks and 271 multi-turn conversations spanning 978 turns. The benchmark combines complex schema-grounded tasks over enterprise-style Spider 2 databases, simpler schema-grounded tasks derived from Spider, and MBPP-derived procedural problems, covering varying levels of database grounding and procedural complexity. Experiments with eight LLMs reveal recurring difficulties in schema grounding, PL/SQL dialect fidelity, procedural control flow, exception handling, and cross-turn consistency. Tool-augmented LLM agents improve performance on several schema-grounded evaluations, although substantial gaps remain. These results highlight procedural database programming capabilities not directly assessed by conventional code generation or text-to-SQL benchmarks. Our code is available at https://github.com/oracle-samples/plsqlbench.
Aug 16, 2026

Who Leads Now? Token-Level Modality Arbitration for Chart-to-Code Generation

Chart-to-code generation requires a model to read the fine-grained visual details of a chart and write executable code that reproduces it. Existing chart-to-code methods either train visual and coding abilities separately, or fine-tune on chart-to-code data with the two abilities entangled. Neither strategy accounts for the distinct nature of the two abilities or the interference that arises when they are optimized together. We propose MoCA (Mixture of Cross-modal Arbitration), which separates the two abilities rather than blending them. MoCA is built on Cross-modal Arbitration Block (CAB), which maintains a visual branch and a code branch as two distinct pathways, and a lightweight arbiter that arbitrates their relative contributions at every layer and generated token. We train MoCA in two stages: a supervised warm-up on self-distilled reasoning trajectories that decomposes visual understanding into explicit steps, followed by reinforcement learning with rewards on both the reasoning process and the final code. Analysis shows that the arbiter learns structured rather than arbitrary allocations, with expert contributions varying systematically across tokens, layers, and instances. Across three benchmarks, MoCA delivers competitive performance against general-domain and chart-specialized models. Ablation results show that the gains cannot be attributed to a larger model size alone, but instead arise from the joint contributions of complementary visual and code branch initialization and input-conditioned arbitration through CAB.
Aug 13, 2026

Does ISO-Grounded NFR Specification Improve LLM Code Generation? A Comparison of Rich and Structured Interventions against a Natural-Language Baseline

In LLM-based code generation, Non-Functional Requirements (NFRs) are often specified as terse one-line phrases. We ask whether grounding those specifications in ISO/IEC 25010 Quality Model, either as rich natural-language prose (NL-rich) or as structured JSON (Structured), improves code generated on HumanEval/HumanEval-ET compared to a RobuNFR-style one-line baseline (NL-simple). We evaluate four NFRs (performance, error handling, code smell, readability) with ten prompt variations per condition under a fixed model snapshot and paired non-parametric analysis. Primary finding: ISO-grounded enrichment improves static quality proxies (unreadability density falls across all four NFRs (e.g., Performance 0.88 -> 0.69 for NL-rich)) and reduces sensitivity to prompt wording, but does not reliably improve functional correctness; for error handling, extended-test pass rate decreases, suggesting tension between defensive coding patterns and exact-output benchmarks. Secondary finding: when ISO content is held constant, NL-rich and Structured differ negligibly in correctness (|delta| <= 0.023), indicating that semantic content matters more than JSON-vs-prose format. Practitioners should invest in standard-grounded NFR content rather than serialization form. A fully traceable replication package is provided.
Aug 13, 2026

Fine-Tuning Qwen3-27B for C-to-Rust Code Translation: A Three-Stage Curriculum of Pretraining, Debugging-Aware SFT, and Task-Specific SFT

