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.

Oct 13, 2026

Verifier-Grounded Agentic RL for Provably Correct Code

Reinforcement learning for code usually rewards passing tests, which a model can do while remaining wrong on the inputs the tests do not cover. A program verifier instead decides whether a program satisfies a formal specification for all inputs. Language models are almost always paired with verifiers at inference time only, and turning a verifier into a reward raises two difficulties. It reports only acceptance or rejection, which gives no gradient when every attempt fails, and a policy can cheat it, most simply by telling it to assume what the proof was supposed to establish. We build an agentic environment and reward that address both. The reward reads the verifier's diagnostics rather than its verdict, scoring a candidate by the weighted fraction of proof obligations it discharges, extended with hidden probes from a reference proof's annotations. An integrity audit outranks the verifier, rejecting any candidate that alters the specification or assumes what it was meant to prove. The model works as an agent against a live verifier over many turns, with a separately trained proof specialist as a frozen collaborator. Across Qwen3 models from 1.7B to 14B and a 35B Qwen3.6 mixture-of-experts model, held-out verification on code generation rises from 66.1% to 93.5% on DafnyBench and from 56.3% to 100% on SWE-Proof. This reward leads every other training signal we compare, including a binary pass-or-fail reward trained under otherwise identical settings, with the widest margin on code generation. When the agent must also deliver the repository patch, graded by each project's withheld tests, the fraction of held-out issues it resolves rises from 59.6% to 72.5%. Evaluated unchanged on three verification suites withheld from training, the checkpoints improve on all of them, including one whose language and verifier are absent from training.
Oct 13, 2026

AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards

Generating information-rich visual artifacts such as slides, posters, and dashboards as code is appealing because the outputs are structured, editable, and verifiable. Yet code models cannot see how their choices of layout and color come together on the canvas, often limiting spatial planning and aesthetic quality. Image generators excel at visual design but can misrender requested content, making their outputs unreliable targets for direct reproduction. We therefore introduce AesCode, which generates code grounded in the content prompt while using an image generated from the same prompt as an aesthetic guidance. To do so, AesCode represents the target as a design graph that describes the whole canvas and makes each property attributable. From this graph, we derive complementary cross-modal rewards: deterministic verifiers score properties parsable from code and rendering, while a VLM judge assesses the non-parsable ones with a sample-specific Visual Graph Rubric (VGR) tied to graph elements and relations. We optimize these decoupled rewards through reinforcement learning with per-channel normalization to jointly improve spatial planning, aesthetic quality, and verifiable correctness. To evaluate this setting, we build a benchmark that scores verifiable correctness and visual quality separately, with visual scores highly consistent with human judgments. We find that reference images substantially improve the visual quality of code generated by existing models, and ablations show that AesCode benefits from references both as model input and as a source of visual rewards. Relative to same-scale Qwen3-VL baselines given the same references, AesCode-8B and AesCode-32B improve visual quality by 31.1 and 22.4 percentage points, reaching scores comparable to those of closed-source frontier models such as GPT-5.5 and Claude Opus 4.8.
Oct 13, 2026

SolBehave: Evaluating the Behavioural Correctness of LLM-Generated Smart Contracts

Large language models increasingly generate Solidity smart contracts that, once deployed, can never be patched, making a single latent fault permanent and exploitable. Yet current evaluations mostly ask only whether generated code compiles. We introduce SolBehave, a benchmark for evaluating the correctness of model-generated contracts at scale, moving beyond ad hoc unit tests. Across 250 real, reproducible Ethereum contracts, we apply three complementary tests of behavioural fidelity: differential fuzzing, historical-transaction replay, and, as our core contribution, synthetic-transaction replay guided by a Dynamic Condition Response (DCR) graph that enumerates the space of legitimate function-call sequences. Differential fuzzing compares each generated function with the original on automatically generated inputs; historical replay compares the whole contract on the transactions it actually received on-chain; DCR-guided replay compares it on sequences of calls that follow its intended usage, including orderings that never occurred on-chain. We evaluate seven state-of-the-art open-weight models after one round of automated repair. Compilation success ranges from 26.4% to 92.7%, but under differential fuzzing only 31.4% of all generated function bodies that compile, pooled over models and samples, are equivalent to the original. Divergence at the contract level is the norm rather than the exception: for six of the seven models, between 13% and 31% of the generated contracts that compile diverge from the original under historical replay, and between 13% and 44% under DCR-guided replay; only Gemma-4-31B stays below 3% on both. Compilation is therefore a necessary condition for correctness and far from a sufficient one.
Oct 13, 2026

