AI Software Engineering

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.

AI reviewers can now produce many specific criticisms, but more criticism is not necessarily a better review. A review may miss a consequential weakness or retain an allegation that available evidence does not support. These failures require opposite corrections, yet generation-oriented systems and aggregate measures obscure the distinction. We therefore recast AI-assisted review as evidence-guided refinement of a structured concern set, with omission and overcritique treated as separate risks. Building on this formulation, we introduce EquiReview-R, which resolves existing concerns against localized evidence, searches for missing issues from independent and review-conditioned perspectives, and returns stop, continue, or defer. To expose the failure mode that motivates this design, we construct an evidence-linked trajectory corpus. Its retrospective analysis shows why revision must precede further search: nearly all concerns in a high-recall review lack a definitive evidential disposition, while an earlier refinement mechanism cannot revise them. On a frozen cohort of previously unseen papers, EquiReview-R satisfies the prespecified non-inferiority criterion for major omission, reduces major overcritique from 15.5% to 8.1%, and attains a one-sided omission upper bound of 9.9% while stopping on 52.4% of papers. Computation-matched controls, controlled pairs, and ablations show that the gain comes from revision rather than extra inference or shorter output. We release the corpus as ReviewTrace, an evidence-linked resource for studying review revision, disagreement, and provenance.

Context: Architectural Design Decisions (ADDs) capture the rationale behind the structure and evolution of software systems but are rarely documented explicitly, and are often hidden inside source code commits. Recovering them is important for Architectural Knowledge Management (AKM). Problem: Extracting ADDs from commits is challenging due to their implicit and unstructured nature. Large Language Models (LLMs) have shown strong capabilities in understanding code and text, yet their effectiveness for this task remains underexplored. Study: We present a preliminary study using four LLMs (Gemini 3 Pro, DeepSeek R1, Kimi K2, Qwen3) with zeroshot and fewshot prompting on 30 developer-written ADDs from open-source projects. We score outputs with ROUGE-L, BLEU, METEOR, and BERTScore, and one author manually reviews the Gemini outputs. Results: All models reach a BERT-F1 above 0.81, and fewshot prompting improves alignment (Gemini BERT-F1: 0.828 to 0.847). However, the generated ADDs are often too long, implementation-focused, and miss the rationale behind the decision. This highlights opportunities for architecture-aware LLM systems and automated AKM.

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.

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

LLM agents increasingly diagnose incidents and propose remediations. In a GitOps workflow, applying a fix means editing a version-controlled config file, and the obvious implementation, having the model author the edited file or a diff, is what practitioners reach for first. Evaluating that choice on real Kubernetes manifests, we find no text-generation strategy is safe for unattended automation. Unified diffs are unsafe: under strict patching almost none apply, but that is an artifact, since a tolerant tool (GNU patch) applies 96%, yet silently misapplies about 1 in 7 (14-20%) with no error signal. Full-file rewrite is capability-dependent: a small model corrupts the file, while a frontier model is usually correct but non-deterministic (it silently drops a field or edits a neighbor on some runs) and must regenerate the whole file, costing O(file size) per edit. We present an alternative that separates the semantic decision (which resource, field, and value) from the syntactic act of editing the file. The agent emits only a structured field-change intent; a deterministic pipeline indexes manifests by (kind, name), locates the target scalar's exact character span via the YAML parser's node position marks, and replaces only that span in the raw text. Because the file is never re-serialized, the diff is minimal by construction, formatting and comments are preserved, and the edit is correct and deterministic independent of the model, at O(1) generation cost. The contribution is the pairing of an LLM-proposed intent with a deterministic, fail-closed application contract for GitOps. We implement it in KubeAstra (Apache-2.0) and release the benchmark. Our claim is scoped to faithful application of a known change; whether the change is right is left to human PR review.

AI is increasingly used in the R&D process that produces future AI systems. We study the conditions under which this feedback becomes self-amplifying. Our model describes how the rate of AI capability growth depends on baseline research productivity, recursive feedback, and the increasing difficulty of research progress. We derive a recursive reproduction number, $\mathcal{R}_{\mathrm{AI}}$, that determines whether improvements are amplified or damped across development cycles. This quantity compares the strength of feedback with the rate at which further progress becomes more difficult. When $\mathcal{R}_{\mathrm{AI}}>1$, the effects of improvements compound across development cycles, placing the system in a self-amplifying regime. When $\mathcal{R}_{\mathrm{AI}}<1$, their effects weaken across cycles. The transition depends on the structure of the AI R&D feedback loop and need not occur at any particular level of model capability. A system can therefore enter a self-amplifying regime before acceleration becomes visible, while rapid progress can also occur without self-amplification. Higher baseline research productivity can accelerate progress without changing whether the system is self-amplifying, but the duration of the development cycle becomes a limiting timescale for amplification. Increasing research difficulty can end a period of self-amplification. Extending the model to multiple research actors shows that improvements shared across organizations can make the overall research ecosystem self-amplifying even when no individual actor is. The framework identifies measurable properties of AI R&D systems that can help distinguish recursive amplification from rapid progress driven by other sources, including the strength of recursive feedback, how effectively improvements propagate into successor systems, cycle duration, and the increasing difficulty of further progress.

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.

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.

