Automated Code Generation

Scientific code repositories encode decades of human knowledge in executable models, methods, and tools. Yet fragmented toolchains, implicit domain conventions, and specialized correctness criteria make this knowledge difficult to convert into reliable learning experience-a challenge we call the scientific experience bottleneck. We introduce ScienceIDE, infrastructure for turning the world's scientific code into programmable environments for scientific agents. Guided by expert-defined scientific cases and acceptance criteria, agents transform repositories into executable environments that support task generation, execution, and scientific verification. These environments provide a shared foundation for supervised fine-tuning, reinforcement learning, and evaluation. Using verified interaction trajectories, we train PhAI-IDE-72B, PhAI-IDE-9B, and PhAI-IDE-4B. The model family shows gains in held-out scientific-code repair and across selected general-purpose benchmarks in code, reasoning, and knowledge, providing evidence of positive transfer from scientific experience to broader capabilities. ScienceIDE lays the foundation for an integrated workspace for agent learning and scientific practice, making humanity's scientific software a shared substrate for developing scientific intelligence. Code: https://github.com/aitofound/ScienceIDE

Coding agents are typically evaluated with desired behavior specified through issues or instructions. In practical web development, however, agents may need to infer behavior from working software and implement it in an incomplete application. We introduce ProgramDistill, a benchmark evaluating coding agents on features discovered through interaction with fully functional reference applications. We build ProgramDistill by factorizing applications into features of different granularities, each associated with replayable behaviors executable via its gold patch. Our pipeline, mine-craft-patch, discovers 1,975 replay-verified behaviors across 26 applications and constructs 4,063 tasks without human intervention. Across nine frontier coding agents, GPT-6 Astra and Claude Opus 5 achieve 49.2% and 28.8% success on cumulative workflows in full-application reconstruction. In partial-application reconstruction, success falls from 100% to 64.0% and from 96% to 32% as restoration depth increases from 1 to 8. ProgramDistill thus provides a scalable benchmark with controlled difficulty for evaluating and diagnosing coding agents, and a natural basis for future curriculum-based training.

This study empirically evaluates whether cost-efficient Large Language Models (LLMs) can be trusted to generate enterprise code to a written specification. Three models (Gemini Flash 3, GPT-5.4 mini and Claude Haiku 4.5) were asked to solve 992 algorithmic problems as Java Spring Boot service methods conforming to a mandated signature and data-transfer-object specification, crossing four model and agentic coding tool combinations with two prompt variants to yield eight configurations, with iteration forbidden and hardcoded answers explicitly prohibited. Eight problem statements were withheld to probe how models respond to missing input. The 7,593 resulting methods were classified by an eight-class outcome taxonomy describing what each does about producing an answer, then deployed and executed, giving 7,936 measured requests joined to that classification. Structural conformance approached ceiling, yet 38.4% of methods do not compute the value they returned and only 12.9% of returned answers were correct. Conditioning on outcome class shows that response reliability and correctness are inversely related, whereas genuinely computing methods answered least often and were correct 19.3%. Limitations include single generation runs per configuration, partial harness coverage, single-pass timing, syntactic classification, and probable corpus contamination.

Thompson's "Reflections on Trusting Trust" showed that a compiler can be poisoned to reinsert its own backdoor, so that even recompiling clean source reproduces the Trojan. Today, substantial coding work is done by AI coding agents -- and increasingly, those agents generate new versions of themselves. We reconsider Thompson's attack when the "compiler" is a self-modifying coding agent. Can an adversary supply poisoned benchmarks to the agent's self-evaluation and self-improvement process to induce future versions of the agent to write vulnerable code on clean, held-out tasks? We instantiate this attack against three recently proposed self-modifying coding agents: the Darwin Gödel Machine (with our experimental modifications), the Self-Improving Coding Agent, and Hyperagents (both substantively unmodified). We demonstrate successful proofs-of-concept: for example, with Hyperagents powered by Sonnet 4.5, our poisoned benchmark leads the agent to self-evolve instructions that disable HTTPS certificate validation on neutral URL-fetching tasks. From our experiments, we distill properties of the vulnerability, benchmark, model, and agent scaffolding that are sufficient to enable a benchmark poisoning attack. Moreover, we show that contamination often persists even when a poisoned agent is subsequently evolved against clean benchmarks. We discuss defensive directions and argue that self-modifying coding agents must be designed to be more resilient to such attacks.

Software clones are fragments of code that are similar or functionally equivalent to each other. They pose significant challenges for maintenance, refactoring, and bug detection. Detecting Type-IV clones, which are semantically equivalent but may differ syntactically, is particularly difficult for traditional token- or syntax-based methods. Recent machine learning approaches rely on contrastive learning, which requires careful negative sampling and can introduce bias. In this paper, we propose LWVIC4Code, a non-contrastive representation learning approach specifically designed for Type-IV clone detection. Building on the Variance-Invariance-Covariance Regularization (VICReg) framework and prior layer-wise VICReg training, LWVIC4Code introduces cross-layer consistency regularization and depth-dependent layer weighting to progressively refine semantic information across transformer layers, producing robust and discriminative code representations. We conduct an empirical study comparing LWVIC4Code against a contrastive learning baseline and zero-shot large language models on Python (Kamino) and multi-language (GPTCloneBench) datasets. Results show that LWVIC4Code achieves competitive or superior performance without negative samples, benefits from layer-wise supervision, and generalizes effectively from Python to other languages, particularly Java and C#. These results demonstrate that non-contrastive, layer-wise representation learning is a promising direction for robust semantic code clone detection.

AI coding assistants are becoming co-authors of production software, yet their evaluation centers on functional correctness, leaving open whether their code differs from human code in the quality dimensions dominating lifecycle cost. We compare human-written and AI-generated code at scale: 787,562 function pairs across Python, Java, and C, each human function mined from open-source repositories paired with implementations generated from its docstring by three AI assistants (OpenAI GPT models, DeepSeek-Coder, Qwen2.5-Coder). We characterize structural complexity and statistical naturalness, and map static-analysis findings onto Orthogonal Defect Classification for defects and the Common Weakness Enumeration for vulnerabilities, making authors and languages directly comparable. AI-generated code is structurally compressed and stylistically templated: roughly half the size and branching of human code, clustering apart at the style level. Defect profiles differ in kind: human code concentrates issues of mature codebases, AI code repetitive boilerplate; security is language-dependent, with LLMs producing more, and more severe, findings in Python and Java but fewer high-severity memory-safety findings than humans in C. Once size is controlled for, complexity metrics carry little signal, while naturalness separates authors. Finally, we release CQBench, a benchmark of 27,346 issue-prone tasks with baselines and an evaluation pipeline for quality assurance and security testing.

Test case synthesis is crucial for evaluating and ranking programs generated by large language models (LLMs). However, constructing high-quality test cases remains challenging because reliable expected outputs are often difficult to obtain. We propose Confidence-Gated Transductive Test Generation (CoTT), which first uses an efficient inductive procedure and invokes transductive generation only when inductive confidence is low. This adaptive design improves output reliability while allocating extra computation only when needed. On code reranking benchmarks, CoTT outperforms prior baselines across the reported metrics while reducing cost relative to applying transductive generation to every input. These results show that confidence-based allocation of test-time computation provides a favorable efficiency-effectiveness trade-off with a single efficient LLM.

An agentic coding system couples a language model to a harness: the tools, prompts and control flow that turn a chat model into an autonomous software engineer. Vendors ship harnesses tuned to their own models, and practitioners assume the vendor-native pairing solves more tasks. We measure that assumption with paired same-model contrasts on a private, contamination-controlled suite of 256 repository and post-cutoff contest tasks. The same 80 tasks ran under claude-agent-sdk and under deepagents on claude-opus-4-8, and under the openai-codex SDK and deepagents on gpt-5.5, with gemini-3.5-flash and deepseek-v3.2 as side cells. 792 of 800 planned runs were graded by an isolated oracle. Neither contrast resolves an average advantage for either harness: -1.25 pp for Opus 4.8 (48.8% vs 50.0%, task-bootstrap 95% CI [-10.0, +7.5]) and +1.25 pp for GPT-5.5 (55.6% vs 54.4%, CI [-4.4, +6.9]). The Opus average combines opposite strata: the native harness trails by 9.0 pp on the 61 repository tasks and leads by 23.7 pp on the 19 contest tasks (label-permutation p = 0.003). The partition was chosen after seeing the data and needs a designed replication. Correctness and completion also separate: 22 of 81 runs cancelled at the wall-clock ceiling had produced a passing patch. Re-priced from raw per-turn usage at frozen list prices, the neutral harness cost 1.3 to 1.6 times as much per solved task on Opus 4.8 and 1.2 times on GPT-5.5. These are observed-usage estimates. On the Anthropic account 58 runs left no usage record, and allocating that spend to either cell would move the Opus ratio between 0.7 and 2.3, so the billed ordering is unresolved. This revision corrects an August 2026 manuscript whose cost figures rested on a usage-semantics defect in our own telemetry (Section 5.1). We release the orchestrator, grading oracle, reanalysis code and derived aggregates. The tasks stay private.