SpecCloak: Probing Harmful Code Generation through Engineering Specifications

The code generation capabilities of large language models (LLMs) can equally be misused to implement harmful functionality, underscoring the need to understand their safety behavior in response to programming requests. While request phrasing is known to influence refusal, it remains unclear whether the form in which coding task requirements are stated affects the refusal process for malicious code generation. We introduce PseudoSpec, a template that organizes functional requirements as engineering specifications, and investigate its effects through controlled comparisons, representation analysis, and activation interventions. Across five open-weight models, removing explicit risk keywords only partially reduces refusal, whereas specification prompting substantially lowers refusal even when these keywords are retained. This reduction accompanies consistent shifts toward code-output-related representations, and interventions along condition-difference directions alter refusal behavior. Output analysis further distinguishes code-related responses from generation degeneration. Building on these findings, we propose SpecCloak, a black-box red-teaming framework combining PseudoSpec with discriminator-guided optimization, achieving an average execution-verified attack success rate of 28.91% across eight target models on RedCode-Gen. We also introduce SpecReveal, a defense prototype combining natural-language intent reconstruction with dual-view detection without target-model fine-tuning. It achieves a 96.88% attack detection rate in a separate prompt-detection evaluation, with false positives assessed on benign programming and specification-style inputs. These results connect specification-induced response differences to practical security consequences and identify intent reconstruction as a complementary detection approach.
Oct 12, 2026

Deleting Code Without Losing Knowledge: Regenerative Software for Python Libraries

In the age of "Software 3.0", when a complete program can be rewritten in minutes by an agent, the traditional approach of relying on code as the sole source of truth becomes questionable. Fowler advocated for a set of seven primitives, which lay the framework for regenerative software, so that programs can be deleted and rebuilt without losing their knowledge. The knowledge lives in machine-readable records in a tracked directory, from which a regeneration bundle is built for each unit. The regeneration bundle is a single file with the module's architecture, intent, decisions, public contract, evaluations, and consumers, but no implementation, plus the one dependency module it may import. The open-source package spotregen implements these primitives and provides a graphical user interface. This report presents a first application of Fowler's primitives to the safety-critical forecasting library spotforecast2-safe. During the first experiments, the Claude Code session that orchestrated the study consumed more than 43 million tokens, almost all of them its own history re-sent with every request. This motivated the switch to an architecture that is built on local models. Deterministic checks and the maintainer judged the results. The report contains executable examples for every primitive. Each example runs spotregen against the repository or against a throw-away copy of it.
Oct 12, 2026

EvoWeb: A Benchmark for Coding Agents on Evolving Web Applications

Web application development often proceeds through successive requests that extend an existing implementation. Yet web-generation benchmarks primarily evaluate development toward fixed specifications. We introduce EvoWeb, a novel benchmark comprising 320 cumulative requests over 32 web applications, grounded in real-world product features and structured by functional dependency graphs. Agents iteratively modify a persistent codebase, while a multimodal web agent tests each intermediate application in a live browser, assessing newly requested functionality, cross-request integration, and previously requested functionality. To characterize reliability throughout development, we integrate trajectory performance across user-tolerance thresholds rather than impose a fixed stopping criterion. Experiments across open- and closed-source frontier models show that EvoWeb reveals clear performance differences between models, with cross-request integration emerging as a key challenge. Further analysis shows that later requests with deeper or more numerous dependencies are solved less accurately, while runtime errors become more frequent over successive requests. EvoWeb provides a testbed for evaluating and improving coding agents in long-horizon, multi-request development.
Oct 11, 2026

Passing Tests, Missing Semantics: Evidence of Interpretive Lock-In in Plan-Based DataFrame Code Generation

Planning and revision are intended to bring generated code closer to the task specification. Yet a mistaken interpretation can persist across the plan, implementation, and tests - a pattern we call interpretive lock-in. We investigate this risk on 30 DataFrame tasks derived from TPC Benchmark DS, comparing Frozen One-Pass, Test-Guided Revision, and PlanAudit-Guided Revision. Test-pass counts rose from 22/30 to 29/30 and 30/30, yet no generated solution matched its stored reference output. Evaluator controls returned the expected outcome in 57/57 cases. Same-engine SQL re-execution reproduced 28/30 references; all 77 test-passing runs on these tasks still failed reference agreement. PlanAudit-Guided Revision improved code scores on 3/30 tasks and test coverage on 11/30, but the median paired change was zero for both measures. Failure analysis revealed tests that omitted requirements, adopted candidate-defined schemas, used nondiscriminating fixtures, or repeated the implementation's incorrect logic. Fresh generation on ten targeted tasks produced 0/30 reference matches and 25/25 false passes among test-passing runs. These findings are diagnostic rather than causal: the pipelines differ in feedback, grounding, call budgets, and editing permissions, and the study uses one model and one primary generation per eligible task. Because pre-adjudication human labels were not retained, inter-rater agreement cannot be reconstructed and the mechanism analyses remain exploratory. Overall, increasingly successful self-generated tests did not establish semantic correctness, even after excluding unreproduced references.
Oct 8, 2026