Code-level autonomous research loops (ARLs) have recently emerged as a concrete object of study in automated machine learning research. In such loops, an LLM agent proposes modifications to an experimental training pipeline, executes the modified pipeline, and retains edits that improve a verifiable in-loop metric. Although executable metrics may appear to provide a reliable signal of progress, it remains unclear whether repeated metric-driven code editing leads to genuine improvements that generalize beyond the loop. We provide a systematic diagnosis of this question. Across various experiment settings, we identify a robust failure mode that we call \textbf{algorithmic mode collapse}. In this regime, surface-level edit diversity remains stable, but semantic and mechanism-level diversity collapse: the agent continues to edit different lines of code while repeatedly proposing the same kinds of algorithmic changes. This collapse is accompanied by a widening gap between in-loop metric gains and gains measured on independent held-out evaluations. We then propose Diversity-Aware Proposal Sampling (\textsc{DAPS}), a lightweight mitigation that combines category-coverage reweighting, persistent edit memory, and a validation gate. Under a three-tier protocol separating the in-loop metric, the audit metric read by the gate, and a blind metric no loop component ever accesses, \textsc{DAPS} reduces semantic-cluster decay of edits by $69.1\%$ and improves relative faithfulness by $83.7\%$ blind and $81.6\%$ audited, while preserving in-loop optimization speed. We provide the code in Github \href{https://github.com/BokwaiHo/arl-mode-collapse}{repository}.

Generating multiple diverse and high-quality solutions is valuable for many applications, such as code-test generation and drug discovery. However, Large Language Models (LLMs) tend to converge on a single high-confidence solution during inference, limiting exploration of alternative valid solution paths. Existing test-time methods promote diversity through tree-like search and prune semantically similar branches using response-level semantic embeddings. However, we find that such embeddings are easily confounded by linguistic and stylistic similarities, making it difficult to distinguish genuinely distinct solution paths. To address this, we introduce Answer Probing, which probes the potential answer an LLM would reach from an intermediate reasoning path. We demonstrate that the hidden states of probed answers more effectively differentiate distinct solution paths than semantic embeddings, and the perplexity of probed answers serves as a practical proxy for reasoning correctness. Based on these findings, we propose Answer Probing-Guided Tree Search (APTS), which guides the tree search by the probed answers' hidden state similarity and perplexity. Experiments on three reasoning tasks across two LLMs show that APTS consistently enhances solution diversity, demonstrating its effectiveness and robustness.

Large language models (LLMs) frequently generate source code containing vulnerabilities, yet little work studies the internal mechanisms that distinguish safe from vulnerable generation in them. In this work, we systematically perform a mechanistic interpretation of LLMs, aiming at both understanding how code safety-vs-vulnerability is represented or driven by components in an LM and turning the insights into actionable steering strategies to encourage safer code generation. To this end, we introduce CodeSec-Pairs, a dataset of 9,342 Python safe-and-vulnerable contrastive code pairs, sampled from Llama-3.1-8B-Instruct. Utilizing the dataset, we explore approaches to localize layers and attention heads that relate to code safety, and further experiment with different steering strategies for inference-time vulnerability reduction. In particular, we propose DuoSteer, a double-steering approach that simultaneously applies safety and code-correctness steering to attention heads. In experiments over five vulnerability types, DuoSteer leads to an average of -26.9% vulnerability rate reduction and +7.5% functional correctness improvement, which outperforms not only other steering variants but also prompting and supervised fine-tuning baselines. The advantage also replicates on Qwen-2.5-Coder-7B-Instruct with another 2,500 contrastive pairs sampled from that model.

Programming with AI is increasingly agentic, users prompt LLMs to directly edit their code and review the changes, with adoption growing especially for web development tasks. Despite this growth, most NLP work uses offline evaluation and lacks support for online studies, losing insights into how programmers truly use coding agents. We release VibeJam, a browser-based user study platform for users to collaborate with AI agents to develop websites. VibeJam enables agent customization and uses the open-source Aider agent by default, and to mirror downstream use, we add diff review, chat and plan modes, and live website previews. In a pilot study with 55 released, game-based website creation tasks, five experienced AI programmers rate our system as fun, simple, and resembling commercial tools, while 13 junior students use VibeJam to make websites of higher quality than agents in the same task. We open-source VibeJam to spur extensions and support studies on how coding agents can help users.

Localizing issue-relevant code regions is a critical step in automated software engineering. However, due to their reliance on sparse trajectory-level signals, existing methods cannot identify which per-turn actions are effective and often discover correct code regions during exploration but fail to commit them. To address these limitations, we propose an action-aware reinforcement learning method that combines a per-turn reward sequence rewarding both the discovery and commitment of gold code regions with an action-level advantage estimation scheme that isolates each action's credit by grouping turns sharing the same exploration context. Extensive evaluations show that our method improves the average F1 over the state-of-the-art (SOTA) by 1.58% on SWE-Bench Verified and 8.55% on SWE-Bench Pro, with our 4B model outperforming baselines up to 8x larger. Our code is available at https://github.com/donian00/A2Agent.

Repository exploration is a distinct and costly stage of coding-agent pipelines: before generating a patch, an agent must identify which repository files are likely to matter. We study whether this stage can be delegated to lower-cost models while retaining useful localization quality. Using our IssueLoc-Bench, we evaluate five explorer models under the same read-only interactive interface on 499 SWE-bench Verified-derived tasks and 500 tasks from 153 additional repositories. We measure early candidate discovery, top-three gold-file coverage, strict file-set recovery, agent time, and token usage, with paired instance-level uncertainty and repository-clustered sensitivity analysis. The highest-quality explorer leads across localization metrics, but substantially cheaper operating points emerge: depending on the model and evaluation arm, lower-cost explorers retain approximately 78-94% of the reference Hit@3 and 73-92% of its F1 while reducing mean agent time by 41-88% and token usage by 84-95%. The preferred operating point depends on how localization is consumed downstream: ranking and coverage metrics characterize recoverable candidate handoffs, whereas F1 and exact match characterize restrictive file gates. These results support treating repository exploration as an independently measurable and budgetable stage of modular coding agents, with explorer selection guided by the downstream handoff contract.