Translating C code into safe, idiomatic Rust is a longstanding software-engineering goal because it can eliminate entire classes of memory-safety vulnerabilities while preserving the functional behavior of legacy systems. Large language models (LLMs) have shown promise for this task but typically underperform when applied off-the-shelf, since general-purpose pretraining rarely emphasizes idiomatic Rust generation, cross-language semantic equivalence, or the ability to reason about and repair compiler/runtime feedback. In this report we describe a three-stage fine-tuning curriculum applied to Qwen3-27B that is designed to progressively specialize the model for the C-to-Rust (C2Rust) translation task: (1) continued pretraining on Rust-centric corpora to strengthen the model's prior over idiomatic Rust syntax and standard-library usage; (2) supervised fine-tuning (SFT) on the microsoft/Verus_Training_Data dataset to instill debugging and self-repair behavior over Rust code; and (3) task-specific SFT on paired C/Rust solutions derived from LeetCode problems to teach direct semantic translation. We evaluate the resulting model using the agentic, static-analysis-guided verification framework of SACTOR, which performs structure-aware, two-phase (unidiomatic to idiomatic) translation with foreign-function-interface (FFI)-based end-to-end (E2E) testing. We report success rate, idiomaticity (Clippy lint counts, unsafe-code fraction), and failure-mode analyses, and compare our fine-tuned model against baseline Qwen3-27B and other LLMs evaluated under the same framework.
Aug 13, 2026

Vero: Can AI Agents Build Formally Verified Software Repositories?

AI agents are increasingly used for programming, but do not provide any guarantee on the correctness of generated code. Verified code generation, in which an agent produces both an implementation and a machine-checked proof of its specification, offers a stronger path toward trustworthy AI-generated software. Existing benchmarks in this direction either focus on individual functions or only evaluate proof generation with provided implementations. It is still an open question whether agents can make coherent implementation and proof choices across real multi-module codebases. To bridge this gap, we introduce Vero, the first benchmark to evaluate joint implementation and proof synthesis at the repository level. Vero contains 43 multi-module instances sourced from real-world repositories spanning Python, Dafny, Verus, and Coq, and covering diverse domains from cryptographic protocols to distributed systems. Each instance consists of a multi-module Lean 4 repository with predetermined API interfaces, manually curated formal specifications, and reference implementations, supporting both proof-only and code-and-proof evaluation modes. To improve benchmark reliability, Vero also includes an audit mechanism where agents are allowed to formally prove unsatisfiability of provided specification or incorrectness of reference code, which surfaces and corrects latent code and specification errors during curation. We evaluate frontier coding-agent configurations with Lean toolchain access. The strongest agent fully solves only 27 of 43 instances and closes no specifications on the hardest repositories. Vero provides a concrete testbed for measuring progress toward repository-scale verified software synthesis, where current agents still fall short. We release the benchmark, curation pipeline, and evaluation harness at https://github.com/sunblaze-ucb/vero.
Aug 13, 2026

Edit2TikZ: A Comprehensive and Challenging Benchmark for Scientific Figure Editing with TikZ

Although multimodal large language models (MLLMs) have shown substantial potential in visual understanding and graphic code generation, editing scientific figures through code presents a greater challenge: a model must jointly recover visual structure, ground the requested change, generate compilable code, and preserve all unrelated content. While existing TikZ benchmarks mainly focus on figure reconstruction and generation, few systematically evaluate instruction-guided scientific figure editing with compilable code. We introduce Edit2TikZ, a comprehensive benchmark for scientific figure editing tasks, featuring 1,548 diverse and high-quality samples. Edit2TikZ combines real-world and controlled synthetic edit cases, supports both textual and visual localization request, and contains multi-step editing, each with step-level annotations. We further construct a human-aligned evaluation framework to measure whether a requested edit is completed while irrelevant content is preserved. Utilizing Edit2TikZ, we evaluate 14 mainstream MLLMs and find that current systems remain unreliable: on average, proprietary models achieve a compilation success rate of merely 75% and remain limited in both figure restoration and edit correctness, while compact models below 9B struggle further with instruction following and complete figure generation. Therefore, we build a mixed training set TikZEditMix and adopt reconstruction-then-editing curriculum learning for compact models. On Qwen3.5-4B, this training improves the compilation success rate from 45.35% to 83.40% and yields an average improvement of 18.7 points across our proposed evaluation metrics. The code and data will be released at https://github.com/Solunny/Edit2TikZ.
Aug 12, 2026