Coding agents increasingly read repository knowledge from SKILLs --- plain \texttt{.md} files versioned alongside the code. Recent work synthesizes these files automatically, by optimizing the document against a benchmark. A bare repository comes with no benchmark, and the synthetic tasks prior work builds are small enough that a capable agent saturates them with no document at all. We mine harder tasks --- merged pull requests of the repository, reverted at a single frozen base commit; and score a candidate document by whether the same agent does better with it than without it. On three Kotlin repositories, the documents GEPA finds raise this score by $4.9$pp on average, and the ones SkillOpt finds leave it where it started, $0.1$pp above the seed. The GEPA gain matches what prior work reports with the same optimizer, and at the dataset size a single repository supplies it cannot be separated from the agent's run-to-run variance; settling that would take more tasks than one repository's history yields. The documents themselves read better than the score: a maintainer of one repository found in them knowledge one only gets by working in the project.

Post-training with reinforcement learning (RL) is a critical phase in the development of code-generating large language models (LLMs), as it ensures adherence to instructions and the production of functionally correct code. This process typically requires computationally intensive code sample generation from Transformer-based LLMs and substantial GPU-CPU communication for sequence verification. To address these computational challenges, this work examines whether RL-based post-training can be performed entirely offline by leveraging existing datasets rather than generating new samples. The findings indicate that, with only a few hours of training, zero-shot code generation performance of LLMs can be substantially improved without online sampling. Additionally, offline RL produces performance gains across models ranging from 0.5B to 7B parameters, although the extent of improvement varies among model families.

Embedding an intelligent agent in an existing application creates a persistent coordination problem: users can revise goals and manipulate shared objects while delegated execution continues. We argue that dependable integration requires an explicit correspondence between task-level interaction and application behavior. We introduce Agent-Integrated Software (AIS) as a software pattern combining a conventional core, direct interaction, and a built-in agent, and Intent-Level Interaction Abstraction (IIA) as the task semantics through which users inspect and control delegated work. An open transition-system model relates AIS execution to IIA states and events. Interaction contracts constrain this relation through task bindings, role-specific authority, control transitions, and outcome evidence; continuous assurance maintains scoped claims as their dependencies change. A compact disclosure contract and conditional propositions illustrate why local component validity is insufficient and how selected admission invariants can be separated from planning. Contrasting software domains expose the framework's assumptions and limits. This perspective develops a research agenda spanning application abstraction, development support, controlled execution, quality assessment, and human supervision, with the aim of making agent integration a maintainable software engineering discipline.

Artificial intelligence is changing both software production and the economics of software-based business models. Classical technology due diligence mainly examines technical properties such as architecture, scalability, and technical debt. These criteria do not fully capture how AI can affect a company's value proposition, competitive position, margins, or access to customers. This paper develops Artificial Intelligence Exposure and Resilience (AI-ER) as a two-dimensional assessment framework. AI exposure describes the pressure for change that AI creates for a business model. AI resilience describes the company's ability to absorb that pressure, adapt to changed conditions, and use AI in an economically viable way. Metrics for both dimensions are derived from current AI capabilities, their deployment conditions, and relevant research on business models and organizational adaptability. The model keeps exposure and resilience separate and adds an explicit assessment of evidence quality and confidence. It can be applied first with public information and later refined with internal evidence. The result is a traceable company profile that supports comparison without concealing uncertainty in the underlying evidence. The paper also specifies an initial score logic and a procedure for empirical validation.

The utility of AI in multi-coder qualitative coding has been widely discussed, yet little empirical evidence exists to delineate the contexts in which it performs reliably. We address this gap by quantifying the effectiveness of multi-agent LLM coding across varied qualitative datasets, revealing key contextual and structural factors that mediate coding outcomes. We developed a literature-informed baseline pipeline that enables AI agents to independently code, debate, and reconcile disagreements. Results revealed that coding accuracy depends on factors such as codebook length, qualitative data similarity, and agent disagreement. Notably, intense and unresolved debates between agents led to higher accuracy. Our analysis showed that while LLMs emulate many human discussion behaviors, they lack adaptive responsiveness to context. From these findings, we offer design recommendations for building automated coding systems. Our open-source AI discussion dataset and methodological framework lay the groundwork for advancing the design of AI-mediated automated thematic analysis.

Advances in large language models (LLMs) fuel the quest for scalable methods to assess the security of generated and security-sensitive software. Static analysis is widely adopted as a scalable, reproducible, and inexpensive security gate, but cannot directly observe runtime exploit behaviour. Vulnerabilities dependent on adversarial inputs, execution context, or exploit chaining may evade static checks while remaining exploitable in practice, yet passing static analysis is often treated as evidence of secure behaviour. This paper introduces the Static-Pass Dynamic-Fail (SPDF) phenomenon and a three-stage agentic pipeline combining static scanning, LLM-driven Common Weakness Enumeration (CWE) reasoning, and autonomous exploit verification in isolated Docker containers. We evaluate 1,355 Python samples from SecurityEval, RedCode, and CyberNative datasets. Of the 654 samples producing no findings under the composite Bandit-Semgrep gate, the LLM detection stage identified 394 candidate vulnerabilities across 235 files. Dynamic verification confirmed or partially confirmed exploitability in 95 files, yielding an inclusive pipeline rate of 14.53% (roughly 1 in 7 statically clean samples). This rate represents the proportion of Bandit-Semgrep-clean samples for which the pipeline identified a candidate vulnerability and obtained runtime evidence supporting exploitability. Outcomes varied by dataset: among candidate file--CWE pairs, confirmed exploitability was 33.7% for RedCode, 28.6% for CyberNative, and 5.4% for SecurityEval. Several frequently confirmed classes, including CWE-338 and CWE-916, were flagged by neither Bandit nor Semgrep. These findings indicate that static-analysis success and runtime security are hierarchical layers of software assurance rather than interchangeable measures, and have the potential to reshape how AI-generated and security-sensitive code is evaluated.

When an agent writes code, the development framework becomes the control system for a non-deterministic worker. Spec-first, agent-driven frameworks have gained rapid traction since 2025; the installable ones, GitHub Spec Kit, obra/superpowers, BMAD, and GSD, and our own, all capture intent through a specification or durable planning artifacts. Since they agree on capturing intent up front, what separates them is how each enforces the engineering discipline that keeps agent-written code clean, correct, and maintainable. Every framework enforces that discipline somehow; they differ in how. We characterize three modes: enforcement by persuasion (prompt discipline the model may ignore), by front-loaded structure (strong specs, then a trusted build), and through controls the agent cannot edit (a deterministic orchestrator, human-approved gates, immutable tests, and a green result that must pass against a live, branched database). We introduce Consort, a spec-first, test-driven agent framework built on the third, enforcing that discipline through controls the agent runs inside but cannot bypass, in which a deterministic orchestrator drives separate role agents through a spec-first design lane and a test-driven build lane on a live database branch. We argue that enforcing the tests and gates in code keeps agent-written code honest and verifiable, while its specialized roles, like the human roles before them, are what make it maintainable, claims we frame as a pre-registered, testable hypothesis.