Interactive web application generation requires models to produce usable HTML, CSS, and JavaScript applications from natural language requests. Unlike conventional code generation, application quality depends on multiple user-facing functional requirements, each often tied to localized code regions such as event handlers, state updates, DOM fragments, or CSS selectors. Standard GRPO collapses these structured outcomes into a single sequence-level reward and applies the resulting advantage uniformly to all tokens, weakening credit assignment. We propose \textbf{Rubric-to-Code Credit Assignment} (RCCA), a reinforcement learning framework that converts rubric-level functional feedback into localized optimization signals over generated code. RCCA builds training tasks around explicit functional rubrics, uses a hierarchical reward to separate format, source-code, runtime, and functional failures, and aligns evaluator-generated textual attributions with responsible code spans and generated tokens. The resulting model, \textbf{Ling-RCCA-Flash}, scores 41.25 on MiniAppBench, improving Ling-3.0-Flash by 32.20 points and slightly surpassing Claude Opus 4.5. It also reaches 76.19 on ArtifactsBench, improving the SFT model by 4.48 points and establishing a new top score under the official ArtifactsBench leaderboard setting by surpassing the GPT-5 score by 3.64 points, suggesting transferable implementation-level gains.

Coding agents are now commonly evaluated on the SWE-bench family of benchmarks, whose tasks are built from curated GitHub issues: long, structured, and information-rich. Real user requests, however, are typically far shorter and less structured. To characterize this gap, we define a six-category information taxonomy and four dimensions of linguistic style, and apply them to real user prompts from SWE-chat and problem statements from SWE-bench Verified and Pro. We find that requests carrying only a problem statement, alone or with limited additional context, account for 88% of real prompts but just 7% of benchmark problems. Furthermore, 87% of real prompts are casually written whereas 94% of benchmark problems are formal. Guided by these observations, we introduce RealSWE, 381 multi-variant task families derived from SWE-bench Verified and Pro. Variants within each family share the same underlying task and gold patch while differing only in information composition and linguistic style. Evaluating seven contemporary LLMs with RealSWE, we find that i) realistic inputs reduce resolution rates by 6.4 pp on average and can change model rankings. Controlled analysis further shows that ii) including Desired Behavior and Motivation significantly affects performance, whereas Environment Information and Reproduction Steps merely add tokens without measurable benefit; iii) linguistic style has only small, model-dependent effects. These findings provide actionable guidance for users and agents: explicitly stating the desired behavior and motivation, which most real prompts omit, substantially improves the LLM's software engineering performance.

Coding agents increase development velocity but also technical debt. Prior work reports only average effects across adopters, hiding wide differences between teams. We introduce RAMP (Repository AI Maturity Profile), a four-level cumulative maturity model grounded in version-controlled artifacts that teams commit to configure AI tools. RAMP runs from behavioral rules and coding standards through named agent definitions to multi-agent orchestration, with observed practice concentrated in the first three levels. Across 441 repositories the levels behave as a cumulative scale, and independent human annotation reproduces RAMP's repository-level labels on 97% of a held-out sample. Adoption is cumulative, forward-only, and set-and-forget: 73.8% of artifacts are committed once and never modified. Re-estimating an existing agent-adoption panel within each stratum, agents accelerate development regardless of maturity (28-38% more commits), but quality diverges: among agent-first repositories, where the contrast is identified, those without committed AI configuration show roughly twice the increase in cognitive complexity (+53% versus +27%) and 1.7x the increase in static-analysis warnings. Because maturity is observational, correlated engineering discipline or model capability may explain part of the gap; we present these findings as hypothesis-generating and release RAMP as a reusable instrument.

Software increasingly functions as part of the scientific instrument itself, making failures in scientific code capable of compromising not only program behavior but also the evidence underlying scientific conclusions. Yet existing evaluations of coding agents largely emphasize aggregate task success, providing limited insight into why agents fail when repairing scientific software. We introduce \textbf{SWE-bench Science}, a repository-level benchmark for scientific software engineering comprising 119 tasks from 98 GitHub repositories across 20 scientific domains. Each task is organized into one of three paradigms: Issue-driven, Expert-exploratory, and Engineering-integration. Even the best-performing agent, \textbf{Claude Code with Opus-5 (max), achieves a pass@1 below 50%}, highlighting the substantial challenges posed by scientific software engineering. We identify four recurring failure mechanisms: deficits in scientific knowledge or abstraction, misguided exploration or surface-level repair, incomplete repair coverage or system integration, and failures to generalize scientific knowledge beyond observed cases in our analysis. We further conduct a paired ablation that removes explicit scientific guidance while preserving the repository and executable engineering context. The results show that scientific knowledge is not uniformly beneficial: well-grounded information can constrain repair and improve average performance and token efficiency, whereas poorly aligned guidance can induce anchoring and does not necessarily improve exact repair success. Together, SWE-bench Science provides a broad testbed for studying both the capabilities and failure mechanisms of coding agents in scientific software engineering.

Autonomous research systems are increasingly capable of executing long research workflows, yet automation alone does not ensure that the resulting process remains scientifically grounded. We introduce AutoResearch, a two-stage system that connects Idea Generation with Idea Execution to address both how research ideas are formed and how they are reliably established through experimentation. In Idea Generation, AutoResearch continuously integrates emerging research signals with accumulated domain knowledge, identifies transferable mechanistic insights, and uses multi-model generation and cross-review to produce grounded, testable research plans. In Idea Execution, coordinated agents decompose these plans into experiments, iteratively implement and diagnose them, and employ independent evidence-based review before accepting research conclusions. Across representative settings in cross-modal retrieval, systems optimization, and benchmark-driven machine learning, AutoResearch turns generated ideas into measurable progress, detects and corrects unreliable experimental results, and makes evidence-conditioned decisions to continue, revise, or terminate research directions. For example, on RSICD benchmark, an AutoResearch-generated idea improves mean Recall from 32.84 to 34.69, while recording only 5 audit-confirmed issue events compared with 11-27 for other autonomous research systems. These results demonstrate a research process in which meaningful insight is grounded before experimentation and conclusions are grounded before acceptance: Insight In, Hallucination Out.