Conditional Transfer from Controlled Pretraining Mixtures to Code

Synthetic tasks are increasingly used both as probes of language-model capability and as pretraining data. Both uses are often justified by loss reduction: falling loss is treated as informative, and faster loss reduction with more sampling as evidence that a task is worth sampling. We separate three signals. A task is diagnostic when its loss tracks global pretraining progress; it is teachable when its loss responds to its own token budget; and a data source transfers when including it improves a downstream target. We study controlled pretraining in which 70% of the corpus is fixed general Python and the remaining 30% is a simplex over three source families: OpenCodeInstruct, a curated suite of 12 code-adjacent synthetic tasks, and 15 literature-derived probe tasks. Across a task-budget sweep we detect teachability for 14 of 27 tasks, with a sharp asymmetry between the two synthetic families (10/12 curated versus 4/15 literature-derived). Teachability and downstream transfer give different rankings. On the mixture-simplex edge between the curated suite and OpenCodeInstruct, HumanEval pass@20 after a fixed fine-tuning stage rises from 15.9 at pure curated data to its highest observed value, 22.6, at a mixture that is 75% OpenCodeInstruct, then falls to 19.5 at pure OpenCodeInstruct. Curated synthetic data therefore has conditional value: it contributes as a limited share of a mixture that a target-aligned source still dominates. Finally, a loss-based adaptive scheduler exposes the mismatch between residual loss reducibility and downstream transfer. Across three 60k-step free-ratio runs, Ado drives the OpenCodeInstruct share below 5% within the first 5k steps and to 1.2--1.4% by the end of training, and underperforms its matched fixed-mixture controls by 2.4--11.0 percentage points. Optimizing near-term task-loss reduction moves the mixture away from the region that transfers.
Oct 7, 2026

TaoD2C-Bench: Benchmarking MLLMs for Industrial UI Code Generation Beyond Visual Fidelity

A key challenge for multimodal large language models (MLLMs) is moving beyond visual recognition to constraint-aware cross-modal reasoning. This involves combining visual cues with information from other modalities to understand elements' relationships under domain-specific rules. This challenge is acutely evident in industrial design-to-code (D2C), which converts user interface (UI) designs into code and requires MLLMs to connect design images with disorganized layer metadata, infer component and layout implementation requirements, and realize them in code under target-library constraints. However, these capabilities remain insufficiently evaluated in realistic industrial settings. To fill this gap, we present TaoD2C-Bench, a benchmark for evaluating MLLMs' ability to generate UI code that satisfies implementation requirements in industrial applications. The TaoD2C dataset consists of 2,861 production designs from 17 commercial platforms with 97,652 expert annotations across four categories: Component, Group, Alignment, and Position. These annotations distinguish required constraints from permitted implementation choices. TaoD2C-Bench defines three tasks: end-to-end UI code generation, requirement inference, and requirement realization. Evaluating eight MLLMs reveals substantial gaps in generating UI code that satisfies implementation requirements, alongside distinct performance profiles in inference and realization. We further show that MLLMs' visual reconstruction ability does not necessarily imply an ability to generate code that meets these requirements. We release TaoD2C to support research on industrial UI code generation.
Oct 7, 2026

Visible Reasoning Is Not a Universal Optimizer: Persona- and Thinking-Dependent Effects in Analytics Code Generation

Visible Chain-of-Thought (CoT) is often treated as a broadly useful reasoning instruction, yet analytics code generation combines natural-language ambiguity, schema grounding, target-language constraints, and model-specific inference behavior. Because the same analytics request can be expressed in two distinct target languages-SQL and Python (pandas)-this setting provides a natural test of a common but under-examined assumption: that visible reasoning is more effective when its representation matches the requested target, as in "think in SQL" or "think in Python." Together with generic instructions such as "think step-by-step," such recommendations remain insufficiently evaluated under controlled, execution-based comparisons. We study a query matched SQL-pandas benchmark that crosses persona phrasing, target language, visible-CoT format, control prefixes, direct generation, and internal-reasoning configurations. The results do not support either a universal accuracy advantage from visible CoT or a consistent benefit from matching the reasoning representation to the target language. Instead, the effects depend on the persona, target, model configuration, and internal-reasoning setting. The control ablations further distinguish effects of reasoning content from those of prompt format. These findings indicate that reasoning strategies should be selected jointly for the model, persona, target, and internal-reasoning configuration rather than adopted as universal defaults. More broadly, the study provides a controlled framework for identifying when visible reasoning improves executable generation, when it primarily perturbs model behavior, and when the internal-reasoning configuration is the more consequential factor.
Oct 7, 2026

From Pixel to Coding: Evaluating the Figure Reproduction Capabilities of MLLMs

Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in both visual understanding and code generation. However, existing benchmarks typically evaluate these two modalities in isolation, lacking a dedicated assessment of their unification, i.e., how a model can perceive complex visual structures and synthesize them into precise, executable code. Moreover, current visual code generation benchmarks often rely on simplified layouts within single programming environments, falling short of evaluating true unified multimodal reasoning. To bridge this gap, we propose FigCodeBench, a comprehensive framework for rigorously evaluating MLLMs on figure reproduction, integrating multimodal comprehension and generation. We first design a systematic dataset construction pipeline, resulting in a total of 6,194 instances that cover 7 functional categories and 4 types of programming languages. We further categorize figure reproduction into three tiers with visual and code complexity modeling, specifically targeting complex structural reasoning, varying aspect ratios, and dense geometric constraints. We introduce a multi-dimensional evaluation protocol, encompassing visual fidelity and syntactic isomorphism, that aligns highly with the Mean Machine Opinion Score (MMOS) and human preferences. Based on our framework, we conducted extensive experiments on 24 widely used proprietary and open-source MLLMs (e.g., Gemini 3.1 Pro, GPT-5.4, and Kimi-K2.5), where we observed a universal, non-linear performance cliff across different programming languages and difficulty scenarios for all models, and gained several insights, such as the significant metric decline in rigid declarative languages.
Oct 7, 2026