This study evaluates Vibe Coding, an emerging AI-led conversational programming paradigm that enables developers to generate software through natural-language interaction with large language models. Using a mixed-methods design, the study assessed performance efficiency, cognitive implications, and responsible adoption in comparison with traditional and AI-assisted coding environments. Thirty participants, including professional developers and advanced computing students, completed equivalent programming tasks under three experimental conditions. Quantitative data were analyzed using descriptive statistics and repeated-measures ANOVA, while qualitative data were examined through thematic analysis. Results show that vibe coding significantly improved development efficiency, reducing task completion time by 27% compared with traditional coding and 12% compared with AI-assisted coding. However, these gains were accompanied by lower maintainability indices and higher security vulnerabilities, indicating trade-offs in software quality. Usability results yielded a good rating (SUS = 71.4), while cognitive workload remained moderate (NASA-TLX = 55.5), reflecting reduced syntactic effort but increased linguistic reasoning. Thematic analysis identified trust calibration, loss of control, cognitive adaptation, and prompt-engineering strategy as key constructs. Notably, perceived loss of control was associated with increased security risks due to reduced transparency and validation of AI-generated outputs. Based on these findings, the study proposes a three-pillar framework for responsible adoption: hybrid integration of human and AI capabilities, human oversight and transparent accountability, and context-aware deployment. Overall, vibe coding enhances productivity but requires critical oversight, reinforcing its role as a transformative yet transitional paradigm in software development.

Large Language Models (LLMs) often generate natural-language comments while writing code, and these comments become part of the context used to generate the code that follows. However, it remains unclear which properties of comments affect code-generation performance. We study this question through observational analyses and controlled interventions. On LiveCodeBench, neither comment frequency nor broad comment intent reliably predicts pass@1. We then prefill weaker recipient models with comment blocks written by stronger source models, allowing us to separate comment surface form from the solution content they convey. Comments from source solutions that pass the tests raise recipient pass@1 by 17.2% on average. In contrast, comments describing failed solutions provide no reliable gain, while comments written for a different problem reduce pass@1 by 20.8%. Finally, across a wide range of models and prompt variants, most recipient models show no significant recovery of the external-comment gain, and the best case recovers only 24%. These results show that comments help code generation not merely because they are comments, but because they can provide correct solution content that prompting cannot reliably elicit.

Exception Related Code (ERC), which includes throw statements, conditions (if statements) that guard those throw statements, and try/catch blocks, is an essential component of software systems, allowing developers to detect and handle exceptional states that deviate from the expected program behavior. However, manually writing ERC across large codebases is tedious. We propose a novel task: retrofitting existing code with ERC. Namely, given code (without ERC) and Exceptional Behavior Tests (EBTs) (e.g., check if method throws InvalidArgumentException if null is given as the value to the argument) we aim to automatically generate missing ERC, such that the given tests pass. We design and implement Exception Coder (EXCODER) that performs context engineering to help Large Language Models (LLMs) tackle this task. EXCODER integrates static and dynamic program analysis with LLMs by providing the extracted contextual information to the LLMs. To evaluate EXCODER, we build a benchmark constructed from GitHub Java repositories, where we systematically remove ERC in 304 methods from 75 projects. Our results demonstrate that EXCODER provides an effective, though imperfect, solution to this problem in automated code generation, offering developers the first way to implement ERC following test-driven development. When combined with Qwen 2.5 Coder 32b, EXCODER achieves pass@1, 5, and 10 rates of 85.92% (12.56 percentage points over baseline), 86.18% (12.82 p.p. over baseline), and 86.51% (13.15 p.p. over baseline), respectively, on developer-written test suites. Our manual inspection of the generated code further reveals limitations of EXCODER, pointing to directions for future work.

Large language models (LLMs) have demonstrated remarkable capabilities in reasoning and code generation, raising the prospect that they could assist in developing and optimizing the very infrastructure that powers them. However, existing benchmarks mainly focus on isolated kernels, predefined operators, or pre-specified optimization targets, and therefore fail to evaluate the ability of LLMs to perform open-ended, long-horizon LLM infrastructure engineering. To address this gap, we present $Φ$-Bench, a benchmark for systematically evaluating LLMs on engineering the LLM infrastructure stack. Derived from optimization problems studied in frontier research and grounded in real-world code repositories, $Φ$-Bench provides broad coverage of the LLM infrastructure stack and spans tasks of varying complexity, ranging from localized kernel-level function completion to long-horizon implementation and end-to-end system optimization. Extensive experiments on frontier LLMs reveal their current capabilities and limitations in engineering complex LLM infrastructure, offering insights into the challenges that remain on the path toward autonomous optimization of future AI infrastructure.

Large language models (LLMs) have become ubiquitous in software development, with LLM-based automated program repair tools increasingly used during code review. In this report, we explore the iterative blind use of LLMs as bug-fixers. Across multiple models and repair environments, we find that LLMs consistently claim to detect bugs in entirely bug-free programs while the rate of repair of buggy programs is less than that of the damage to correct programs. We also explore the long-term dynamics of this iterative process, and find that this frequently reaches a pseudo-bug-fixing cycle where the same changes are added and removed again ad infinitum. Lastly, via mechanistic probing, we unveil the existence of a steering vector which controls the editing propensity, suggesting that LLMs have an internal representation of ``buggy code", and that this representation is what is falsely activated to induce pseudo-bug fixing. These results provide insight towards the dynamics of fully autonomous bug-fixing systems, as well as stopping conditions under ambiguous goals.

Dense change detection in remote sensing requires vision-language models (VLMs) to compare bi-temporal images and generate accurate pixel-level masks. Existing VLMs are largely confined to change captioning outputs, and the few that produce pixel-level masks still rely on external decoders or flat text-as-mask serialization, which are less effective for small and fragmented changes. We introduce QUAKE-CD, a framework that recasts dense change prediction as syntax-verifiable structured generation. QUAKE-CD represents binary change masks as grammar-constrained quadtree token sequences, making the masks compact, syntactically checkable, and deterministically decodable within an autoregressive generation space. We further construct QUAKE-CoT, which pairs these sequences with chain-of-thought traces grounded in visual evidence, and jointly optimizes textual reasoning and spatial dense prediction through a progressive curriculum followed by grammar-gated dual-reward RL. On QUAKE-CoT, QUAKE-CD achieves 78.31% accumulated F1, outperforming decoder-based and flat text-as-mask VLMs while producing more faithful bi-temporal reasoning.

Large language models (LLMs) have been ex- ploited to generate malware, but the effective- ness of guardrails for code generation secu- rity remains unclear. We introduce CS-Guard, the first benchmark to systematically evalu- ate guardrails for code generation security. It covers 1) text-to-code generation with 1000 high-quality malware-generation prompts, 7 jailbreak attacks, and a novel fictional scenario attack (FSA) that embeds malicious intent in a legitimate fictional software-development sce- nario; and 2) code-to-code generation with 331 code prompts spanning code infilling, code completion, and code translation. We empiri- cally evaluate 9 guardrails across seven LLMs. We find that current guardrails perform poorly against malicious code-generation re- quests: for text-to-code, the average attack success rate (ASR) after jailbreaks reaches about 50% for many guardrails; for code-to- code, average ASR approaches 100% on base LLMs and remains high across many guardrails (14.4% to nearly 100%). Our FSA also achieves ASR close to 100% across many guardrails, raising major reliability concerns for real-world software development. To sup- port future research, CS-Guard uses a modular three-layer guardrail taxonomy that lets devel- opers register guardrails for evaluation. We release the benchmark and data to enable fur- ther community evaluation.

Existing methods for test-time reinforcement learning (TTRL) derive rewards from answer-level self-voting on unlabeled test-time tasks with canonical answers, but this breaks down for code generation because programs cannot be compared by surface form and therefore do not directly provide a usable training signal. To make TTRL applicable to code generation, we propose probe-driven TTRL, which constructs output-free probe inputs from the problem statement, executes candidate programs on these probes, and defines a Probe Consensus Reward (PCR) from the resulting behavioral agreement. PCR provides a behavioral training signal for open-vocabulary programs, but it is not a fully reliable verifier and remains susceptible to reward hacking through spurious consensus. We therefore introduce Entropy-Regularized Rank-Masked Policy Optimization (ERPO), which converts low PCR into conservative negative updates through rank masking and controls policy drift with an entropy ceiling. On coding benchmarks, ERPO substantially improves pass@1 and pass@k in both in-domain adaptation and zero-shot transfer.