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

Autonomous vehicles depend on large safety-critical software stacks, where weaknesses reachable from adversarial inputs may affect steering, braking, or other control decisions. Static analysis can identify candidate sites, but dynamically confirming exploitability requires executable test artifacts that are difficult to construct manually. We investigate whether large language models (LLMs) can automate this process for Autoware, an open-source autonomous-driving stack. We perform compiler-precise static analysis across 185 packages, identifying 1,375 decision rules, 2,274 validation checks, and 482 input-to-safety-output flows, from which we derive a weakness taxonomy and sample 740 reachable sites. Two local open-weight LLMs, a no-static-context ablation, and a naive-template baseline generate 3,700 artifact sets, which are compiled against the real build under sanitizers, repaired through compiler-in-the-loop feedback, and fuzzed when executable. The main result is a build-integration failure taxonomy showing that 80% of first-shot compilation failures arise from dependency wiring rather than program logic. The reasoning model compiled 64% of harnesses on the first attempt, compared with 6% for the code-specialized model. Repair achieved full object-compileability for the reasoning model only through extensive stubbing; fewer than half of its harnesses reached the fuzzer, and all 37 observed crashes originated in stubbed code rather than Autoware. No candidate weakness was dynamically confirmed within budget. These results show that build integration, not candidate generation or fuzzing, is the primary barrier to reliable LLM-assisted dynamic analysis of full autonomous-vehicle software stacks.

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

With the rapid advancement of large language models (LLMs), research idea generation has attracted increasing attention. Existing approaches enable LLMs to retrieve relevant literature and propose novel ideas for research areas. However, current evaluation practices for idea generation remain fragmented and lack objective standards, often relying on direct LLM scoring, which limits their ability to provide unified and reliable assessments across a coherent distribution of generated ideas. To address this challenge, we propose LigBench, an automated evaluation benchmark that enables fine-grained and reliable evaluation of AI research ideas, consistently applicable across different generation distributions. In addition, we introduce PAIR-IQ, a dataset tailored for training pairwise idea judgment models and serving as an auxiliary reference to support more objective comparative evaluation. Extensive experiments demonstrate that LigBench achieves stable and interpretable evaluations, significantly improving alignment with expert judgments. Furthermore, models trained on PAIR-IQ exhibit enhanced ranking accuracy and robustness, establishing a principled standard for scalable and objective research idea assessment.

The extent to which large language models for code rely on memorization over genuine understanding remains highly debated. While current literature frequently reports widespread memorization, evaluating the underlying probing techniques across dense architectures reveals a severe breakdown in their utility at scale. Traditional encoder-style probes using perturbations such as synonym fuzzing or dead-code insertion struggle to expose memorization in scaled models, even on known-contaminated benchmarks, and decoder-style probes that rely on log probabilities show similar performance degradation. The specific mode of failure for these probes, particularly why such techniques disrupt smaller models but fail to impact larger ones, motivates us to untangle representation load from memorization rather than treating them as a single phenomenon. By applying invertible mathematical transforms to numeric problems, we isolate these two factors and reveal that scaled encoders successfully absorb substantial representation load while still converging on the correct family of solutions. In practical software engineering, this ability to adapt to varying surface forms is what truly matters for usability and generalizability in LLM and agentic applications. Whether a specific solution was seen during training becomes a much less pressing question because although memorization inflates scores on contaminated benchmarks, factoring out representation load makes it debatable how much we should truly care if a functional answer was originally memorized. Future evaluations must therefore be built around separating these phenomena rather than relying on methodologies that quietly entangle them.

Long-running LLM agents act through tools, and a single step can send an email, merge a pull request, or wire a payment. The steering decision is the pre-commit choice at that boundary: proceed, or hold for human or policy review. We introduce SteerBench-Work, an incident-anchored, bidirectional benchmark for that decision in workplace agents across developer operations, customer service, finance, legal, medical, HR, and security. Release v2026-05 contains 106 scenarios anchored in public incidents, paired evidence-reversed mirrors, and calibration controls, with labels split nearly evenly between proceed and hold so the two error directions get near-identical numbers of chances. A model sees the proposed action and the available evidence, returns a gate decision, and is scored on whether it crosses or holds the boundary correctly. Across 30 model conditions the failures run almost entirely in one direction: models wrongly hold authorized, evidence-cleared work on 28.1% of opportunities and wrongly allow unsafe work on 1.0%. The hardest cases are risk-resolved commits, where signed or structured evidence has already cleared a real risk trigger, and models score markedly worse on evidence-reversed mirrors of famous incidents (63.8%) than on the incidents themselves (98.5%). General capability is not the same as steering calibration: higher-capability models often over-refuse at the commit boundary, and more reasoning can repair a weak gate while leaving a calibrated one flat. The public leaderboard is at steerbench.com.

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

Privacy documents (e.g., privacy policies) are a central mechanism through which digital services disclose data practices and seek user consent. Over the past decades, research on privacy documents has expanded significantly, encompassing not only traditional privacy policies but also short notices (e.g., privacy labels) and interface-level transparency mechanisms. As this research area continues to grow, it has become increasingly difficult to obtain a coherent view of how privacy documents are created, analyzed, evaluated, and maintained across their lifecycle. This SoK provides a unified, lifecycle-oriented view of privacy documents from a software engineering perspective. We systematically review and analyze 290 papers published between 2010 and 2025, organizing them around five research questions that examine how privacy documents are (1) defined and scoped, (2) generated, (3) analyzed and extracted, (4) checked for inconsistencies and noncompliance, and (5) evaluated and improved for usability. Building on our findings, we identify 15 key research trends and 21 open opportunities. We further chart four broader research directions that highlight (i) emerging challenges in AI-centric platforms, (ii) the need for diverse and up-to-date data foundations, (iii) LLM-based unified policy-code analysis, and (iv) dual usability for end-users and developers. We hope this SoK provides a shared foundation for future research on privacy policies and privacy documents.