From Visual Widgets to UI Code: Efficient Tool-Grounded Generation

Existing screenshot-to-code systems face a trade-off between flexibility and controllability. Direct multimodal generation can hallucinate visible details, whereas structured pipelines reduce such errors through component-wise decomposition, predefined templates, and customized intermediate representations. These structures, however, introduce additional generative orchestration and restrict outputs to designs covered by the representation. We investigate whether selective tool grounding can improve the fidelity--efficiency trade-off of direct widget-to-code generation. We introduce WidgetGen, a lightweight tool-grounded framework that extracts observable text and color evidence, performs high-level layout and optional chart reasoning, and directly generates executable JavaScript XML (JSX). This design reduces reliance on component-wise generation while avoiding a fixed UI schema. Across six multimodal models and 1,0001{,}000 held-out widgets, WidgetGen outperforms direct prompting and the structured Widget2Code pipeline on most visual reconstruction metrics, with consistent gains in area, legibility, and style. Finally, reconstruction-derived image-code pairs improve six Qwen-family open-weight models across every reported metric through supervised fine-tuning. These results establish WidgetGen as a strong lightweight baseline and show that selective evidence grounding offers an effective alternative to extensive representation constraints.
Aug 12, 2026

Diagram-MMU: A Multi-Modal Benchmark for Scientific Diagrams

Multimodal Large Language Models (MLLMs) have been growing the capability for scientific writing and collaboration. For example, OpenAI Prism is a free workspace for scientific writing and collaboration. One important feature in Prism is turning scientific diagrams directly into LaTeX TikZ code. In this paper, we build a benchmark, Diagram-MMU, a multi-modal benchmark designed to assess MLLMs' ability for scientific diagram parsing and understanding. Diagram-MMU features 3.7k curated diagrams and 18.3k human-validated questions across six domains. It evaluates MLLMs on three tasks common in vibe writing workspaces: diagram-to-code parsing, diagram-to-code editing, and diagram question answering, alongside agentic settings per task. The evaluation of 12 MLLMs reveals that diagram-to-code tasks are more challenging than diagram question answering: models can reason well over diagrams but struggle to parse and edit them, underscoring the need for methods to enhance MLLMs' capability in diagram-to-code generation. Under agentic settings, most models improve parsing and editing performance but degrade on question answering, while Claude-4.6 Opus consistently improves across all three tasks. Project Page: https://vi-ocean.github.io/projects/diagram-mmu.
Aug 10, 2026

P3^{3}: Joint Program-and-Proof Planning for Verified Code Generation

Verified code generation asks a large language model (LLM) to generate both an executable program and a machine-checkable proof that the program meets a formal specification, promising software that is correct by construction. The de facto workflow decouples the two halves of the problem: first synthesize a program, then attempt to prove it correct. We observe that this sequential pipeline can be both ineffective and inefficient in practice. A program generated without anticipating its proof can be subtly incorrect or structurally difficult to verify, forcing the LLM into brittle repair loops that alternate between patching the code and patching the proof. Inspired by Dijkstra's view that a program and its correctness argument should be developed hand in hand, we propose P3P^3, an LLM-based agentic workflow that first derives a unified program-and-proof plan from the specification, then elaborates the implementation and proof scaffold under this shared plan. To evaluate verified code generation in realistic settings, we further introduce Lean4Commit0, a repository-derived, library-level benchmark built by extracting core APIs from real-world software repositories and translating their requirements, including relational specifications across APIs, into Lean tasks. Using four frontier LLM backends, we evaluate P3P^3 on Verina, AlgoVeri, and our Lean4Commit0 benchmark, where it achieves the highest solve rate in every benchmark--model setting. Compared with the stronger baseline, it improves solve rates by 4.6--11.2 percentage points and reduces per-task API cost by up to roughly 40% and wall-clock time by up to roughly 37% on the difficult subset of each benchmark. A targeted ablation further shows gains of 3.3--8.3 points over implementation-only planning, isolating the benefit of planning the program and proof jointly.
Aug 6, 2026