Execution feedback can guide coding agents toward correct repository repairs, but only when the tests capture the behavior requested by the issue. Agent-generated tests can encode incomplete or incorrect behavioral targets; when the same trajectory writes both the patch and the test, their errors can agree and create false confidence. We introduce ExecCritic, combining a test--verify--revise scaffold with a role-specific reinforcement learning recipe for training agents within it. The scaffold separates test construction from source-code repair: a Test agent independently generates repository-native tests, a fail-closed harness qualifies and freezes them, and a Repair agent revises source code from their execution feedback without changing the tests. Both roles use Qwen-3.5-35B-A3B as the backbone and are trained separately. In Learn to Test, the Test agent learns to produce behaviorally valid tests that distinguish correct from incorrect patches. In Test to Improve, the Repair agent learns both direct task resolution and feedback-guided revision. On SWE-bench Verified, test quality determines whether feedback helps: holding the base Repair agent fixed, tests from the base Test agent reduce resolved rate from a no-test baseline of 61.2% to 57.3%, whereas tests from GPT-5.6-sol raise it to 65.3%. Role-specific post-training raises the Qwen Test agent's Base-to-Gold success from 22.2% to 62.2%; composing the two post-trained Qwen agents reaches 72.6%, an 11.4-point gain over the original no-test baseline without stronger-model or Oracle feedback at evaluation time. Code is publicly available at https://github.com/MSR-Orchard/execcritic.

Ensuring the safety of autonomous driving is a critical challenge. Scenario-based testing is a systematic process used to validate Autonomous Driving Systems (ADSs), but it remains a fragmented modular pipeline in which scenario generation, retrieval, modification, ADS execution, and results analysis are performed by separate tools with little interaction. Large Language Model (LLM) agents have shown promise across ADS sub-systems such as perception, planning, and control. However, no prior work covers the whole scenario-based testing pipeline for ADSs with a unified LLM-agent framework. We present PlannerForge, an LLM-agent framework that extends all scenario-based testing stages (from Scenario Generation to ADS Assessment) and adds two further LLM-enhanced stages: ADS Enhancement and ADS Benchmarking. We evaluate PlannerForge with 10 off-the-shelf LLMs across all tasks (Generation, Selection, Modification, Module Routing, Planner Testing, and Enhancement) under 5 prompt conditions. Best-per-task scores range from 0.88 to 1.00, and open-source 20-35B backends match commercial APIs on most tasks. Open-source models such as Qwen3.6:35B match commercial APIs on three of the five tasks. Chaining the modules end-to-end retains 83% / 78% of seed queries (commercial / open). It outperforms Scenario Factory 2.0 (Finkeldei et al., 2025) on natural-language generation (193 vs. 144 executable of 200) and realises 92-96% of requested city, road and vehicle attributes. It outperforms BM25 (Robertson and Zaragoza, 2009) at rank 1 selection (92.0% vs. 67.5%) and From-Words-to-Collisions (Gao et al., 2025) on physically valid edits (>=94% vs. 31%). At N=400, cost-tuning lifts planner success from 50.4% to 70.2% and cuts collisions from 19.0% to 8.4%, without domain-specific fine-tuning.

Solving repository-level code tasks requires LLM-based agents to use code search tools to navigate large codebases and identify a small set of relevant files and functions. However, current retrieval tools typically return flat lists of isolated code snippets: such lists can surface relevant files, but provide insufficient structure for agents to distinguish the target function from semantically similar alternatives in the same file. We introduce RepoNav, a lightweight post-retrieval interface that reorganizes retrieved snippets into a file-centered navigation scaffold. By presenting compact structural cues and candidate targets, this scaffold guides on-demand file-structure browsing, helping agents compare sibling symbols before selecting a target function. Across diverse models on LocBench, RepoNav improves function-level localization and narrows the file-to-function gap. Controlled ablations demonstrate that these gains come from structured evidence organization rather than simply exposing additional file structure, and the approach also improves performance on a repository-level question-answering benchmark.

The transition from human-centric assistance to Autonomous Software Engineering (ASE) agents has enabled the resolution of complex real-world SE tasks. However, the trial-and-error nature of these agents generates lengthy interaction trajectories, creating severe bottlenecks in terms of context window limits and cost. While context compression offers a potential remedy, prior approaches suffer from static pruning strategies and granularity mismatches, often failing to preserve the semantic dependencies and syntactic details crucial for SE tasks. To strictly preserve critical task evidence while reducing context length, we introduce AttnCompress, a dynamic attention-guided trajectory compression framework. Unlike existing approaches, AttnCompress bridges the gap between semantic integrity and dynamic adaptability through three key mechanisms: (1) structure-aware segmentation via perplexity (PPL) spikes to preserve the syntactic structure of code and logs; (2) relevance estimation using proxy attention weights to quantify the precise relevance of historical blocks to the agent's current reasoning; and (3) a dynamic rolling window to re-evaluate and recall historical context as the task evolves. Extensive evaluation on SWE-Bench-Verified and Multi-SWE-Bench demonstrates that AttnCompress achieves a pass rate of 53.17%, outperforming prior state-of-the-art baselines while reducing token consumption by 21.6% and total costs by 33.6%. The framework proves to be model-agnostic and generalizes effectively across diverse programming languages.

SWE-Bench Pro has emerged as a standard benchmark for evaluating software engineering agents on challenging repository-level tasks. However, our analysis work show that its evaluation is undermined by two sources of unreliability: reward hacking, enabled by leakage of gold solutions or hidden evaluation information, and task quality issues, including misleading problem statements and improperly scoped tests. These issues can inflate benchmark performance and obscure agents' true coding ability. We present SWE-Bench Pro Verified, a verified version of SWE-Bench Pro that addresses both problems. Our approach combines anti-hacking safeguards that eliminate major leakage channels without disrupting normal agent functionality, with task refinement that minimally corrects inconsistencies within flawed instances. Evaluations on SWE-Bench Pro Verified reveal that some models perform substantially worse than previously evaluated, suggesting that existing results on SWE-Bench Pro may overestimate real software engineering capability. SWE-Bench Pro Verified offers a more trustworthy benchmark for assessing software engineering agents.

The software supply chain has become an increasingly exposed attack surface because of its reliance on intricate yet fragile dependencies. Existing defenses such as GitHub Dependabot often raise many false alerts because their coarse-grained matching cannot determine whether a vulnerable dependency is actually exploitable. Security analysts typically spend substantial time assessing vulnerability exploitability case by case. Recent LLM agents have emerged as promising candidates for this task given their advanced capabilities in coding and cybersecurity, yet no existing benchmark evaluates them on it. Prior benchmarks target zero-day settings, where agents detect and exploit previously unknown vulnerabilities. In contrast, software supply chain security focuses on how known vulnerabilities in upstream dependencies affect downstream projects. This requires agents to reason across repositories and determine whether an upstream vulnerability is exploitable in the downstream project. To address this gap, we introduce VEX-Bench, the first benchmark for evaluating LLM agents' ability to assess the exploitability of software supply chain vulnerabilities. It contains 75 real-world cases mined from GitHub and labeled by security experts, covering Python, Java, and Go. We evaluate nine models across three agent harnesses. While GPT-5.5 and Claude Opus 4.6 reach approximately 80% F1 on binary vulnerability-status classification, only GPT-5.5 surpasses 70% macro-F1 on fine-grained justification classification. This gap highlights the challenge of moving beyond binary exploitability assessment to identifying fine-grained exploitability reasons. Code and data: https://github.com/steven1518/vex-bench

Existing causal-inference benchmarks for LLMs mostly score method descriptions or whether generated code runs, not whether the executed workflow recovers the target causal estimate. CausalVerify studies this verification problem for structured econometric causal-estimation workflows by separating realistic interpretation from verifiable computation. It pairs 259 published economics papers (reconstructed research question, data description, institutional context) with 100 fixed-seed synthetic scenarios that realise CSV datasets for difference-in-differences, event study, instrumental variables, and regression discontinuity designs. Experiment A (real-paper text agreement) scores method-family and direction agreement against four-LLM consensus labels. Experiment B (synthetic execution) runs model-written R code and checks whether the extracted treatment-effect estimate matches a canonical estimator on the same realised dataset; this execution-grounded correctness layer is L2b+, distinct from L2b, which records only whether the code executes. A calibration arm asks whether self-reported confidence separates correct from incorrect workflows. On Experiment B, seven LLMs reach L2b+ pass rates of 10% to 88% at the default 50% tolerance, and 66 of the 426 workflows that execute (15.5%) return a wrong estimate. Execution ranking (L2b) agrees with L2b+ far better than text-direction scoring (L4): Kendall $τ=0.81$ and Spearman $ρ=0.93$, versus Kendall $τ$ between $-0.20$ and $0.10$ for L4. Llama-3.3-70B-Instruct shows the same qualitative gap, and reported confidence does not reliably separate correct from incorrect workflows. The claims are confined to standardized single-shot workflows in these four design families under the evaluated R backend and model panel; the benchmark does not measure general causal-inference ability. Code, data, cached outputs, and a datasheet are released.