This paper reports a single, fully instrumented case study of a large-scale architectural refactoring by an AI coding agent under a specification-first protocol, with no human review of the generated code and no pre-existing oracle to validate the target behaviour. The task, dismantling a central invariant across a large interdependent codebase, was assessed by the author as effectively infeasible through incremental refactoring, the kind of change that conventionally calls for a rewrite instead. Under the protocol described here, the agent completed it successfully. The system is a 717,725-line production TypeScript application across 3,648 files. The task required dismantling a core lifetime invariant: the guarantee that a UI panel remains open for the duration of an AI request. The target behaviour was that a streaming generation survives the closing of its panel and can be reattached, on reopening, to the same live stream with no loss or duplication. The protocol: formal specification by the agent, 14 refinement cycles auditing that specification against the source code, atomic implementation, a compile/test feedback loop, then 17 verification cycles auditing the code against the frozen specification. Across 31 audit passes, 201 defects were corrected before any human executed the program. The convergence criterion was empirical: two consecutive verification passes returning zero findings. The change touched 189 files (31 new); with the extraction phase, the two commits total 288 files, 34,770 insertions, 16,422 deletions. Across the first and roughly thirty later sessions, the software behaved as specified, no bug observed. Elapsed: three days; cost: USD 2,430. The full specification and raw session logs, 1,500+ pages in French, are published as evidence, allowing inspection of the process and submission to a language model for consistency checking.

Self-correction is particularly useful when a failure constrains the next repair. Coding agents benefit from this property because compilers, tests, and execution traces turn many failures into typed recovery signals, but broad language-agent tasks often expose only a coarse task failure. This creates a tension for generic recovery playbooks: they broaden the agent's context precisely when the system needs a narrower repair interface, mixing incompatible signals for invalid actions, missing procedures, and strict-format errors. Our insight is that development-set failures can recover part of the missing diagnostic substrate by deciding which recovery interventions are admissible before test-time correction. We propose DARC, a diagnosis-guided recovery harness that profiles task-family failure modes, prunes mismatched interventions from a shared recovery library, and freezes a verifier-selected success-cost policy for deployment. This causal order makes correction selective: the harness first determines what kind of failure can be repaired, then decides how much recovery evidence to spend. In ALFWorld, AppWorld, and XBRL Finance, the same protocol yields an action-validity harness, a procedural-recovery fallback, and a format-precision retrieval policy; in each evaluated setting it improves average task performance over base agents and broad playbooks while reducing environment steps or retrieval budget. Our experiments show that failures need not trigger uniformly more context: DARC turns self-correction from prompt expansion into recovery-interface design. DARC provides a practical route toward more reliable agents in domains where compiler-like feedback is absent: making failures actionable before making contexts larger.

When a coding agent obeys a rule, it may simply have been going to do that anyway. Existing instruction-following benchmarks cannot tell the difference: they concentrate rules in the user turn, while coding-agent benchmarks emphasize final task success. We introduce Harness-IF, which scores operational rules one at a time from execution evidence: 60 realistic multi-turn coding items drawn from a 642-rule library, 256 rules receiving verdicts, placed on the five configurable surfaces a deployed agent reads. To separate compliance from coincidence we introduce Against-Prior Accuracy (AP-Acc), which scores only rules labeled as opposing unprompted defaults, observed by re-running tasks with the rule withheld across nine probe builds and curated otherwise. Across 12 frontier models, accuracy spans 72.1-85.9% and AP-Acc 66.1-78.6%; every model is worse on against-prior rules, by 3.6 to 7.4 points (mean 5.81), and the direction survives a common-support analysis with item-clustered intervals. Aggregate scores therefore overstate compliance by a model-specific margin: prior control leaves the top build unchanged and exchanges three adjacent rank pairs. A counterbalanced conflict pilot on nine separate builds adds a second result: pooled precedence does not follow prompt depth, with system prompts, project files, and user instructions ahead of tool and skill descriptions.

Large Language Models (LLMs) are increasingly integrated into software engineering workflows, helping developers write, debug, test, and maintain code. While prompt wording and structure are known to influence model performance, the impact of psychologically inspired prompt framings remains unexplored. This study investigates whether different psychology-based communication strategies that humans use to persuade or motivate others can lead to more effective prompt framing, which may, in turn, affect LLM behaviour in coding tasks. Drawing on Yukl & Falbe's well-known taxonomy, we operationalized eight influence tactics (like rational persuasion, ingratiation, and exchange) into reproducible prompt templates. These prompt templates were evaluated across five leading open-weight LLMs using two widely adopted benchmarks: LiveCodeBench and SWE-bench Verified. We assessed the resulting code output on four key software quality dimensions: functional correctness, quality, maintainability, and security. Our results show that certain influence-induced prompt framings, particularly those emphasizing urgency, were associated with reduced correctness and security. This work presents the first large-scale empirical study of influence-induced prompt framing in software engineering tasks, offering insights into how linguistic cues may shape LLM outputs. We conclude with practical insights for designing transparent and interpretable human-AI interactions in code generation.

Generative engines are reshaping the web ecosystem by making citations a key mechanism for allocating attention, attribution, and downstream value. This creates a strategic tension: content providers are incentivized to optimize for model citation, while platforms must preserve answer quality and trustworthy attribution. We show that this tension can escalate into citation wars. In repeated simulations, state-of-the-art generative engine optimization (GEO) attacks adapt to conventional defenses by producing citation-seeking rewrites that degrade document quality and introduce unsupported claims. To study this problem, we formulate the supplier--platform interaction as a repeated Stackelberg game with partial monitoring. A local best-response analysis identifies when citation competition approaches an inert stationary outcome. Motivated by this finding, we propose a platform--creator mechanism called VCR based on verifiable-content rewards. Rather than only penalizing suspicious rewrites, the platform also credits rewrites that surface checkable factual substance, aligning creator incentives with answer trustworthiness. Experiments on three benchmarks show that VCR consistently achieves the largest Net defense-utility score, outperforming the strongest baseline by an average of 12.1 percentage points, and produces a win--win outcome under our empirical equivalence criterion.