Characterizing the Quality Profile of AI-Generated C++ in Production

The widespread integration of AI coding assistants offers undeniable boosts to engineering velocity. Yet, recent studies point to a growing trade-off, revealing persistent challenges with code quality and maintainability. Industry leaders, including frontier AI labs, echo these concerns. As large language models are increasingly relied upon to author production code, understanding their impact on shipped software quality has become a critical priority. However, assessing these effects in industrial workflows remains difficult due to observability barriers. We study the impact of AI-generated code on production quality within a large enterprise operating global products relied upon by billions of users daily. Driven by this scale and user trust, the organization values code quality and has built thorough observability for every line of code deployed into production, enabling us to overcome measurement barriers to assess these effects. This study presents a large-scale empirical analysis of AI-generated C++ code from April 2025 to April 2026, tracking 3.52 million code changes across this enterprise's brownfield codebase. The core purpose is to understand the quality, performance, and maintenance characteristics of AI-generated code compared to human-written code in a production environment at scale. We find that AI-generated C++ code has a distinct quality profile, showing higher rates of interface and coupling burdens, copy and allocation overheads, and a reliance on explicit loops over optimized standard APIs. These issues translate into tangible downstream costs, including increased review effort and a 5-8% increase in compute resource consumption. However, we demonstrate that providing models with targeted, taxonomy-informed feedback can mitigate these effects, leading to an 11.1% reduction in targeted static analysis warnings and improved computational efficiency.
Aug 6, 2026

RA-CAD: Learning Post-Execution Critique for State-Aware Text-to-CAD Generation

Text-to-CAD generation translates natural-language design intent into editable and executable parametric computer-aided design (CAD) codes, reducing the expertise and effort required for manual modeling. Existing methods incorporate fixed, externally supplied, prompt-induced, or separately optimized critique mechanisms to optimize the generation process, but they do not necessarily optimize how feedback is interpreted and translated into effective corrective actions throughout the generation process. To bridge this feedback-utilization gap, we present RA-CAD (ReAct Agent for CAD), a state-aware agent that interacts with the CAD environment through a Generate--Execute--Critique--Rewrite loop. At each iteration, RA-CAD executes the current code and observes its outcome. Conditioned on the design instruction, current code, and execution feedback, the agent then generates an explicit post-execution critique as an intermediate policy action. This critique either validates the current result for termination or provides revision-oriented guidance that conditions the next rewrite. CAD Code Bootstrapping (CCB) first establishes fundamental parametric CAD coding capabilities through supervised fine-tuning. Feedback-Driven Agent Optimization (FAO) subsequently applies trajectory-level Group Relative Policy Optimization to both policy-generated code and critique sequences, assigning terminal F1 and Chamfer Distance rewards to the complete interaction trajectory. This formulation makes critique an outcome-aligned, learnable policy decision rather than an unoptimized auxiliary output. Experiments on CADFusion and Text2CAD show that RA-CAD achieves state-of-the-art execution validity and geometric quality compared with existing methods and strong proprietary language models, demonstrating the effectiveness of the proposed state-aware text-to-CAD agent.
Aug 5, 2026

COMPAS: Difficulty-Aware Joint Search for Optimizing Code Generation

Code generation systems make each LLM call with a model, a prompt, and decoding settings. However, existing optimization methods usually tune only part of these choices or use one fixed configuration for all tasks: global optimizers search one configuration for all tasks, routers choose only a model, and prompt optimizers keep the model and decoding settings fixed. This leaves their joint, group-specific interactions unclear. We therefore examine how these choices interact and observe that prompts and decoding settings interact, tuning effects vary by model, and the best configuration varies by task difficulty. Guided by these observations, we introduce COMPAS (Code-generation Optimization over Models, Prompts, And Decoding Settings), a difficulty-aware method that learns group-specific quality-cost fronts through low-cost model selection and joint prompt-decoding search, then routes each test task to its matching front online without further search. Under a matched search budget on LiveCodeBench, COMPAS improves pass@1 from 45.9% for the best baseline to 52.8% while reducing cost from 36.57to36.57 to 4.92. This also transfers to repository-level code generation on SWE-bench, resolving 76.0% of tasks versus 70.0% for the best baseline. Code and the reproducibility artifact are available at https://github.com/gjz78910/COMPAS.
Aug 4, 2026

Pattern over Pixels: Measuring Pattern Completion Bias in Multimodal Code Generation