We present FrogNano, a 4B coding agent designed to tackle software engineering (SWE) tasks efficiently and effectively, even under resource-constrained environments. It is post-trained exclusively via RL on around 1,500 SWE environments with synthetic tasks. A key ingredient for improving performance is an online task synthesis pipeline that creates tasks calibrated to the frontier of learnability for the current checkpoint. This report provides evidence that competitive small coding agents can be trained with synthetic tasks alone, without traditional distillation from larger models, and that generating tasks at the learnability frontier of the current agent is important. We report details on the training methodology, evaluations across diverse environments, and in-depth analyses, serving as a foundation for our ongoing exploration of lightweight yet capable coding agents that can run on minimal hardware.

As AI-code assistant tools become widespread, automatic assessment of the correctness of generated code becomes a significant challenge. Code LLMs are prone to hallucinations, which may lead to code that does not solve the required problem, or even to code with severe security vulnerabilities. In this paper, we introduce CodeTD -- the first approach to pre-execution assessment of code correctness based on topological data analysis (TDA) of Code LLMs' attention maps. Our method quantifies prompt-generation mismatch using topological patterns of attention maps. We carry out experiments with common benchmarks (HumanEval, MBPP, BigCodeBench, MultiPL-E), 5 programming languages and 10 Code LLMs of size up to 34B parameters. The experimental results show that the proposed method outperforms recent baselines. Moreover, CodeTD is transferable between coding benchmarks.

AI coding assistants now select, install, and configure software, and attackers have exploited that position through invented package names, compromised maintainer accounts, and manipulated repository text. In response, the supply-chain community publishes machine-checkable trust signals: software bills of materials, signed releases, build provenance attestations, and declared official channels. Whether coding assistants read or act on those signals has not been measured for any of these classes on research software. We pre-registered and ran a controlled study on six open-source research software projects (three HPC, three quantum computing) drawn from an 87-project corpus, with protocol, seed, panel, and analysis plan deposited with a DOI before any trial. W created nine modified copies for each project: no signal, one per signal class, two with a signature or attestation from the wrong issuer, one with all four signals, and one reproducing documented conflicts in the project's own metadata. Three models under two ways of operating an assistant, with and without an approval step, gave 1,920 registered trials, plus a supplement on three frontier models. We scored behavior from container logs rather than from what the assistant said, and recorded the cost of every trial. Verification was rare under every condition: in 9 of 1,920 registered trials (0.5%), the assistant opened any provenance signal before installing in 0 of 384 control trials, and no trial ran a verification command, so signal presence had no measurable effect. We drew three conclusions: publishing signals is necessary but not sufficient; price did not buy verification (the model that verified most often costs $0.10 per trial; the most capable, at$1.00, verified nothing); verification must be built into the program that runs the assistant. We release the per-trial cost ledger, the protocol, and every log.

Software repositories contain vast amounts of data on code contributions, bug reports, and project activities, yet this information remains challenging for non-technical stakeholders and developers to access due to limited expertise in querying repositories. To address this, we introduce a novel chatbot architecture leveraging OpenAI's GPT-4 model for automated extraction and analysis of repository data. In contrast, our architecture takes a structured path first by parsing the user's query to extract relevant parameters, then selecting the correct tool to employ based on that analysis, and finally invoking the GPT-4 model to create a highly detailed response. In contrast to previous work based on multi-component systems with embedding models and document retrievers, our architecture inverts the process by relying on prompt engineering and tool selection to fit with the query intent. To validate our approach, we conducted experiments on various question types, including Issues, Pull Requests, Commits, Compound Questions, and General Repository Information, evaluating our target prompts' ability to improve the accuracy of responses from the model. Beyond demonstrating the utility of this architecture to a diverse set of users, our findings suggest that this architecture can make repository data more accessible to technical and non-technical audiences through the production of actionable insights.

Natural-language Computer-Aided Design (CAD) code generation aims to turn design intent into executable and editable parametric programs. Large language models (LLMs) make this goal increasingly practical, but useful systems must preserve the construction process behind the rendered geometry. Existing benchmarks and methods mostly focus on how closely the generated CAD model matches the reference geometry, often using metrics such as Intersection over Union (IoU). Such metrics can miss errors in part decomposition, construction hierarchy, Boolean operations, sketch structure, and geometric relations. This gap calls for a representation that makes design intent explicit and lets a system check generated code against that intent. We propose CIT-CAD, a framework that infers a Constraint Intent Tree (CIT) from the input description to represent the intended entities, hierarchy, operations, and relations. The tree has two roles: it guides CAD code generation and defines expected constraints for verification. The framework extracts actual constraints from the generated program, compares them with the expected constraints, and uses mismatches to localize and repair design violations. Experiments show that the framework improves CAD generation performance, with larger gains on more complex multi-entity designs. By turning design intent into an explicit and checkable object, this work is the first attempt to move text-to-CAD generation beyond rendered-geometry matching toward construction-aware synthesis, verification, and repair.

LLM agents are rapidly becoming production software, deployed to handle customer service, adjudicate disputes, and operate internal systems. Notably, the work of building them is increasingly handed to coding agents, yet existing benchmarks say little about whether an AI system can deliver one under the conditions of a real client engagement. We introduce $\tau^\tau$-bench (pronounced hyper-tau-bench), a benchmark that makes agent construction the task. A developer agent is given the records a business actually keeps, a client who holds requirements, a production API that operations must run through, a codebase to inherit, and limits on serving cost and models: the same starting point a real engagement provides. From these it must deliver a complete customer-service agent, scored by deploying that agent against held-out simulated users. Across 53 tasks spanning four domains, the strongest configuration, Claude Opus 5 under Claude Code, passes just 23.9% of evaluation simulations. Meanwhile, an expert-authored reference ceiling scores 82.2%. The failures mirror ones human agent developers see: models issue shallow queries in place of deep comprehension of the records, communicate almost nothing to the client, and experiment too little with agent architecture and serving spend, shipping the first design that runs. We aim for $\tau^\tau$-bench to turn the work of cooperative agent building into a measurable target for coding agents.

Agent reinforcement learning (RL) increasingly runs through full execution harnesses, and a multi-harness recipe mixes two choices: exposing the policy to several harnesses, and comparing their rewards inside one relative-advantage group. We isolate the second choice in repository-level coding. From one Qwen3-8B supervised warm start we replay the same frozen task-harness records from Aider, OpenHands, Qwen Code, and SWE-agent, with the same number of updates, under two rules for group-relative policy optimization (GRPO), Within (one group per task-harness pair) and Cross (harnesses pooled within a task), and score every checkpoint with a sealed SWE-bench Verified oracle on four source harnesses and a minimal harness held out of training. The evaluation harness is the dominant variable: across 24,000 sealed evaluations it moves the mean solve rate from 2.14% to 9.27%, a factor of 4.3, where the training recipe moves it by 1.16. The grouping rule is not. On the held-out harness, Cross minus Within is +0.25 pp, 95% confidence interval [-0.48, +1.02], at eight attempts per task, and +0.16 [-0.41, +0.72] pooled over three training seeds whose individual estimates change sign. Each rule's own seed range, 0.42 to 0.45 pp, exceeds the difference between them. Both rules place their largest gains on the same source harness. The pooled advantage carries the harness: an out-of-fold classifier recovers the generating harness from Cross's advantage +4.48 pp above the shuffled-label baseline and from Within's not at all, and the two rules still reach the same held-out score and action distribution inside each harness. Re-collecting half the training data on-policy does not change this. Cross-harness credit yields configuration adaptation and no more portable capability than within-harness credit. Multi-harness RL reports should state the grouping boundary and test under an unseen harness.

Repository-level software engineering benchmarks have significantly advanced the evaluation of coding agents, but existing benchmarks primarily measure whether generated patches pass functional tests and overlook review-derived acceptance constraints (review constraints) that often influence whether a patch is acceptable in real-world software development. We introduce SWE-Gate, a repository-level benchmark for software engineering agents that explicitly evaluates review constraint compliance alongside functional correctness. SWE-Gate derives review constraints from real pull request review comments and synthesizes repository-level repair instances around these constraints. Each instance provides separate functional and constraint tests, together with non-compliant and gold patches, enabling explicit separation between issue resolution capability and review constraint compliance. We construct SWE-Gate with 303 repository-level repair instances spanning 75 open-source Python repositories across diverse software domains. Experiments with four LLM backends spanning different capability levels under a common coding-agent scaffold reveal a substantial gap between functional success and success under the complete repair specification: among 644 repairs that pass the functional tests, 221 fail to satisfy the provided review constraints. These findings show that functional-only evaluation overestimates agents' ability to satisfy the full requirements of repository-level repair tasks. The replication package including code, data, and experimental results is available at https://github.com/DeepSoftwareAnalytics/SWE-Gate.