Agentic coding READMEs like CLAUDE.md grow without bound in real repositories, stopping only when the repository retires or someone rewrites the file wholesale. We trace this to imperfect recall: appending an instruction is always cheap, but once an instruction's rationale is gone, deleting it without risking a correctness regression costs O(2^|D|) in a prompt of |D| instructions. We name the resulting divergence catastrophic remembering, the inverse of catastrophic forgetting around which continual learning is organized. First, we characterize this phenomenon across 247,694 instruction lifetimes in 1,867 repositories: agentic prompts grow without bound, more than tripling over their lifetime (+226%), gaining +4.9 net instructions every commit; further, the older an instruction gets, the less likely it is to be deleted (log-hazard -0.032/commit). Then, we show that prompt comments can halt the growth: inverting IFEval yields verifiable worlds whose optimal prompts are known, and there comments encoding latent reasoning remove 99.3% of excess instructions (+211.3% to +1.4%). Finally, applying the same inversion to WildIFEval, we show that prompt comments can improve real-world agentic instruction-following by up to 23.1%. If English is the new code, why don't we have comments yet?

Large Language Models (LLMs) have undergone a shift from stateless conversational interfaces to autonomous agents capable of multi-step planning, tool invocation, code execution, and maintaining persistent memory. When these agents operate with real-world privileges---calling APIs, modifying files, and querying databases---a compromised reasoning step can trigger unauthorized data access, irreversible state changes, or cascading failures, yet the security research community has not kept pace. To quantify the state of the field, we conducted a systematic literature review under PRISMA 2020 guidelines across six databases, screening 743 records and retaining 85 papers (2023--2025) on agentic LLM security. Attack research outpaces defense work by 3.9:1. Perception-layer vulnerabilities (prompt injection, jailbreaking, adversarial perturbations) dominate, accounting for 66% of papers, while action-layer vulnerabilities (tool misuse, code injection, sandbox escape) appear in only 4.7%, misaligned with real-world risk. Code execution security accounts for 3.5%, and tool-augmented agents 12%. We contribute a four-layer taxonomy mapping 13 vulnerability types across perception, brain, action, and interaction layers, and identify seven open problems centered on containment. Agentic LLM insecurity stems from architectural coupling, where weak isolation allows vulnerabilities to propagate across layers.

Complex software systems develop over timescales that exceed the lifespan of any individual coding agent. Most agentic software systems preserve continuity through persistent sessions, memories, managers or shared context. We introduce EvoX Genesis (hereafter, Genesis), which instead makes the software project persistent while allowing local agents to remain finite-lived. Genesis represents software as a persistent recursive world: each local world is situated by an accepted version and a repository path, finite-lived agents propose local changes, recursive delegation moves work across paths, and only accepted consequences advance the persistent version history. We evaluate this organization across formation, continuation and redevelopment. Starting from a repository with no compiler implementation, Genesis used DeepSeek V4 Flash to build a Rust-based C compiler with about 250k tracked lines; the run lasted over 120 hours, archived over 1,000 agent episodes and incurred only US$44 in model-token charges. The compiler passed the complete c-testsuite and most LLVM and Csmith tests. In a separate compiler world generated with GLM 5.2, development continued after repeated agent replacement while retaining full test performance. Genesis also reimplemented 13 MESA modules with over 100k Fortran lines as a Rust workspace with nearly 90k Rust lines; across six numerical workloads, it achieved median speedups of 1.55--6.87x. These results show that long-horizon software development can be organized around a persistent project rather than a persistent agent.

Large language model (LLM)-powered agents have rapidly evolved from code-completion tools into solvers of complex software engineering tasks. As developers collaborate with coding agents over time, their preferences emerge through repeated interactions and can be used to adapt agent behavior to better meet individual developers' needs. Capturing and reusing these preferences may reduce repeated corrections and improve developer-agent collaboration. Agent skills provide a lightweight mechanism for transferring experience without modifying model parameters. However, existing work primarily focuses on task-specific skills, and it remains unclear whether developer-specific skills distilled from interaction histories can generalize to future tasks. We propose a framework for extracting reusable developer preferences from interaction traces. It first generates personalized skills through rule-based bootstrapping and evidence-grounded refinement, and then evaluates them using a reproducible replay framework with an interactive, trajectory-conditioned LLM-based human developer simulator. We conduct an experiment on 206 real-world developer-agent sessions from 13 developers and compare personalized skills against no-skill, generic-skill, and other-user-skill baselines. Personalized skills provide small and inconsistent improvements over the no-skill baseline, whereas generic skills pooled across developers achieve the largest and most consistent gains. Further analysis suggests that personalized skills become more effective when developer preferences appear frequently, particularly when their histories contain multiple examples relevant to future tasks. These findings provide empirical insights into when developer-specific personalization is effective and demonstrate that broadly transferable procedural knowledge can be more robust than developer-specific preference signals.