Adaptive Code Generation for Controlling Robots

Deploying robots as Complex Adaptive Systems (CAS) in unknown and dynamic environments necessitates a transition from rigid command libraries toward intention-based autonomy, as natural language represents the only medium capable of articulating complex goals beyond the capacity of finite instruction sets. While Large Language Models (LLMs) offer a path toward natural language goal description, their integration introduces significant challenges: the formalization gap between imprecise intentions and executable actions, the taxonomy gap induced by unpredictable environments, and the challenge of maintaining temporal state and progress awareness. This work introduces an architectural framework that enables robotic control by leveraging generative AI. The system follows a dual-AI design: an LLM translates high-level intentions into executable program code restricted to a formal robotic library and constrained by verifiable syntax, while a Vision-Language Model (VLM) provides semantic grounding via a distillation process. To ensure robustness, the framework incorporates environment-driven replanning triggers based on geometric and semantic thresholds, complemented by continuous runtime monitoring and an adaptive planning loop. Benchmarked across frontier models, our framework architecture demonstrates that grounding generative AI in a reactive, constrained loop enables robust fulfillment of complex intentions in dynamic and unknown environments.
Oct 6, 2026

SPLATIFY: Reproduce, Discover, Innovate! From Papers and Ideas to Trainable 3DGS Code

The rapid growth of 3D Gaussian Splatting (3DGS) research demands significant effort to reimplement papers before building on them. We introduce SPLATIFY, a multi-agent framework that converts 3DGS papers into trainable gsplat-based implementations, where generic paper-to-code methods and frontier models fail. SPLATIFY achieves this through five innovations: (1) A context-free grammar for gsplat over a modular method template with extension points for losses, densification, rendering, and optimization, constraining synthesis so generated code satisfies gsplat's architectural invariants by construction. (2) Architectural elements for faithful reproduction: fork-aware citation recovery retrieving component-level code at function-level granularity, Graph-of-Thought synthesis in topological dependency order, RAG-guided in-context example selection from over 20 verified implementations, and visual feedback combining PSNR-guided regeneration, Gaussian-level structural checks, and VLM-driven patching. (3) Knowledge-driven compositional improvement that autonomously finds weaknesses and composes complementary regularizers, losses, and densification strategies to improve upon original results. (4) Interdisciplinary method discovery where agents retrieve physical priors from outside the 3DGS literature and compose them with rendering knowledge to produce methods for previously unaddressed scene types. (5) SPLATIFY-Bench, an evaluation framework across 30 diverse 3DGS papers. On papers without public code, SPLATIFY matches expert implementations while reducing development time from weeks to minutes, and through compositional discovery further improves PSNR by up to 2.4 dB. We additionally demonstrate novel methods for volumetric nebula rendering and other scientific domains, synthesized entirely by SPLATIFY.
Oct 6, 2026

WorldSolver: Can LLM Agents Simulate the Physical Dynamics via Solver Generation?

LLM-based agents are increasingly advancing scientific and engineering problem solving, with physics simulation emerging as a challenging yet practical testbed for reproducing complex physical phenomena with application in embodied AI, games and films. As the workhorse of such simulation, a solver computes how the state of a dynamic system evolves over time. Building such solvers requires physical understanding to identify appropriate models, mathematical reasoning to formulate the underlying dynamics, and software engineering to implement them as executable code, yet this capability of LLM agents remains underexplored. To this end, we introduce WorldSolver, a benchmark of 168 simulation tasks derived from physical phenomena in 61 classic computer graphics papers, spanning 7 physical domains. Each task contains a code scaffold that provides a fixed simulation environment for the scene, with the solver implementation left for the agent to complete. Specifically, we evaluate them along three dimensions: Execution Checks for successful execution, Visual Fidelity for reproducing the intended dynamic behavior in the rendered simulation, and Physical Plausibility for physics-grounded verification of the generated dynamics. Experiments on frontier agents reveal that producing executable solvers is difficult itself, and satisfying visual and physical correctness is even harder. GPT-5.6-Sol and Claude-Opus-5 perform comparatively better than the other evaluated agents, yet achieve overall scores of only 48.7% and 46.7%, respectively. WorldSolver is an early step toward agentic solver generation, and we hope it helps drive progress toward agents that can faithfully simulate the dynamic physical world. Code is available at https://github.com/sirujiang/WorldSolver.
Oct 5, 2026