As terminal-based code agents become prevalent, agent trajectories have accumulated at scale, while realistic, executable environments remain scarce. However, environments are what agent post-training actually requires: each can be re-queried into many verifiable tasks and provides execution feedback, whereas a trajectory is a single frozen demonstration. Rather than generating environments from scratch, we observe that the tool-execution history in existing trajectories exposes the structure and contents of the environments in which they ran, making it possible to reconstruct those environments from the trajectories themselves. Thus, we introduce Terminal-Universe, a framework which turns each trajectory into a reusable environment and explores it for synthesizing new tasks and continued interactions. Specifically, Terminal-Universe replays the file operations recorded in a trajectory to restore each file before the agent modified it, yielding a partial workspace; a completion agent then supplies the missing files and dependencies. On this recovered workspace, we both reconstruct the original intent task and synthesize entirely new ones. Besides, we also scale the tasks along two complementary axes: breadth and depth. For breadth, we mine directional dependency relations between related environments and synthesize cross-workspace queries spanning multiple codebases, as developers routinely do in real-world development. For depth, we extend the initial single-turn query into a multi-round session that captures iterative user feedback and requirement refinement via a user agent. Applied to public terminal agent trajectories, Terminal-Universe produces 37.3k task-sufficient environments. Supervised fine-tuning of Qwen3.5-27B on this corpus improves single-round performance on Terminal-Bench 2.1 by 11.9 points and multi-round performance on EvoCode-Bench v2 MT@4 by 13.8 points.

Large language models (LLMs) are increasingly used to edit existing code, but correctness alone is not enough: useful repairs should also be minimal, reviewable, and faithful to the original implementation. We study over-editing, the tendency of a model to rewrite code beyond what is required to fix a bug. We construct an evaluation framework from 400 BigCodeBench problems by injecting controlled AST-level corruptions into reference solutions, giving each repair task a known minimal patch. Across frontier LLMs, over-editing is widespread even among strong models like GPT-5.5: high Pass@1 can coexist with unnecessarily large edits and added cognitive complexity. A preservation instruction substantially reduces this behavior, lowering average excess Levenshtein distance from 0.195 to 0.131, reducing added cognitive complexity by 26.6%, and increasing Pass@1 by 2.3 points. However, these gains do not simply follow from a larger reasoning budget or larger models. We next ask whether minimal editing can be learned directly during post-training. We observe that supervised fine-tuning overfits to seen corruption patterns, whereas reinforcement learning gives the best out-of-domain edit-fidelity and performance-retention trade-off. These results position edit fidelity as a distinct axis of code-repair quality and show that it can be measured and learned.

While diffusion base models such as GPT-Image-2 and Nano-Banana exhibit remarkable visual expressiveness, their end-to-end generation inherently yields flattened bitmaps with error-prone text, precluding layer-wise post-editing. Conversely, code-based visual generation via Coding Agents provides precise layout control and decoupled layers, yet remains constrained by a lack of global aesthetic intuition and the difficulty of coding complex visual assets. To address this, we propose Editable Visual Design, a new paradigm driven by a Coding Agent. We designate the VLM as the creative brain'' for requirement comprehension, task planning, and aesthetic judgment, while utilizing the image generation model as an on-demand visual world simulator'' to synthesize standalone visual assets. Operating under an ``imagine first, then act'' closed-loop workflow, the agent generates isolated assets, writes native HTML/CSS, and iteratively refines the design against visual rendering feedback. Furthermore, Agent Design Replay faithfully reproduces the creative and reasoning trajectory akin to that of professional human designers. Ultimately, the system delivers editable artifacts with decoupled layers and real text, enabling users to perform intuitive mouse dragging and layout adjustments on a graphical user interface. Validations on posters, infographics, and other scenarios show that this paradigm successfully achieves both refined aesthetics and production-grade editability.

Reinforcement learning (RL) has substantially advanced code generation with large language models (LLMs) through executable feedback. The feedback for coding problems mainly comes from specific test cases, where high-quality test cases are often scarce since they should be both sound and discriminative. We thus turn to study the auto-generation of test cases using the learned model. We find this is naturally an adversarial RL problem: the model is expected to generate effective test cases as counterexamples, depending on the solver's current failure modes. We propose Test Cases Scaling (TCS), a two-stage RL framework for effective test generation. Both stages train a test generator from a rolling policy-aligned buffer: Stage 1 generates tests consistent with the reference solution, and Stage 2 restricts the buffer to current failure modes and learns counterexample tests. Across TACO and LiveCodeBench, TCS improves both pass@1 and inference-time answer selection according to generated tests. We find the learned test generator also enables effective selection among other LLM outputs.

Artificial intelligence (AI) is increasingly used to augment software engineering (SE) workflows. While code generation remains the main use case, organizations are actively seeking AI integration in other practices such as test cases generation and code reviews. Organizational AI adoption strategies seem to focus on tangible outcomes such as productivity. However, AI is a disruptive force, introduced into settings where role identity, team norms, and the sources of job satisfaction were well established before the recent advances in generative AI. Historically, technological disruptions have caused psychological and social strains in workplaces, ranging from anxiety and eroded meaning to deskilling and disrupted professional identities. The assumption that AI for SE is cost-free may not be accurate. Therefore, in this study we sought to understand the psychological costs software professionals experience during organizational AI adoption. We carried out a case study in a large software development services company, one year after the company launched its AI adoption. We collected qualitative data through meetings and semi-structured interviews (N = 21). We found that software professionals experience accountability anxiety, craft identity disruption, meaning and satisfaction erosion, cognitive and workload intensification, and uncertainty distress. Practitioners manage these costs through practices that restore control, mitigate them through protective and identity-preserving adaptations, or absorb them, carrying what neither can resolve. We contribute to AI-human collaboration in SE by repositioning AI adoption as a human transition, not only a technological and organizational one.

LLM-empowered paper-code discrepancy detection has received growing concern since the scaling of research submissions exceeds the manual review capability. However, the limited context capacity and one-sided discrepancy detection of existing single-agent LLM paradigms lead to an inferior recall performance in detecting discrepancies. In this paper, we propose Dude, the first Dual-Detection Multi-Agent System for paper-code discrepancy detection. We discover that the granularity asymmetry of the paper-language and code-language introduces over-interpretation and over-reporting challenges in a multi-agent system design for discrepancy detection, resulting in increasing false positives. To address this, we propose a granularity-aligned negotiation and a two-stage salience-filtering mechanism in Dude, which effectively prevents agents from falsely reporting discrepancies. Experimental results in real-world paper-code discrepancy datasets showcase Dude's significant recall and precision improvement by up to 22.8%, increasing F1 score by up to 18.7% compared to baseline methods.

Evaluating software engineering agents on realistic benchmarks is costly, since each task may require multi-step code exploration, modification, and test execution. Existing efficient evaluation methods select representative subsets to estimate full-benchmark performance, but are largely result-only: they fit historical pass/fail response matrices or static task semantics, discarding how agents solve problems. We propose PTA-IRT, a Privileged Trajectory-Aware Item Response Theory framework that fuses process and outcome signals. Historical execution trajectories supply process-level evidence beyond pass/fail, such as explored context, attempted edits, and solving paths, which PTA-IRT uses as privileged information for calibration subset selection and ability estimation. Under low calibration budgets, PTA-IRT consistently outperforms prior IRT baselines on score and ranking recovery across four SWE benchmarks. Code and data are publicly available at https://github.com/DeepSoftwareAnalytics/PTA-IRT.