Code review is credited with substantially changing a patch's code between its first submission and the version that eventually lands. However, prior work typically studied only the final merged patch without comparing it to the first submission. We present a function-level measurement that tracks 10,117 trajectories (each function followed across the numbered revisions of one patch series) through the patch history of the Linux IIO subsystem, comparing similarity scores against unrelated function pairs as a baseline. A naive reading yields near-total similarity, but this is largely an artifact of composition: 75.3% of tracked trajectories are never textually modified between versions, contributing a trivial 100% similarity that inflates the headline. Restricting to the trajectories with a real edit, semantic purpose is still largely preserved (mean similarity 0.990 vs. a 0.909 baseline), but drift appears to concentrate in the first review round mainly because later rounds contain more functions that nobody touched, not because edits become more conservative over time. After controlling for it, a statistically detectable but small residual effect remains. This points to an open question: whether near-ceiling similarity reflects preserved purpose or a measurement tool that cannot detect the significance of small, localized edits. We present this work as a first look and outline next steps.

Public chest X-ray repositories are widely used to train medical AI systems, yet their labels are typically extracted from radiology reports rather than verified directly on images. As a result, repository labels are often treated as image-level ground truth without validating whether they reflect what is actually visible in the radiograph. We introduce Repository Supervision Auditing (RSA), a framework that evaluates repository-derived labels against expert image-level annotations before model development. Using cardiomegaly in MIMIC-CXR as a case study, RSA compares repository labels with radiologist-reviewed image annotations, characterizes disagreement sources, and builds a curated cohort for deployment-oriented evaluation. Repository-derived cardiomegaly labels showed near-zero agreement with expert image-level assessment, identifying only 1% of expert-confirmed cases. Most discrepancies resulted from non-mention rather than explicit report negation, with expert-confirmed cardiomegaly identified in nearly half of studies assigned a repository-derived No Finding label. Using the resulting expert-curated cohort, a DenseNet121 model achieved a test ROC-AUC of 0.853. These findings show that repository labels may not reliably represent image-level truth and highlight supervision auditing as a critical step for developing trustworthy medical imaging AI.

As AI coding agents take on increasingly complex, long-horizon software engineering tasks, existing benchmarks are rapidly saturating and their evaluation quality has come under serious scrutiny: a recent audit found that nearly 60% of unsolved SWE-bench Verified instances contain flawed tests -- either overly narrow tests that reject correct solutions or overly broad tests that check unstated requirements -- and that frontier models can verbatim reproduce gold patches from training data. Code refactoring, which requires coordinated, behavior-preserving changes across many files, offers a substantially harder and more realistic test of agent capability, yet remains underserved by current benchmarks. We introduce SWE-Bench ProMax, an expert-curated, multilingual code refactoring benchmark of 170 instances drawn from real commits across seven programming languages (Python, Java, TypeScript, Go, C, C++, and Rust). Every instance undergoes rigorous, multi-stage curation that directly addresses the quality problems identified in prior benchmarks: issue descriptions are rewritten from scratch to provide precise, unambiguous specifications, and test suites are manually reviewed to remove overly narrow and overly broad tests. Tasks with insufficient complexity or limited cross-file scope are filtered out, yielding a benchmark of challenging, large-scale refactoring tasks that average 11.4 modified files and 261.6 lines of code per instance, substantially exceeding the scale of existing benchmarks. Experiments with frontier models under two agent scaffolds show that the best model achieves only 41.2% resolve rate, confirming that SWE-Bench ProMax presents a meaningful and unsaturated challenge for current AI coding agents. Our benchmark is available at https://huggingface.co/datasets/swe-bench-promax/SWE-Bench-ProMax.

AI coding agents now write a growing share of production code, and human security review does not scale at the rate code is generated. The agents in widest use are closed-weight, so a deploying team cannot read their internals. It can instead run an open-weight model as a reviewer over the agent's output. That reviewer's activations are readable. We ask whether reading those activations recovers a security signal that simply asking the same reviewer misses. We fit a single linear probe per model on a corpus of paired vulnerable-and-fixed Python functions, then test it without retraining on real disclosed vulnerabilities whose weakness type the probe never saw in training, across five open-weight reviewer models. On the vulnerabilities fixed by changing a single function, the probe scores the vulnerable function above its fix on 61-67% of cases for every model, beating the 50% chance line. It also beats the same model's prompted YES/NO win-rate read from its logits, under every prompt we try. Asking the model for a written verdict, even with chain-of-thought, returns the same answer on the vulnerable and fixed function most of the time and so cannot tell them apart. Model activations carry a code-security signal that prompting the same model misses.

GUI agents have advanced rapidly, producing a growing body of frameworks, benchmarks, and applications. However, this growth has outpaced the maturity of the field. GUI agents remain technically brittle, incompletely engineered, and insufficiently validated for sustained real-world use. They are evolving into closed-loop software systems. Within these systems, model reasoning is coupled with interface perception, execution feedback, recovery, and human oversight. This evolution calls for a software engineering perspective that remains largely absent from existing research. We address this gap by reviewing 336 GUI-agent papers from January 2018 to April 2026. Five research questions examine the research landscape, architectures, evaluation, software lifecycle concerns, and future opportunities. Our findings show that the field has expanded sharply since 2024, while mobile and web settings remain dominant. Architectures increasingly adopt modular perceive-reason-act loops, but recovery, human escalation, safety enforcement, and auditability remain underdeveloped. This architectural imbalance extends to evaluation. Evaluations are becoming more interactive, but they remain centered on task success and are difficult to compare across protocols. More broadly, existing studies provide limited support for testing beyond benchmarks and for maintaining agents after release. Observability, privacy engineering, and systematic human oversight are also underdeveloped. Together, these findings show that capability improvements alone cannot ensure deployment readiness. Future research should connect dependable execution with lifecycle-centered testing and reproducible evaluation. It should also integrate permission and privacy controls with cost-aware, human-centered governance. This integration is necessary to build dependable, maintainable, secure, and deployable GUI-agent systems.

