Coding Agents

Coding agents, autonomous systems that use large language models (LLMs) to resolve software engineering tasks, rely on agentic scaffolding: a middleware layer in between a developer and a large language model that orchestrates system prompts, tool execution, context management, and iterative reasoning loops. While these scaffoldings evolve at extreme velocities, no study has examined how this evolution affects agent quality (i.e., effectiveness and efficiency) over time. Practitioners regularly report quality regressions after scaffolding updates, yet consistently attribute them to the underlying model rather than the scaffolding itself. In this paper, we address this gap by conducting the first controlled longitudinal study that isolates the scaffolding's contribution. Unlike prior work that fixes the scaffolding and varies the model, we fix the model and vary only the scaffolding, evaluating 35 sequential releases to measure their impact on agent effectiveness and efficiency. We first empirically study the development and release evolution of five major open-source scaffoldings (i.e., Codex, Qwen Code, Gemini, OpenCode, and OpenHands), revealing extreme release velocities exceeding two releases per day and thousands of issues within months. We then perform a controlled deep dive into 35 sequential releases of the Qwen Code CLI, evaluating each against 50 stratified SWE-bench Verified tasks while holding the underlying LLM constant. We trace the resulting quality fluctuations to specific development patterns and architectural components, and illustrate our findings with concrete qualitative evidence linking individual pull requests to measured quality shifts.

Game engines provide real-time simulation, rendering, physics, interaction, networking, and asset pipelines, making them valuable not only for games but also for 3D applications in healthcare, robotics, architecture, manufacturing, and related domains. Because game development is where these systems are most mature and publicly available, it offers a practical testbed for evaluating coding agents that must modify C++ code within stateful, interactive, real-time systems. We present GameEngineBench, a benchmark for evaluating coding agents on scoped C++ implementation tasks inside Unreal Engine 5 projects, built from nine real-world game repositories. The evaluation set consists of 110 tasks spanning gameplay mechanics, multiplayer behavior, AI and world orchestration, animation and movement, UI and session code, loading behavior, online-service integration, persistence, data serialization, XR behavior, and rendering-oriented plugins. These tasks require models to make native C++ changes that compile and satisfy behavioral tests within executable Unreal Engine projects. Across twelve evaluated configurations, the strongest model reaches 55.5% pass@1, while 31 tasks remain unsolved by every configuration. Our results demonstrate that frontier coding agents continue to struggle with deeply integrated C++ development for real-time interactive software, highlighting game-engine benchmarks as a valuable complement to existing software engineering evaluations.

While skill optimization for autonomous agents has gained traction, existing methods rely on complex pipelines. This leaves a fundamental question unaddressed: What constitutes a minimal viable pipeline for skill optimization, where every component is justified by theory or empirical necessity? We formalize skill optimization via Zeroth-Order (ZO) optimization, mapping classical counterparts (central difference, trust regions) to recent literature. Noting that unlike blind numerical perturbations in classical ZO, skill trajectories serve as interpretable debugging feedback. Grounded in Claude Code philosophy and PAC learning, we establish three principles for convergence and generalization: file-system-based trajectory exploration, consensus attribute mining, and independent validation gating. Eliminating redundancies, we propose SkillOpt-Lite. It accelerates convergence and outperforms full SkillOpt: improving LiveMath by +8.8 points on GPT-5.5 and +25.4 points on GPT-5.4-nano, allowing the nano model to surpass standard GPT-5.4 optimized by SkillOpt. Finally, we integrate our framework into production coding agents like VSCode Copilot, enabling developers to evolve agent skills via one line of vibe. Because our framework treats all agent components simply as standard editable code, this minimal pipeline naturally generalizes to full harness optimization (HarnessOpt). On SpreadsheetBench, HarnessOpt enables GPT-5.4-nano to achieve 0.7758 accuracy, outperforming the larger GPT-5.5 running standard pipelines (0.7620). Code is available at https://github.com/EvolvingLMMs-Lab/SkillOpt-Lite.