Multimodal large language models (MLLMs) are increasingly used to translate webpage screenshots into front-end code, but repeated UI patterns may sway them toward visually incorrect yet pattern-consistent outputs. In this work, we test how repeated webpage patterns hurt MLLM accuracy on an objective screenshot-to-code fill-in-the-blank task. We introduce the first benchmark for visual pattern-completion bias, where one localized element in a repeated UI pattern is perturbed and the model must recover the masked width or font-size value from the screenshot and HTML context. Starting from 30 webpages curated from the Design2Code dataset, we build 1,440 evaluated screenshots spanning structural card and text-style patterns under standard and noise-overlaid conditions. We evaluate five frontier MLLMs and find that all are strongly biased toward the repeated baseline. Mean bias rate reaches 69.78% on card-width perturbations and 80.22% on text font-size perturbations, while mean accuracy is only 21.17% and 7.89%, respectively. Codex-5.3 performs best but still drops from 68.61% accuracy on cards to 13.89% on text, while Flash-3.0 reaches 96.11% bias on text. Noise, subtler perturbations, and boundary positions further increase bias rate. Reasoning analysis further shows that greater reasoning effort correlates with lower bias, yet qualitative evidence reveals that models can identify the anomalous element and still override it with the pattern-consistent answer. Our results identify a concrete failure mode in multimodal code generation and show that its severity is strongly associated with visual saliency
Aug 4, 2026

GenOS: Compositional Certificates for Semantic Robustness in AI Code Generation

AI coding agents are stochastic workflows: prompts are interpreted, artifacts are sampled, validators produce observations, and orchestrators commit or repair. Small prompt or specification changes can therefore alter program-behavior distributions even when the texts appear synonymous. Existing systems evaluate correctness, but lack a compositional criterion for safely replacing a prompt, contract, generator, or program inside a complete agentic workflow. We introduce GenOS, a probabilistic operational semantics for this replacement problem. Each layer is modeled as a Markov kernel, and each interface carries an observer-relative equivalence. We prove that equivalence-compatible kernels descend to quotient classes and that quotienting commutes with distributional extension and sequential composition. Hence, equivalent prompts induce equal probabilities for all downstream equivalence-closed events, including verified commit. We also establish workflow bisimulation, guarded-commit safety under sound validation, total-variation non-expansiveness, and an additive robustness bound that attributes approximation error to individual pipeline layers. An executable insertion-sort audit instantiates the theory with natural-language paraphrases, a formal contract, six programs, two observers, and exhaustive execution on 121 inputs. Equivalent prompts yield identical code-class and commit distributions; a prompt assigning 5% probability to an in-place contract is distinguished by a mutation observer, while downstream distances remain within the predicted bound. Across 20,000 randomized finite-kernel trials, no exact or approximate law is violated. GenOS is model-parametric: compatibility is a measurable property to test, not an assumption about language-model behavior.
Aug 4, 2026

MT-Web2Code: Benchmarking Coding Agents on Multi-Turn Regional Reconstruction and Localized Modification

Recent advances in Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities in web UI generation. However, existing benchmarks predominantly focus on single-turn full-page generation from scratch, overlooking the iterative workflow of real-world frontend engineering, where developers repeatedly reconstruct missing regions and modify localized elements within existing codebases. To bridge this gap, we introduce MT-Web2Code, the first multimodal coding benchmark for multi-turn Macro-Level Regional Reconstruction and Micro-Level Localized Modification, which contains 102 tasks spanning 16 vertical domains. To construct deterministic repair trajectories without costly turn-level human annotation, we develop a scalable Reverse-Corruption Trajectory Engine that iteratively injects structural and stylistic defects into golden pages. We further propose a dual-axis evaluation protocol that measures target-region fidelity and the preservation of unaffected content, where regional reconstruction is assessed by a 5-dimensional VLM-based rubric and localized modification by deterministic pixel-grounded alignment. Experiments on 13 frontier coding agents reveal that current agents struggle to faithfully reconstruct target regions while preserving unaffected content, lack fine-grained visual-code alignment for localized edits, and suffer from error snowballing over multiple turns. Beyond benchmarking, our deterministic evaluation metrics provide fine-grained feedback signals that may facilitate future research on training iterative UI coding agents. Our evaluation code and data will soon be released.
Aug 4, 2026