SPECTRUM: Proximal Spectral Modulation for Looped Self-Distillation

A model that learns from its own outputs inherits more than their correctness: it inherits which solutions it produces. We formulate Looped Self-Distillation, a self-evolution framework for code generation in which a model repeatedly generates and learns from its own raw outputs, under a fixed information budget, without ongoing external assessment or test-based selection of the generated samples. We identify a consequential separation: correctness can improve while the breadth of correct implementations contracts. We introduce SPECTRUM, which re-estimates loss-sensitive key/value geometry from a fixed reference anchor at each round and converts it into full-rank proximal spectral modulation. All generated completions train a single student, whose subsequent inference requires no intervention. After five rounds of experiments on MBPP, SPECTRUM retains 89.9% of the initial model's 64-sample correct AST richness, compared with 66.4% for Vanilla self-distillation and 65.5% for a subspace-projection control. The advantage persists at matched correct-sample counts. Without further training or recalibration, the resulting student also achieves higher matched-correct richness than Vanilla SD on HumanEval+ and APPS Intro, demonstrating transfer of the diversity benefit. These findings establish correct-solution retention as a complementary objective of recursive self-improvement (RSI) and show that generation-time intervention can improve the solution repertoire retained by subsequent students.
Oct 4, 2026

VHDL-REPOBENCH: A Repository-Level Benchmark for Evaluating Large Language Models on VHDL Design Generation

Large Language Models (LLMs) are increasingly applied in hardware design automation, demonstrating strong potential in generating and understanding hardware description languages. However, most existing benchmarks focus on Verilog, with limited evaluation of VHDL, which remains widely used in industry and academia for FPGA and safety-critical systems. To address this gap, we introduce VHDL-REPOBENCH, a large-scale, cross-file, repository-level benchmark for assessing LLM capabilities on realistic VHDL design generation and analysis tasks. VHDL-REPOBENCH curates ~100 open-source VHDL repositories, encompassing ~2.5k VHDL files and ~500 testbenches, and provides structured problem statements, module stubs, and self-verifying testbenches. The benchmark enables comprehensive evaluation across syntax, semantic correctness, hierarchical reasoning, cross-file dependency resolution, and functional verification. We evaluate several state-of-the-art models, including GPT-4o, Llama-3-70B, Qwen2.5-72B, CodeLlama-70B, and multi-step reasoning approaches such as Reflexion and CoDes. Results reveal that while current LLMs achieve moderate line- and block-level accuracy, substantial challenges remain in multi-file reasoning, hierarchical design understanding, and specification-to-module generation. VHDL-REPOBENCH represents the first large-scale VHDL-focused benchmark and provides a valuable resource for the hardware design community to evaluate, compare, and advance LLM capabilities for practical VHDL development.
Oct 3, 2026

Spec2Game: Can LLMs Generate Complete Playable Games from Detailed Specifications?

Generating an executable program does not necessarily mean that it correctly implements the behavioral requirements specified in natural language. To evaluate large language models' ability to realize detailed specifications as complete interactive programs, we introduce Spec2Game, a benchmark that requires models to generate complete Pygame projects from detailed natural-language game specifications. Spec2Game comprises 15 game families and 150 task instances, with one canonical task and nine controlled rule variants per family, spanning three levels of implementation complexity. Using source-code, runtime, and visual evidence, we evaluate generated projects along four dimensions---Executability, Specification Realization, Code Quality, and User-Facing Quality. Across 14 LLMs and 3,330 generated projects, we find that high executability does not imply faithful specification realization. Component-level analysis further shows that models perform substantially better on Game Element Modeling than on Rule and Mechanism Modeling or Goal and Termination Modeling, indicating that faithfully implementing game rules and termination logic remains a major challenge.
Oct 2, 2026

MintEval: Do LLMs Implement the Trading Strategy You Asked For? A Behavioural-Equivalence Benchmark for Natural-Language-to-Strategy Code

Large language models are moving from producing trading signals to writing the code that executes them. The failure mode of the second role is silent: generated code runs, a backtest plots, yet the risk logic that the trader described is not the logic being executed. Existing code benchmarks test functional correctness on unit tests and finance benchmarks test forecasting; neither measures whether an implementation behaves like the strategy that was asked for. We introduce MintEval, a benchmark in which reference strategies are generated programmatically from a library of composable building blocks, back-translated into colloquial trader instructions, and re-implemented by the model under test. Generated and reference programs are executed bar by bar on identical market data and frictions, and compared on their actions rather than on code similarity or profit: alpha is differenced away. MintEval v0 contains 800 tasks on BTCUSDT 15-minute data, stratified by an execution-measured state-span complexity tau that is decoupled from description length. Low-cost models reach a mean ActionMatch of at most 0.544 and reproduce at most 0.087 of tasks exactly; on a stratified subset of 200 tasks a frontier model (Claude Opus 5.5) reaches 0.889 and reproduces 0.575 exactly, yet still fails silently on 0.275 of tasks. Given a menu of building blocks, models identify the strategy almost perfectly, yet 79.2% of the implementations whose specification was read correctly diverge on more than 10% of active bars. The LLM judge of a recent strategy-generation benchmark, applied verbatim, accepts every one of these silent failures.
Oct 2, 2026

PLCWorld: Benchmarking LLM-Generated PLC Programs in Closed-Loop Plant Simulation