The repository-level code generation task requires synthesizing code that satisfies task requirements while remaining consistent with the target repository context. Since real-world repositories often exceed the input length limits of LLMs, existing approaches commonly adopt retrieval-augmented generation (RAG) to provide repository-specific context. Despite improving repository-context retrieval, existing methods typically provide context as task-level support, without explicitly identifying the critical tokens that require fine-grained repository context during generation. During the autoregressive generation process of LLMs, errors often concentrate at a small number of decisive positions: once such tokens are generated incorrectly, subsequent code may follow an incorrect semantic path and eventually lead to functional failure. We refer to these positions as "critical tokens". In this paper, we propose ACToR, an adaptive critical token-aware retrieval framework for repository-level code generation. ACToR identifies critical tokens during generation and triggers targeted retrieval on demand to provide repository context at these decisive positions. In addition, we design a position-aware weighting method for dense retrievers to prioritize context that is more informative for generation. We evaluate ACToR on two representative repository-level benchmarks, RepoExec and CoderEval. Experimental results show that ACToR consistently outperforms state-of-the-art methods, achieving relative improvements of 8.4% on RepoExec and 15.4% on CoderEval. Beyond performance gains, we systematically quantify the impact of critical tokens, revealing their central role in major generation failures and highlighting the necessity of targeted retrieval strategies. We provide the code and data at https://github.com/DeepSoftwareAnalytics/ACToR.

Writing involves diverse cognitive activities, from ideation to revision, and writers' needs vary across individuals and moments. Proactive AI promises to provide the right support at the right time, yet existing proactive tools largely focus on generic textual assistance, such as autocomplete. This paper studies the design space of proactive thought partners: AI agents that proactively offer customizable, higher-level cognitive support during writing. We instantiated this concept in a technology probe and deployed it with 16 participants for one week. The probe allows users to create partners by configuring their roles and proactivity. As users write, relevant partners take the initiative at appropriate moments to offer suggestions. Our findings show that participants configured proactive support through prospective planning, used suggestions for both idea generation and self-monitoring, and valued lightweight visual representations alongside non-directive rhetorical framing for non-intrusive interventions. We derive implications for designing proactive writing assistants around customization, timing, engagement, and representation.

This paper studies autonomous software development, in which LLM-based coding agents transform high-level requirements into complete, functional, and usable software systems without human intervention. We introduce Harness-of-Harness (HoH), a framework that enables coding agents to continually improve software during autonomous development. HoH operates on existing coding-agent harnesses, and organizes their executions into iterative planning-coding-testing loops. To sustain improvement across loops, HoH balances repair with capability growth, scopes development into small and verifiable increments, separates implementation-time testing from independent evaluation, and constrains verifiable outputs rather than prescribing agent workflows. It progressively exposes deliverables, role-specific tools, and skills, encourages reuse rather than recreation, and maintains versioned project histories. On GameCraft-Bench, FrontierSWE, and ProgramBench, three harness-model pairs (Codex with GPT-5.5, OpenCode with DeepSeek-V4-Pro, and Pi with MiniMax-M3), HoH consistently outperforms the corresponding standalone harnesses, achieving an average relative gain of 52.25 percent and a maximum gain of 82.86 percent after three iterations. In a multi-day deployment with more than 70 iterations, HoH autonomously develops a first-person-shooter game, featuring a coherent storyline, fully implemented core mechanics, human-playable experience, polished visuals and integrated audio. Github: https://github.com/Flesymeb/HarnessOfHarness Project Page: https://flesymeb.github.io/HarnessOfHarness/

Agentic software engineering benchmarks are typically summarized by nominal category labels such as "bug fix" or "feature implementation," yet benchmarks carrying the same label are built through very different curation pipelines. A label thus reveals little about the engineering work a benchmark demands. We introduce the Spread--Novelty--Centrality (SNC) profile, a three-axis characterization of the demands of repository-level coding tasks, grounded in empirical software engineering research. We apply the profile to five widely used benchmarks and 14,922 trajectories of two model families at three scales, and report three findings. (1) A label is an unreliable proxy for task demands, as every pair of benchmarks is statistically separated on at least two SNC axes, and the separations trace back to specific curation decisions. (2) Agent behaviour reveals demands that the human-written gold solution cannot. Agents produce larger solutions than the gold where problem statements withhold hints and smaller ones where curation inflates the gold. How a task is phrased shapes what an agent produces. (3) Task demands correlate with success uniformly, with resolved runs concentrating in the low-SNC region for every family and scale, whereas the behavioural signatures of success are family-specific. Claude succeeds by matching the scope of the gold solution, and its parity share on files rises from $0.17$ at the smallest scale to $0.54$ at the largest. Qwen succeeds by exceeding the gold scope at every scale, and editing too little marks failure for both families.

When a hint turns a failing generated program into a passing one, does it provide missing information or merely steer the model toward a solution it could already produce? We test these hypotheses on HumanEval+ and MBPP+ using executable evaluation. For Qwen2.5-3B-Instruct, adaptive relevant hints rescue 36 of 79 selected failures; an unrelated hint rescues 19, while eight unhinted samples solve 46 and recover 31 of the 36 relevant-hint rescues. Phi-3.5-mini shows the same pattern: relevant hints rescue 42 of 101 failures, an unrelated hint rescues 17, and unhinted sampling solves 57, including 36 of the 42 relevant-hint rescues. Because the hint conditions use different attempt budgets, these comparisons do not isolate a purely semantic effect. Mechanistic tests on Qwen identify a stable activation direction shared by relevant and unrelated hints. Persistently adding this direction yields 14 rescues and 18 regressions, with no detectable net accuracy gain; learned low-rank interventions have a positive but imprecise estimated effect. Full textual specifications solve 22 of 24 context-defined problems, versus 5-11 for tested virtual-KV prefixes. Post-generation hidden-state probes transfer across benchmarks, with pooled AUROC 0.806 and 0.780, but their top-one selection advantage over token confidence is statistically unresolved. Overall, relevant hints can rescue failures, but most rescued solutions are already reachable through ordinary sampling, and the internal interventions tested here do not establish task-general capability transfer.

Test-set accuracy is silent on two issues that matter when deploying autoregressive neural sequence models: how much probability mass the system under test (SUT) places on constraint-violating alternatives that are reachable under sampling and what fraction of the input population satisfies a domain requirement. We answer both with probabilistic model checking. The pipeline extracts a discrete-time Markov chain (DTMC) from the SUT's token-by-token generation, verifies formal PCTL specifications with the PRISM model checker, and aggregates the per-input verdicts into a coverage curve over the input space. A soundness theorem establishes the DTMC as an under-approximation, so every verdict yields a certified interval on the SUT's true reachability probability. The coverage built from those verdicts is, therefore, conservative by construction. A counterexample-guided abstraction refinement (CEGAR) loop adaptively tightens the interval, and a maximum-likelihood algorithm extracts the most probable falsifying trace. Two case studies exercise the pipeline. On a GPT-2 computer-aided process-planning (CAPP) model with 100% test accuracy, the pipeline quantifies the probability mass greedy decoding hides, but that is reachable with sampling; and identifies the smallest training fraction at which an ordering requirement holds population-wide, neither of which test accuracy can report. We then verify the SMILES molecular generator with a 50x larger vocabulary. The only change is an external chemical-validity oracle, and the pipeline identifies the gap between structural completeness and chemical validity.

Feedback-based coding schemes have demonstrated substantial performance gains over today's open-loop coding schemes. Unfortunately, these gains are usually achieved in idealized settings with perfect feedback. Over the last few years, machine learning-based schemes have been shown to be promising solutions for implementing feedback-based codes, particularly when combined with short-block-length open-loop error correcting codes (ECCs) in a concatenated coding structure. However, existing ML-based feedback schemes remain agnostic to the outer code's structure, potentially misallocating feedback resources on error patterns already correctable by the outer ECC. To address this, we propose MaskCode, a Transformer-based inner feedback code for concatenated coding systems, which explicitly incorporates structural knowledge of the outer linear block code into the inner feedback encoder design via two synergistic mechanisms: 1) a soft syndrome-based input that informs the encoder about potential parity constraint violations, and 2) a code-aware attention mask derived from the Tanner graph. We further show that end-to-end training with a differentiable belief propagation (BP) decoder offers no additional gain, as MaskCode's structure-aware design already internalizes the structural knowledge of the outer code; in fact, backpropagation through the iterative BP decoder introduces gradient explosion, which degrades rather than improves performance. Extensive evaluations on BCH and LDPC outer codes demonstrate that MaskCode consistently outperforms all baselines, achieving up to 1.5 dB SNR gain.