Route-Align-Verify for Functional Correctness in Code Generation

Large language models (LLMs) have substantially improved code generation, yet achieving strong functional correctness remains difficult, especially for heterogeneous programming tasks where a single prompting strategy and a single directly generated output are often insufficient. In this paper, we present RAV, a lightweight and modular framework that improves code generation with a fixed backbone model through three coordinated stages: Route, which applies task-aware prompt routing before generation; Align, which reduces the mismatch between fine-tuning prompts and inference-time prompts through aligned LoRA adaptation; and Verify, which selects the final output by executing multiple candidates against visible public tests. We evaluate RAV on the MBPP benchmark under both the sanitized and full settings. The complete RAV pipeline achieves the best performance among all evaluated configurations, reaching 0.8911 on MBPP Sanitized and 0.8520 on MBPP Full. Compared with the base model, these results represent improvements of 6.35 and 9.92 percentage points, respectively. Component-wise ablation experiments further show that task-aware routing and aligned adaptation become substantially more effective when combined with execution-based verification. Additional robustness and contamination analyses support the reliability of the observed improvements. Overall, the results indicate that functional correctness in code generation can be meaningfully improved without modifying the backbone architecture, by jointly optimizing how tasks are prompted, how the model is adapted, and how final outputs are selected.
Aug 2, 2026

Security-First Evaluation of Text-to-Terraform: Benchmarking LLMs and SLMs for Secure IaC Generation

Cloud misconfiguration remains a leading cause of security incidents, yet whether LLMs and SLMs can generate security-compliant Infrastructure-as-Code is an open question. We benchmark seven models, three closed LLMs (Claude Opus 4, GPT-5.4, Gemini 2.5 Pro) and four open SLMs (Qwen2.5-Coder-14B, WizardCoder-33B, CodeLlama-13B, Magicoder-S-CL-7B), on AWS Terraform generation across 17 scenarios, integrating Checkov and Trivy scanners into a GitLab CI/CD pipeline and evaluating two prompt strategies at three security levels (pass@5). Syntactic validity and security compliance are largely orthogonal properties in LLM-generated IaC, a model that reliably produces well-formed Terraform does not necessarily produce secure Terraform: WizardCoder-33B achieves 77.8% validate rate yet zero Checkov compliance, while Claude Opus 4 reaches 23.1% Checkov and 92.5% Trivy pass rates under detailed security prompting. Consequently, prompt engineering alone is insufficient: automated multi-tool scanning remains a necessary complement to LLM-assisted IaC generation regardless of model family or prompt strategy. All artifacts are publicly available.
Jul 30, 2026

PrintAnything: Learning an Intermediate Representation for 3D printing G-code Generation

Point clouds are one of the most fundamental and widely used 3D representations, serving as the most basic geometric representation of 3D shapes. Nevertheless, most existing 3D printing pipelines require a watertight mesh as input, preventing the direct use of point clouds for fabrication. A common workaround is to reconstruct meshes from point clouds; however, the resulting meshes often contain geometric artifacts, such as incorrect faces or topological inconsistencies, that are difficult to repair and may lead to printing failures. To overcome these limitations, we propose PrintAnything, a novel framework that learns to produce executable 3D printing G-code directly from 3D point clouds without requiring mesh reconstruction. To enable point clouds to serve as direct input for slice-wise toolpath generation, we introduce a slice-wise point projection strategy that transforms unstructured 3D point clouds into slice-aligned 2D representations consistent with layer-by-layer nature of fused deposition modeling in 3D printing. To eliminate mesh dependency and provide a unified representation that bridges point clouds and G-code, we propose Geometric plan (G-plan) map, a compact 2D representation composed of occupancy, region, and flow maps that encode the geometric and extrusion properties required for toolpath synthesis in 3D printing. As a result, our proposed method accurately generates printable G-code directly from point clouds, enabling a practical and fully mesh-free pipeline for 3D printing. The code is publicly available at https://github.com/Sangminhong/PrintAnything.
Jul 30, 2026

Metaphor-Induced Algorithmic Steering: Cross-Domain Procedural Transfer in LLM Code Generation