Programmable logic controllers (PLCs) coordinate industrial equipment by reading sensor inputs and issuing control commands. Evaluating whether large language model (LLM)-generated PLC programs satisfy task requirements and safety constraints requires observing how their commands affect device and workpiece states. We introduce PLCWorld, a common closed-loop execution environment and benchmark that couples Structured Text (ST) execution with simulated plant responses and sensor feedback. Grounded in control relations identified in industrial PLC programs and engineering documentation, PLCWorld contains 100 synthetic tasks and 473 registered task-condition pairs across Motion Control and Material Handling, with difficulty defined by control-dependency scope. A common protocol reports Task Success and Safety Violation separately. Validation combines practitioner review, reference and alternative programs, targeted counterexamples, specification-evaluator alignment checks, and comparisons with independent ST runtimes. Reference and alternative programs satisfy their applicable cases, while all 542 targeted counterexamples activate their designated evaluator rules under at least one registered condition. Execution Gap relates submission-profile acceptance to subsequent task failure or observed Safety Violation. Across the constructed task groups, direct GPT-5.5 achieves 82.70% Task Success on Easy cases but 25.10% on Hard cases. Evaluations of six LLMs and four adapted generation-and-verification workflows further expose differences between completion, safety, and generation cost. Our code, simulation environment, benchmark tasks, and baseline implementations are publicly available at https://yunji0516.github.io/PLCWorld/.
Oct 2, 2026

WebUIProof: Benchmarking WebUI Code Generators with UI-Agent Execution Harness

Evaluating WebUI code generation at scale is difficult: outputs may compile and look plausible yet fail under user interaction, and prior benchmarks largely rely on free-form prompts with static checks (build success, screenshots) that miss functional correctness. We introduce WebUIProof, an execution-oriented benchmark that provides structured specifications and dense, executable interaction tests for WebUI generation across two task families: general WebUIs (e.g., dashboards, game, interactive tools) and 3D interactive simulation (e.g., particle/galaxy systems, physics dynamics). WebUIProof includes a UI-agent harness that runs executable interaction tests in a headless browser using an iterative plan--act--observe loop: it locates DOM elements, performs actions, observes resulting UI/DOM changes, and checks the specified assertions. We evaluate across eight commercial LLMs and observe frequent failures on interaction-based requirements even when pages render successfully, especially on 3D simulation interfaces. Finally, we show the UI-agent harness can provide outcome-level training signals. Training compact models (e.g., Qwen2.5 14B and MIMO 7B) with RL rewards derived from executable interaction tests improves functional completion while reducing build failures.
Oct 1, 2026

Improving the Energy-Efficiency of the Code Generated by LLMs through Effective Prompting

As AI-assisted programming becomes increasingly mainstream, the environmental impact of AI-generated software has emerged as an important consideration. This motivates evaluating LLM-generated code beyond functional correctness by considering execution efficiency and energy consumption. However, despite substantial advances in code generation, frontier LLMs are rarely evaluated based on the energy efficiency of the code they produce. In this work, we conduct a comprehensive evaluation of 21 prompting strategies for energy-efficient code generation and identify 8 strategies for evaluation across 10 widely used open-weight and proprietary LLMs. We evaluate their effectiveness for both Python and C++ code generation relative to a baseline prompt. Across the evaluated models, the selected prompting strategies achieved energy reductions of up to 25% for Python and 17% for C++ code generation. At the model level, Python energy reductions reached up to 50% for Granite-4.0-H-Small, 39% for Claude 4.5 Haiku, and 28% for MiniMax M3, while C++ reductions reached up to 57% for Granite-4.0-H-Small and 6.4% for Qwen3-Coder-480B-A35B-Instruct. These results demonstrate that prompting strategies can substantially influence the energy consumption of LLM-generated code, although their effectiveness varies across models and programming languages. Our findings highlight the importance of incorporating energy efficiency into the evaluation and optimization of LLM-based code generation and provide practical insights into designing prompts for more sustainable AI-assisted programming.
Oct 1, 2026

CONTRA: Discovering and Qualifying Behavior-Changing Questions for Selective Clarification in LLM Code Generation

Coding agents can generate code that appears correct but implements behavior the user never intended. This mismatch can arise when an agent silently resolves underspecified requirements through its own assumptions. As subsequent development builds on these assumptions, correcting the resulting behavior can become increasingly costly. Early clarification can help prevent such mismatches, but unnecessary questions can interrupt developers and slow down development. Existing methods struggle to identify key clarification questions while avoiding unnecessary ones. Therefore, we propose CONTRA, a training-free method that combines broad question discovery with semantic and execution-based question qualification. CONTRA first generates candidate questions and filters out those unrelated to required behavior or already resolved by the requirement. For each remaining question, it generates programs conditioned on two plausible answers and checks for stable behavioral differences on shared inputs. It then uses the interaction history to select among qualified questions or stop asking. Experiments on ClarifyCodeBench show that CONTRA achieves the highest F1 with all four coding agents, exceeding the best baseline macro-average F1 by 13.88 percentage points. With the same LLM and evaluation protocol, CONTRA also achieves higher clarification recall and F1 than the coding harnesses Claude Code and OpenHands. To support practical use, we also implement CONTRA as a Claude Code plugin that integrates selective clarification into everyday development.
Sep 30, 2026

Code That Works, Environments That Don't: Measuring Environment Reproducibility in AI-Generated Software