Agentic code review, where autonomous agents provide code review comments on pull requests, is increasingly integrated into development workflows, yet there is limited empirical evidence on how developers respond to such comments in practice. In this paper, we present an empirical study of agentic code reviews using CodeRabbit as a case study. Through an empirical study of 31,073 pairs of code reviews and developer feedback from 10,191 pull requests across 239 GitHub repositories, our results show that agentic reviews receive mixed reception: 36.4% were accepted and 7.3% triggered discussion, while 56.3% were rejected. Rejections were primarily associated with invalid suggestions that were false positives, redundant, or out of scope, as well as misalignment with developer intent and coding practices. We further found that agentic reviews tend to focus more on functional concerns than evolvability-related comments, yet they were more likely to be invalid. To improve effectiveness in review practices, we explored various LLM-based approaches for predicting review rejection. We found that lightweight learning-based methods achieve up to 76% F1 score, suggesting learnable patterns exist between code reviews and their corresponding feedback. Our results highlight the current state of CodeRabbit's agentic code reviews, showing opportunity gaps for improvement, as well as shortcomings hindering its effectiveness.

AI tools are accelerating scientific publication while the systems that review it struggle to keep up, and independent verification of published research has become both harder and more important. As manual replication is slow and expensive, a growing line of work uses coding agents to automate parts of the process. Existing efforts are largely packaged as benchmarks with companion agents that only run inside the benchmark's own pipeline, and no general-purpose replication tool exists. We present VERITAS, a domain-agnostic replication framework built around CLI coding agents. Given a paper, a code repository, or both, VERITAS extracts the paper's claims, runs the methodology while resolving issues as they arise, and judges each claim against the evidence from experiment runs. The pipeline returns an importance-weighted Replication Score, a severity-rated log of every fix applied, and the patched codebase. We evaluate VERITAS on CORE-Bench and ReplicationBench, 65 papers spanning computer science, social science, medicine, and astrophysics. Against two strong Claude Code baselines on the same model and host environment, VERITAS achieves state-of-the-art performance and leads on every metric on both benchmarks.

LLM-based coding agents solve software-engineering tasks through iterative interactions with development environments, where returned observations accumulate in the context and become a major source of inference cost. Observation compression reduces this cost by shortening observations before they are appended to the context. However, existing methods still exhibit an unsatisfactory efficiency-effectiveness trade-off, as they do not explicitly model how compression affects the agent's subsequent behavior. This paper proposes CoACT, an action-preserving observation compression method for coding agents. CoACT is built on next-action preservation (NAP), which requires a compressed observation to induce the same next action as the raw observation. By checking the agent's immediate next action, NAP provides a practical signal for whether a compression preserves the information needed for continued task solving. During training, a teacher model first generates multiple compressed candidates of each observation. CoACT then uses an action-preservation reward based on NAP to filter out candidates that would change the agent's next action, and uses a length-reduction reward to choose compact candidates as supervision for a lightweight compressor. Experiments on SWE-bench Verified with three agentic models show that CoACT reduces average total token consumption by 33.0% while maintaining task-solving effectiveness close to the uncompressed agent.

Long-running coding agents such as autoresearch can persistently discover optimizations for open-ended problems. However, they tend to converge onto a single high-level approach, then proceed with low-level edits while missing other superior approaches to the problem. We hypothesize two harness-level design choices contribute to this behavior: accumulating context in a single long-running agent and only exposing a single program state to edit. We introduce SwarmResearch, an orchestrator-subagent harness in which a Shepherd Agent uses global context to steer a population of Search Agents, each operating with local context in their respective git branch. On open-ended optimization tasks, SwarmResearch discovers better or comparable solutions to state-of-the-art LLM-guided evolution and multi-agent techniques on 13/15 tasks, driven by higher-level exploration. Compared with fixed scaling of serial and parallel agents, SwarmResearch's orchestrator-guided scaling discovers better-performing solutions by adapting parallelism at different search depths.