Large language models benefit from elements in natural language, such as metaphors and analogies in training data and inference input to achieve generalisability across different domains. However, these language elements may also lead to unwanted behaviors when metaphorical expressions implicitly transfer inappropriate procedural patterns into new tasks. In this paper, we show that metaphorical instructions can induce analogical transfer of procedural mechanisms, thus steering code-generation models towards less efficient algorithms. We refer to this metaphor-induced effect as metaphorical algorithmic steering: a skill that is benign and plausible within its source domain transfers an abstract procedural schema into a programming task, causing the model to favor exhaustive search, full scans, or repeated reconstruction without explicitly mentioning the target algorithm. More broadly, this suggests that code-generation models can carry procedures that are appropriate in a task's background domain into the task's programming problem, where they can lead to unwanted outcomes. To study this phenomenon, we develop MASC (Metaphorical Algorithmic Steering for Code Generation), a framework that iteratively metaphorizes and refines benign skills to elicit low-efficiency code while remaining benign and task-relevant. Beyond behavioral evaluation, we study whether this phenomenon is detectable and mechanistically reflected in model representations. Our method achieves high detection rates for metaphorical skills and less-efficient implementations. We also find that metaphorical skills induce a hidden-state shift towards lower-efficiency procedural behavior prototypes. These results suggest that metaphorical algorithmic steering operates through the transfer of procedural patterns associated with metaphorical source scenarios rather than surface level metaphorical language alone.
Jul 30, 2026

Drawing-Recode: Annotation Grounding for Parametric CAD Code Generation from Raster 2D CAD Drawings

Recovering Parametric CAD sequences from raster-format 2D Computer-Aided Design (CAD) drawings accumulated prior to digital transformation is important for part reproduction and manufacturing process automation. However, existing studies either process only vector drawings or are limited to specific domains, and fail to explicitly connect dimensional annotations to geometric information, limiting their use of dimensional information for 3D Parametric CAD sequences recovery. We propose Drawing-Recode, a framework that generates Parametric CAD sequences as CAD code from raster 2D CAD drawings. Drawing-Recode extracts geometric features via an image encoder and recognizes annotations through a separate text recognition module, then explicitly grounds annotations to geometric information using cross-attention and our proposed Annotation Grounding Loss (AGL). The resulting features are fed into a Large Language Model (LLM) to generate CAD code in the Structured Parametric CAD Code (SPCC) format. Experiments show that Drawing-Recode outperforms existing baselines and remains robust on scanned drawings resembling industrial conditions. We expect Drawing-Recode contributes to digitizing raster 2D CAD drawings in industrial settings and to part reproduction and manufacturing automation.
Jul 29, 2026

Fewer Clarifications, Better Code: Benchmarking Cross-Session Personalized Ambiguity Adaptation in Coding Assistants

AI-assisted coding increasingly translates informal user intent into executable software, yet coding requests often contain ambiguities that recur in user-specific ways across tasks and sessions. Existing disambiguation methods typically address each ambiguous request in isolation within the current coding session, often through eliciting additional clarification. However, whether resolved session history from the same user can serve as memory for resolving recurring personalized ambiguity in a newly opened session remains underexplored. We formulate personalized ambiguity adaptation as a new task: given a user's previously resolved coding sessions and a new ambiguous request, an assistant should identify the recurring ambiguity pattern, produce the intended executable solution, and minimize clarification. To benchmark this task, we introduce CAPA, which characterizes personalized coding ambiguity through six mechanisms and injects these mechanisms into unambiguous executable tasks using a controlled three-stage generation pipeline. CAPA contains 600 coding sessions across 60 balanced user--ambiguity cells, including 300 held-out evaluation sessions. We evaluate 12 recent LLMs under no-history and same-user-history conditions using executable success, first-turn success, and turns-to-completion. Our analyses examine task difficulty, user identity, and memory-based history use, and we further propose same-user history gating as a lightweight inference-time method. CAPA provides a foundation for developing long-term coding assistants that better align generated code with user intent while reducing repeated clarification.
Jul 28, 2026

TraceCoder: Explainable and Auditable Code Generation with Position-Key Snippet Versioning