Code generation has emerged as a central capability of large language models, with coding agents now able to produce functionally correct software projects from natural language prompts. However, functional correctness alone does not capture a critical dimension of generation quality: environment specification, defined as the accurate identification of the dependencies required to execute generated code, is equally critical. We develop an agent protocol for environment specification and introduce a three-layer framework comprising declared, runtime-installed, and necessary-and-sufficient dependencies to systematically assess coding agents for environment specification. Using this protocol, we evaluate the extent to which coding agents systematically misspecify software environment dependencies and how this misspecification varies across three agents, four languages, and fifty programming tasks. Our results show that current coding agents exhibit systematic generalization failures along this dimension, producing dependency specifications that are inconsistent, redundant, or incomplete in ways that functional tests do not detect. Across agents, dependency set agreement is as low as 7% for identical tasks, and newer agents show no meaningful improvement, suggesting the failure is not resolved by scale or recency. The largest divergence occurs between the declared and runtime dependency layers, implicating environment priors learned from the models' training distributions as the primary driver. Our findings establish environment specification as a distinct, measurable axis of code generation quality that current benchmarks do not capture, and motivate training objectives and evaluation protocols that jointly optimize for functional correctness and environmental portability.
Sep 30, 2026

Self-Spec Verifiable Code Generation

Large language models (LLMs) may generate unreliable code on corner cases missed by testing, while formal verification can provide machine-checkable guarantees. Recently, researchers have proposed several benchmarks to evaluate the capabilities of LLMs in generating formally verifiable code, where LLMs need to formulate formal specifications, generate the corresponding code, and verify its correctness. However, existing benchmarks have two key limitations: (I) They primarily evaluate specification and code generation stage-wise, with code generation typically conditioned on an oracle specification. This setup overlooks whether strong stage-wise performance translates into end-to-end success. (II)They mainly focus on a single proof-oriented language and mathematically structured tasks, offering limited coverage of tasks common in software development. In this paper, we introduce VeriCodeBench, a benchmark for self-spec verifiable code generation, where the LLM relies solely on its own generated specification and code throughout the entire process. VeriCodeBench contains 400 language-native problems across C, Java, Rust, and Python, covering practical concerns in software development. We evaluate specification coverage, code validity, and joint problem-level success. We further introduce CodeNova to enhance the capabilities of LLMs in self-spec verifiable code generation. CodeNova makes requirements explicit through constraint-guided specification and uses verifier feedback to guide targeted implementation repairs. Experimental results reveal that self-generated specifications remain a major bottleneck, while providing more sophisticated specifications may not necessarily lead to higher verification success rates. CodeNova substantially improves performance across all evaluation metrics, enabling Claude Sonnet 5 to achieve the strongest results under the self-spec protocol.
Sep 30, 2026

QuantCode Model: Specializing Language Models for Executable Algorithmic Trading Code

Large language models are strong general-purpose code generators, but executable algorithmic trading remains a demanding specialization target: a model must translate a natural-language strategy specification into correct program logic for a specialized trading framework, execute on historical data, produce trades, and remain semantically faithful to the request. We study two complementary mechanisms for specializing language models for this setting: continued pretraining on algorithmic-trading framework code and supervised fine-tuning (SFT) on agent-validated request-to-code pairs. Evaluation is centered on QuantCode-Bench, our 400-task benchmark for Backtrader strategy generation, together with a repository-level SWE-bench-like track. Continued pretraining improves single-turn Judge Pass from 41.5% to 47.5% for Qwen3.5-397B-A17B and from 27.8% to 33.0% for Qwen3.6-35B-A3B. SFT applied after continued pretraining yields a larger gain for Qwen3.6-35B-A3B, reaching 58.2% Judge Pass and 83.5% successful backtests; in agentic evaluation it raises first-turn success from 22.3% to 58.3% and final success after up to 10 turns from 47.5% to 79.5%. Continued pretraining alone improves first-turn agentic success but lowers final success after repair from 47.5% to 32.5%, consistent with degraded instruction following, whereas SFT improves both. We also identify a capability-retention failure: domain specialization degrades parser-conformant structured tool calling, and targeted recovery SFT restores tool-call formatting but not the base checkpoint's repository-level agent performance. The results show that framework-oriented pretraining, validated SFT, and explicit capability-retention evaluation address distinct failure modes in domain-specific executable code generation.
Sep 30, 2026

From Verification Failures to Reusable Guidance for Coding Agents

Coding agents need to establish that a program satisfies a specification and that the specification captures the requested behavior. We study how expert diagnosis of verification failures can become reusable guidance for this work. Our approach combines executable language definitions in the K framework with a kit of procedures for constructing specifications, repairing proofs, and auditing their adequacy. A human-guided development campaign on HumanEval, a benchmark of 164 Python programming tasks, achieves a 164/164 success rate with the semantics and the kit, measured by final AI audit Pass verdicts after two targeted repairs. To examine whether auditing detects problems that successful proofs leave unresolved, we construct 12 author-reviewed pairs of clean and defective packages. Every package passes its K proofs, and completed audits identify all defects and accept all clean packages. We then use KleverBench to test specification and proof construction for 31 programs with changed operator meanings. Comparisons with complete acceptance rules and equally long generic advice yield mixed results across two model and budget settings, motivating further work on selecting useful guidance within resource limits. Human-reviewed Optimism proofs establish expected pause reverts for six operations within declared input bounds under London semantics with unbounded gas. We report progress, difficulties, and lessons toward agents that deliver programs with checkable correctness arguments.
Sep 28, 2026