In this paper, we describe LLMoxie, an institutional AI platform whose three-tiered architecture supports multi-cloud and on-premise inference, a LiteLLM/MLflow control plane for authentication, budgeting, PII masking, and observability, and an application augmentation layer for AI coding agents. Layered on top, an open-source RSE-Plugins ecosystem encodes accumulated RSE knowledge as a Plugin-Agent-Skill hierarchy spanning scientific Python practice, domain-specific knowledge, a six-phase research-and-implement workflow, and project lifecycle management. Scientific software is judged less by raw code quality than by whether it can be cited, audited, reproduced, and extended. Off-the-shelf AI coding agents, optimized against commercial software benchmarks, are poorly calibrated for this setting: they ignore the conventions of the scientific Python libraries they invoke, mishandle sensitive or embargoed data, and leave decision trails that are difficult to reconstruct after the fact. We report on twenty months of practice at a university-based research software engineering (RSE) center, where RSEs embedded across astronomy, earth and climate science, agriculture, and health projects worked to close this gap. We characterize the recurring infrastructure, governance, and process challenges of adopting Agentic AI inside a multi-domain RSE center, describe the platform and plugin design, and distill operational lessons from real scientific software deployments. Together, the platform and plugins shift AI coding agents from generic code generators into domain-aware collaborators that respect community norms and produce auditable provenance of technical reasoning.

Agentic coding assistants are increasingly given extra capabilities, such as browser based testing tools and design oriented system prompts, on the assumption that more capability yields better software. This study tested that assumption directly. Ninety independent agent runs built the same application, a real time retrospective board, from one detailed specification, each scored on a fixed 14 criterion functional rubric (42 point maximum) and a visual quality review. The runs spanned several model generations, two agent harnesses, two reasoning effort levels, a testing tool, and two design oriented prompts. Capability tier dominated: frontier models clustered near the ceiling while a low cost local model fell to 24 to 37 points. A criterion level analysis revealed what run totals conceal. Container deployment was the dominant defect, failing first try in 44 percent of runs, with its failure rate shifting sharply across model generations while mean totals moved less than a point. The testing tool raised cost by 42 to 68 percent without improving functional score or reliability, even on interface visible criteria. Raising reasoning effort from High to xHigh lifted first try perfect runs from 28 percent to 89 percent and cut corrective prompts about five fold, for 9 to 29 percent more cost. A design oriented prompt raised visual quality, 4.5 versus 3.0 on a 5 point scale, without lifting function, and a one paragraph paraphrase of its directive reproduced the entire lift. The practical lesson is to match the fix to the failure: most first run failures came from weak reasoning, which a stronger model or more effort prevents, not from visible flaws a checking tool would catch.

Coding agents are capable; human oversight is the bottleneck. Unconstrained agents introduce security risks, erode codebase scalability, and make human review increasingly costly. We argue that the same methods used for decades to manage large human engineering teams: access control, network policies, strict coding conventions enforced by tooling; transfer directly to coding agents, and are cheaper (in token) than recent agentic scaffolding. We sketch a start-to-end system on this principle, and report a controlled experiment in scalable oversight: a small reviewer (Gemma 4 e4b) inspects a Python codebase containing 11 inserted backdoors. Recall rises from 54.5% (unconstrained, no tools) to 90.9% (constrained substrate plus a ~200-LoC docs CLI), with substrate and tools contributing independently. We choose Python deliberately: substrate-level oversight gains are largest where the language gives the fewest guarantees by default; the principles extend to languages like Rust.

Compiler missed optimizations refer to cases in which compilers failed to optimize certain code. It takes many compiler developers' efforts to implement or patch such missed optimizations. In this paper, we present a systematic study of how well agents patch compiler missed optimizations. We identify a significant challenge that patching a missed optimization requires more than just fixing the reported case, and instead requires generalizing to similar cases. We construct a benchmark of real-world LLVM missed optimization issues and compare agent-generated patches with patches from developers in terms of optimization scope. Our results show that coding agents often optimize the given examples, but many generated patches either cover only part of the developer-intended scope or partially overlap with it; in some cases, they further generalize beyond the reference patch. We further introduce historical-knowledge augmentation techniques that leverage prior LLVM optimization pull requests through retrieval and distillation, showing that they improve developer-aligned generalization and yield practical benefits when applied to real-world IR.