Contemporary LLM-based coding agents produce code as black-box outputs: the rationale behind each line is hidden, the evolution of the code through benchmark-driven repair is ephemeral, and post-hoc auditing is impossible. We present a code generation concept that addresses these shortcomings through three complementary mechanisms: (i) a relational snippet-history schema that records, per repair event, the benchmark reference, round number, failure text, and LLM explanation, enabling full provenance queries; (ii) a browser-based visualisation tool that renders this history as heat-mapped, hover-annotated source code; and (iii) a competitive fractional position-key indexing scheme with tree-node delimiters that assigns stable, lexicographically-ordered identifiers to each code snippet, enabling fine-grained tracking without disrupting surrounding lines. We evaluate TraceCoder on 30 algorithmic programming tasks spanning string processing, mathematical computation, and data-structure manipulation, across two provider configurations. Of these, 10 exhaust the 6-iteration budget on tasks with subtle edge-case behaviour. Mean Chg% reaches 30%, three in ten code snippets carry a traceable repair-event row, compared to 21% when using Gemini 2.0 Flash as sole provider on a 20-task subset. Three detailed case studies demonstrate how the system explains which specific benchmark failures shaped each line of the final program. The proposed mechanism makes the internal "narrative" of automated code generation auditable and replayable, a property essential for trust and accountability in production deployments.
Jul 28, 2026

Try Again, Don't Look Back: Blind Resampling Outperforms Self-Repair in Small Code Models

Self-repair - returning a failed program to the model together with its test output and asking for a correction - is a standard component of code agents, and is almost always evaluated against a baseline that does not retry at all. We argue that this comparison confounds the value of the feedback with the value of the extra attempt. Using a placebo-controlled design on MBPP+ at three model scales (1.5B, 3B, 7B), we compare four matched-budget retry conditions: blind resampling, a content-free failure notice, genuine execution feedback, and feedback augmented with verbal self-reflection. Blind resampling is the strongest condition below 7B, and remains statistically tied with the best condition at 7B, while consuming 2.5-5.5x fewer tokens; conditioning on the model's own failed attempt costs 6.1 points at 1.5B (p=0.006), and the informational content of execution feedback adds nothing measurable over the placebo. We attribute this to anchoring: when shown its previous attempt, a model reproduces a near-identical program in 33-68% of retries, against 2-14% under blind resampling. Two further experiments delimit the effect. Retrieved solutions to other tasks change nothing (bounded to +/-3.5 points), which localizes the harm to self-conditioning rather than context length; and reflection, the only condition that measurably weakens the anchor, remains dominated on cost. Replication rules out two competing explanations: the penalty is unchanged at full precision, and it reproduces on an independent model family. Across six configurations spanning two families and two precisions, its magnitude is predicted by baseline quality alone (r=0.96) - the cost of anchoring is the cost of committing to a bad first attempt.
Jul 25, 2026

Wrong Design Intent Is Worse Than Never Conditioning: A Derangement-Control Diagnosis of Header Conditioning in CAD Program Completion

Fine-tuned code LLMs are routinely conditioned on a design-intent specification, but the correctness axis of such a signal -- a wrong intent rather than an absent one -- has not been tested, and the benefit of conditioning is usually scored with the same detector that defines the signal. We study CADCON, a five-feature design-intent header prepended to CadQuery-style programs during LoRA fine-tuning of Qwen2.5-Coder-1.5B, scoring adherence with executable geometric assertions that share no code with the header-defining extractor. On a pre-registered sample of 400 deduplicated held-out programs stratified over eleven intent profiles, at 40% prefix and three seeds, a semantically wrong header degrades adherence below the never-header-trained baseline on 3/3 seeds under both tokenizations at the program level, and on 3/3 token and 2/3 text seeds at the 298 distinct model inputs they present. Wrong-header executability is not depressed relative to that baseline. A derangement control, retrained so every program receives another program's header -- holding the header marginal fixed while destroying its correlation with the program -- saw the same programs, indices and wrong headers. Its correct-to-wrong change is -0.006/+0.016/-0.003 against 0.124/0.241/0.230 for the standard model, and the interaction is significant on 3/3 seeds (p <= 5.9e-7), so the model's sensitivity to whether the header is right or wrong requires the learned mapping. The control sits below the baseline by the same margin under a correct as under a wrong header, so we claim that sensitivity and not the below-baseline level. On features the true intent lacks, the standard model realizes a feature far more often when the wrong header names it; the control does not. Ground truth itself scores only 0.567 here, the scale on which arm levels should be read. Wrong design intent is not inert: it actively misdirects generation.