Code generation aims to automatically generate source code from task requirements and has attracted significant attention with the rapid advancement of large language models (LLMs). Despite remarkable progress, LLMs often struggle to generate correct code for complex software engineering tasks because task descriptions are frequently incomplete, ambiguous, or lack critical contextual information. Existing approaches primarily improve the capabilities of coding agents through more sophisticated tools, skills, and workflows, while largely overlooking the quality of the task requirements themselves. To address this limitation, we draw inspiration from software requirements engineering and propose WiseSpec, a novel requirements-driven agent framework for repository-level code generation. WiseSpec automatically constructs structured and information-rich requirements, assesses their quality through execution-based evaluation, and iteratively refines them to better guide code generation. Experimental results show that WiseSpec consistently outperforms all baselines, achieving an average improvement of 13.17% in %Resolved.

Giving an agent a file about a named expert can supply hard-to-find material, produce a recognizable persona, or change what the agent decides. These are different claims. We test each one. mimeo is an open-source tool that finds a person's public work, checks each extracted quotation against the cached source text, and writes a file an agent can load. Eight logged builds averaged 38 model calls; the check rejects 13.2% of extracted quotations. We tested four expert files with one coding-agent harness. Knowledge access was clearest: mimeo answered all 20 obscure, quotation-heavy questions; no closed-book condition answered more than 10. Keyword search (BM25) over the same pages answered 15-17, a gap this sample cannot resolve. Grounding showed one clear benefit: personas written from model memory misstated a documented position on 1-4 of 20 answers under every grader; the plain agent and mimeo never did. Every persona was easy to spot on short open prompts, and adding task material lowered identification by 18-23 points. mimeo was no more identifiable than a from-memory profile. Judgment transfer remained unresolved because both tests hit their ceiling: every condition found 94-97% of the problems planted in engineering tasks and scored 94-100% on 16 new application scenarios. An AI-judged "sounds like the expert" score changed with the judge: two of four preferred answers based on a model's stereotype, while two found no difference on the same text. That is a caution against relying on a single AI judge. The evidence supports mimeo as a compact, inspectable reference on a person, not as a demonstrated transfer of their judgment. Toolkit and expert profiles: https://github.com/K-Dense-AI/mimeo

Industrial post-training is a brownfield regime. Teams inherit a deployed checkpoint and must land targeted improvements under fixed compute and mixture budgets without regressing the rest. The maintained artifact is increasingly dataware: behavior governed by a curated post-training mixture, updated via bounded mixture patches rather than clean-slate retraining. From an industrial code-generation improvement effort, we offer a maintainer's perspective on why this work is hard in practice, distilling three recurring challenges, zero-sum mixture design, yield as the binding metric, and end-to-end integration under uncertainty, and arguing that progress depends less on one-off recipes than on an engineering discipline for programming dataware. In our case study, interventions that raised the conversion of teacher distillation into usable training data increased accepted supervision by 2.84 times while using the same solution teacher and four solution attempts per candidate problem. In our primary evaluation, the yield-engineered patch improved CodeForces pass@1 by +2.59 points (+3.11 pass@3) and held-out LiveCodeBench v6 pass@1 by +6.11 (+8.05 pass@3), all statistically significant across 16 stochastic evaluations of each benchmark from one fixed checkpoint per condition, with internal AIME and MATH regression suites within tolerance.

Agent working memory is heterogeneous. Objects such as instructions, artifacts, tool outputs, and agent-generated state play different semantic roles and exhibit different size, retention, and representation profiles. Recent work has begun to explore memory-management mechanisms that account for such heterogeneity. This work focuses on semantic heterogeneity and studies how it should shape the management and evaluation of working memory in coding agents. Across 55 archived coding-agent trajectories, we find that semantically different working-memory objects exhibit distinct retention and compression behavior. This heterogeneity motivates semantically informed memory management. We study two semantically informed strategies: an object-aware compression policy and a retrieval-based policy. Their evaluation shows that calibration gains may not transfer to held-out tasks, and that equal token budgets do not imply equal delivered context or management cost. A real-system replay further exposes serving limits that nominal budgets alone do not capture. Together, these results show why semantic structure matters for agent working memory and why evaluating memory-management strategies requires more than a nominal token budget. We organize these lessons into four levels: stored state, delivered context, management work, and task or process outcome.

Large language models (LLMs) have become an essential tool for assisting developers, yet we still lack knowledge on ways to effectively support their interactions during development activities. That is, the quality of interactions with a chat-based LLM still strongly depends on how developers phrase prompts and which information they include. Our goal is to evaluate whether interventions into these interactions with LLMs have an effect on software developers---be it harmful or beneficial. To this end, we conducted a four-month longitudinal study with third-semester computer science students working on a full-stack Web development project using chat-based LLMs under three conditions: (1) a \emph{context}-aware group received intent-based conversation augmentation, (2) a \emph{proactive} group received follow-up suggestions and tailored advice, and (3) a \emph{control} group without intervention. Our augmentations are minimal: (i) to reduce confounding factors and (ii) to isolate treatment effects. Analyzing interaction logs and user surveys revealed no major differences in interaction patterns, indicating no detectable harmful effects in the measured outcomes when intervening in interactions. Moreover, we observed trends of increased satisfaction with the \emph{proactive} treatment. The results indicate that even with minimal interventions, dynamic guidance mechanisms for developer-LLM interactions show observable effects, such that more severe augmentations may have the potential to substantially improve developer satisfaction.

Railway foreign object detection (RFOD) is critical to safe railway operation, yet scarce real positive samples incompletely represent task-relevant variations in object scale, intrusion relation, railway scene, illumination, and adverse weather. Existing synthetic augmentation can improve RFOD detection, but its gains lack an explicit account of the task-relevant deficiencies complemented by the generated data. We therefore introduce RailSyn, a diagnosis-guided framework comprising a real-referenced Inspector and a requirement-aligned Generator. The Inspector constructs a variable-radius empirical cover from finite real observations to localize candidate completion regions and profile synthetic pools. The resulting audit identifies railway-context, intrusion-semantic, and visual-consistency requirements; the Generator addresses them through domain adaptation, agent-planned placement and physical contact relations, and plan-consistent conditional refinement. Using the Inspector, we further trace representation-space changes across generation variants; the complete system attains a local-shell occupation of $C_{gap}$ to 13.64%, which measures generated coverage of real-derived completion regions. Extensive experiments show AP50--95 gains of up to 4.9 points and consistent improvements across nine mainstream detectors, demonstrating broad cross-architecture utility.

Coding agents are increasingly used for software engineering tasks, including bootstrapping projects from third-party repositories whose integrity cannot be assumed. Prior work on repository poisoning largely focuses on attacker-controlled injection and disguise, but developers also shape risk through everyday invocation choices: what task to delegate, how to phrase the request, and which skills or rules to supply. We term these user-side choices Prompt-Level Configurations (PLCs) and introduce CIPR (Coding In Poisoned Repos), the first benchmark that systematically varies PLCs in poisoned real-world repositories. CIPR comprises 1,920 instances across 20 repositories, four task types, three social-media-grounded prompt styles, and three skill/rule conditions, and measures attack success rate (ASR) and agent alert rate (AR) using automated runtime and trace-based oracles. Our evaluation reveals two key insights: (1) Vulnerability is highly context-dependent, with task type creating up to a 4.5-fold difference in ASR, with test-execution task forming a silent attack surface (high ASR, low AR). (2) Prompt expression shifts risk indirectly: underspecified prompts reduce ASR by truncating execution depth; noisy prompts exhibit a directional trend toward suppressing alerts by making malicious content less conspicuous. These findings highlight that coding agent vulnerability is not a static property, but a dynamic outcome shaped by everyday user configurations.

Existing approaches for synthesizing Partial Differential Equation (PDE) solvers predominantly rely on autoregressive models, yet their global left-to-right decoding incurs substantial redundancy when addressing inherently localized bugs. In this work, we challenge this inefficient paradigm and propose DiffPDE, a framework leveraging discrete diffusion language models for targeted code repair. By introducing a localized re-masking and infilling strategy, DiffPDE regenerates only erroneous regions while preserving correct context, naturally aligning generation with the sparse nature of PDE errors. Furthermore, to handle coupled bugs requiring sequential interventions, we present Iterative Debugging GRPO (ID-GRPO), a reinforcement learning scheme that enables multi-round debugging within single trajectories via intermediate rewards. Experiments on PDEBench show that DiffPDE achieves competitive accuracy, outperforms same-scale AR models, and significantly accelerates repair.