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

LLMs have demonstrated strong capabilities in code generation and automated program repair, but migrating an entire repository rarely produces a runnable application because long-horizon translation challenges LLM-based agents' ability to maintain repository-level migration objectives. In this work, we propose Entropy-based Code Adversarial Translation (ECAT), a multi-agent framework for automated Android-to-HarmonyOS repository migration. ECAT formulates repository migration as adversarial entropy minimization through a generator-discriminator architecture. The discriminator measures migration quality using a unified metric called Code Entropy and produces text gradients that specify both file-level generation directives and the skills needed to execute them. Guided by these optimization signals, the generator iteratively updates the repository, and each update is accepted only if it reduces Code Entropy. Repeated generator--discriminator interactions progressively drive the migration from an initial template toward a functionally complete HarmonyOS repository. Successful low-entropy trajectories are further distilled into a self-evolving memory tree, enabling transferable migration knowledge across repositories. We also introduce A2H-RepoBench, the first real-world benchmark for Android-to-HarmonyOS repository migration, covering applications from tens of thousands to hundreds of thousands of lines of code. Evaluated by node alignment and an agent-based functional judge, ECAT achieves 74.7% overall migration quality and consistently outperforms existing agent-based methods across repositories of different scales.

Visual modality has recently been explored as a way to compress textual tokens, including rendering code as images for static code understanding. We study whether this representation can serve as operational context for agentic coding, where an agent must navigate repositories, edit source files, and verify executable patches. Using SWE-bench Verified, we evaluate rendered code in repository-level repair workflows and introduce controlled agent settings to separate unguided repository exploration from more structured repair stages. Our results show a mixed picture. Rendered code consistently reduces prompt-token cost, but the savings do not increase linearly with the nominal visual compression ratio. It largely preserves end-to-end repair accuracy, but does not overcome the performance limits of the underlying model or agent architecture, and can become unstable under aggressive compression. Further analysis suggests that visual code is most useful when raw source reading is a major bottleneck; once repository localization is structured, much of the remaining cost comes from patch--test trial-and-error, where visual compression has limited leverage. Overall, our study positions rendered code as a viable but conditional compression mechanism for realistic coding agents.

Large language model-powered coding agents are increasingly used to modify existing code repositories, for example, by adding features or fixing bugs. Yet existing repository-level benchmarks typically evaluate only whether the final patch passes tests. Satisfying a user request requires a long chain of interdependent reasoning and decisions: an agent must recover explicit and implicit requirements, formulate a repository-grounded implementation plan, and translate it into correct code. A pass/fail outcome cannot characterize how an unsuccessful trajectory diverges from the requirements and implementation process needed for a correct patch. To address this gap, we introduce SWE-RPG, a repository-level benchmark that combines executable patch evaluation with validated ground-truth references (GTs) for (1) Requirement Clarification and (2) Implementation Planning. These intermediate GTs support retrospective, GT-aligned diagnosis of complete coding-agent trajectories across clarification, planning, code generation, and artifact submission. SWE-RPG comprises 163 tasks from 31 Python and Java repositories, including 113 bug fixes and 50 feature additions. We evaluate 3 coding agents, including Claude Code, Codex, and OpenCode, with 6 large language model backends, including Claude-Sonnet-5 and GPT-5.6-Terra. Results show that the evaluated popular coding agents still struggle to implement user requests in existing repositories, achieving an average resolved rate of only 31.5% on SWE-RPG. Intermediate-GT diagnosis further identifies implicit requirement recovery as the main bottleneck, accounting for 24.5%--46.0% of agent runs. This result suggests implicit-requirement recovery as a key candidate direction for improving coding agents. The benchmark data and evaluation code are available at https://github.com/Xin-Zhou-smu/SWE-RPG-Bench.

For safety-critical software, data from the software's operational past (e.g. a sequence of success and failure events experienced by the software) can provide strong statistical support for reliability claims about the software. However, such data might not describe past software failure events in sufficient detail, and this might leave a reliability assessment (based on this data) unable to account for important features of past software failures. In this paper, by extending conservative Bayesian inference (CBI) techniques used in reliability assessment, we illustrate a principled statistical approach for checking the robustness of reliability claims derived from insufficiently detailed operational data. We demonstrate the extent to which insufficient detail in operational data can undermine software reliability claims in autonomous vehicle (AV) safety assessment scenarios. Reliability claims derived from insufficiently fine-grained data might be dangerously optimistic, despite a concerted effort by an assessor to use such data conservatively during the assessment. While these findings are consistent with previous work on the impact of statistical model fidelity in Bayesian software reliability assessments, our work clarifies why attempts to use low-fidelity data conservatively can be naive, and we give the first conservative estimates of the impact of data fidelity on assessments.

Agent Skills package reusable instructions and assets for tool-using language-model agents. Progressive loading creates failure boundaries poorly represented by session-, model-, or tool-centric traces: a Skill can be discovered but not activated, activated without instructions, or appear successful without an independently verified outcome. We present Skill Runtime Intelligence, a passive runtime-intelligence system that reconstructs supported Skill-lifecycle stages across heterogeneous harnesses while preserving unsupported stages as unknown. Its Run Panorama separates immutable events, deterministic relations, inferred diagnoses, and controlled outcomes with four evidence grades; optional trace import and OTLP/HTTP export support existing observability deployments. Across six frozen repository profiles, three coding agents, and seven clean or fault-injected conditions, all 126 executions preserve source worktrees and each correlates to exactly one source session. Yet adapters expose three distinct semantics: no Skill runs; complete runs but no failure-like events; or failure-like events in every operational-failure and clean session. In a seven-template diagnostic study, semantic aliases and Panorama localize the same six non-clean boundaries but differ in exact/status behavior; both Raw views emit a failure status on all 18 clean cases, while Panorama emits none. A known-rule graph conforms to 126/126 frozen contracts, whereas a second model completes only 228/378 calls. These observations motivate executable adapter qualification and show that event presence is not boundary fidelity, composite exact scores mask distinct errors, and model explanations must not overwrite deterministic facts.