Reasoning with Continuous Latent Diffusion

We introduce the Continuous Embedding Diffusion Reasoner (CEDR), a training and inference pipeline for continuous latent diffusion models that achieves strong performance on mathematical reasoning and code generation. We learn compact answer representations from three hidden layers of the autoregressive Qwen3-4B model. A staged curriculum first trains the ELF-based diffusion backbone with teacher prompt conditioning, then initializes a compact prompt encoder through imitation and jointly adapts both networks. This replaces the large teacher contextual prompt encoder at inference with a compact learned Transformer. The multilayer answer representation also enables asynchronous inference, with different components denoised under separate clocks. We further adapt DiffusionNFT to learned self-conditioning guidance, enabling reinforcement learning with verifiable rewards. Controlled ablations evaluate the effects of representation design, prompt training, and denoising schedules. CEDR outperforms recent continuous-diffusion baselines at comparable backbone scales, including before reinforcement learning. With a 638M-parameter denoising backbone and DMD2-style stochastic sampling, post-NFT CEDR-L achieves {pass@1, pass@8} accuracies of {68.97%, 80.82%} on GSM8K and {32.40%, 53.80%} on MATH500 at 64 denoising steps per sample, and {37.56%, 51.00%} on HumanEval+ and {26.96%, 39.92%} on MBPP+ at 128 steps per sample. Code and model weights are available at https://github.com/chengxiang/CEDR and https://huggingface.co/xc91/CEDR, respectively.
Sep 28, 2026

Do Coding Agents Reuse Existing Code or Reinvent the Wheel?

Coding agents are increasingly deployed for iterative development on real repositories, yet existing evaluation barely answers a basic question: do coding agents reuse existing code or reinvent the wheel? The question matters: every duplicated implementation is a fix applied twice and agents produce code far faster than humans can audit, so redundancy accumulates unsupervised. Thus, we present RepoReuse, a multi-turn benchmark for auditing code reuse in real repositories, where requirements are revealed turn by turn and the workspace accumulates across turns. It is built by a fully automated pipeline combining AST-based dependency graphs, guided evidence collection, and execution-verified task synthesis, and scales readily to new repositories. Beyond pass rates, we measure the reuse rate together with recall and cross-turn structural redundancy. An audit over 3{,}000 turns shows that agents progressively stop exploring relevant repository code, reuse their own history less even when it is fully in the workspace, and leave duplicated logic in 50.8% of task chains by turn~5---all while pass rates barely move. Such deficiencies are invisible to pass rates, underscoring the need to evaluate code generation beyond functional correctness.
Sep 28, 2026

Reinforcement Learning from Intermediate Renders for Image-to-Code Generation

Reinforcement learning is increasingly used to post-train vision-language models for image-to-code generation, such as generating SVG code from a reference image, by optimizing rewards computed from the final rendered output. However, relying on a single terminal reward provides sparse feedback that is poorly aligned with the contribution of individual tokens. A generated program may contain operations that accurately reproduce some parts of the target image alongside others that introduce errors, yet all tokens are trained from the same final outcome. We observe that many intermediate code prefixes are not only executable, but already produce meaningful partial renders that reflect progress toward the target. This property provides a natural source of denser supervision during generation. Based on this observation, we introduce IR4RL, an RL framework with a token-level render-progress reward that turns changes between intermediate renders into localized feedback for the generated sequence. We evaluate our approach on Image-to-SVG and Image-to-TikZ generation. Across both tasks, our method improves over supervised fine-tuning and standard GRPO, yielding new state-of-the-art open-source models. This shows that intermediate rendering provides a simple and effective source of process supervision for RL post-training of image-to-code models.
Sep 26, 2026

Noisy Test-Time Reinforcement Learning for Code LLMs

Large language models (LLMs) have demonstrated remarkable performance across various code-related tasks. However, unlike carefully curated datasets that are typically high-quality and error-free, real-world user instructions are often vague and error-prone, posing significant challenges to the robustness of code LLMs. Furthermore, robustness-oriented fine-tuning relies on paired clean-noisy samples, which are costly to curate and require sophisticated noisy simulation techniques. To address these challenges, we propose the Noisy Test-time Reinforcement Learning framework (NTRL-Code), which enables robust self-evolution of code LLMs using only unlabeled noisy data during the testing stage. Specifically, NTRL-Code uses conservative self-denoising to obtain a cleaner semantic anchor for target estimation, and employs an abstract-syntax-tree (AST)-based structural aggregation mechanism to estimate a proxy target from multiple candidate programs. The policy is then optimized on the original noisy prompts with a hybrid reward that combines format validity, code similarity, and anti-repetition signals. Extensive experiments on three benchmarks, each incorporating character-level, word-level, and paragraph-level perturbations, demonstrate that NTRL-Code yields robust and consistent improvements, stabilizing the predictions of various base models. Our code is available at https://github.com/Xikai97/NTRL-Code.