Scientific machine learning papers typically make computational claims, e.g., that the relative mean square error is less than 5% or that the 95% predictive credible interval covers the test data. A coding agent can be prompted to replicate those claims from paper materials alone, but the prompt does not by itself reliably preserve progress or check whether generated evidence supports the paper's claims. We introduce Paper-replication, a workflow that makes each selected paper claim a target with recorded evidence, and implement it as a coding-agent skill. The workflow makes the agent record those targets, reconstruct the paper's method, run computational experiments, link generated outputs to provenance and comparisons with the paper's claims, record where matched evidence appears in the replication report, and pass validation checks before completion. We evaluate Paper-replication on twelve independent runs across four scientific machine learning papers. All twelve workspaces pass the completion gate, and all 158 recorded targets are matched with report coverage. Even in this completed workspace state, repeated runs differ in how papers are divided into targets, in numerical fidelity to the source papers, in elapsed replication time, in the number of intermediate executions replaced before final evidence is accepted, and in the rules used to accept evidence. Paper-replication makes completion depend on workspace evidence and validation checks rather than on the agent's final message.

Large language model agents can repair real repository issues, but they often spend large context budgets on whole-file reads, broad searches, and long terminal outputs where useful evidence is mixed with irrelevant code and logs. This paper presents ContextSniper, AntTrail's code-repair module for precision evidence selection in repository-level program repair, part of AntTrail's broader agent-memory engine. AntTrail is available at https://gitcode.com/datagallery/AntTrail. ContextSniper indexes code and action memory as three abstract levels, retrieves candidates with a hybrid ranker, filters long tool output through an intention-aware context gate, and returns compact evidence packets while keeping full source recoverable on demand. In a matched 50-task-per-condition comparison on SWE-bench Lite (same tasks, baseline vs.\ ContextSniper), ContextSniper reduces total token use by 51.5% and logged cost by 36.4% for OpenClaw, and by 38.9% and 27.3% for Claude Code, with submitted-resolution rates essentially unchanged in both host-agent settings. In a separate five-task comparison, ContextSniper beats existing memory- and RAG-style integrations on token efficiency. These results suggest ContextSniper can substantially cut token and cost overhead for repository-level repair agents without a measurable loss in repair quality. The evaluation harness for this study is available at https://gitcode.com/lukchiwang/ContextSniper.

Open-source projects depend on a steady inflow of newcomers. A growing concern is that AI coding agents (tools such as Cursor and Claude Code that write code from natural-language instructions) will crowd them out, by absorbing the simple tasks that beginners start with and by making code harder to read. We give this concern a causal answer. Using GitHub code search we identify 1,888 projects that adopted an agent, signaled by their first commit of a configuration file. We apply difference-in-differences against matched non-adopting controls, restricting the main analysis to the 603 adopters with a genuine pre-adoption period. We find no evidence of crowding-out: across estimators newcomer inflow shows no significant decline after adoption (point estimates run from a small increase to, under the most conservative trend specification, a slight and insignificant dip), onboarding and retention are unchanged, and a sparse, correlational beginner-task measure (good-first-issue labels, which we cannot test for parallel trends) shows no decline. The feared mechanism is real but decoupled: adoption raises per-function code complexity (about +11% on a cognitive metric for Python, a quarter of the prior estimate, and +3 to 4% in cyclomatic terms across all languages), yet in fixed-unit subsets where complexity rose (Python on the cognitive metric, and all languages on the cyclomatic metric), newcomer participation does not decline. These results suggest that, in established open-source projects, adopting an AI coding agent makes code modestly more complex but does not crowd out the human newcomers that a project depends on: the feared trade-off between AI assistance and human participation does not materialize.

Understanding large, complex codebases, especially those with obfuscated structures and incomplete documentation, remains a significant challenge. Existing code summarization solutions often rely on a single language model or coding assistant like Claude Code, and treat source code as flat text, underutilizing the rich interdependencies and hierarchical information within a repository. To address these shortcomings, we propose Agent4cs - a multi-agent framework that summarizes large codebases in a bottom-up fashion, where a summarization agent focuses on producing robust summaries; a keyword-extraction agent proactively identifies critical information from subfolders; and a quality-assurance agent iteratively refines the outputs for readability, coherence, and completeness. Evaluated on 7 frontier models, Agent4cs improves semantic consistency across all folder levels by average 8% compared to two structured prompting baselines with code segments. Furthermore, extensive evaluation on real-world datasets demonstrates up to 38% gains in normalized keyword coverage rate over the same baselines.

Organizations rolling out agentic command line tools like Anthropic's Claude Code and GitHub's Copilot CLI need to know who will try them, who will keep using them, and whether the tools produce enough output to justify their cost. At organizational scale, token spend can run into millions of dollars annually, so misreading adoption, retention, or impact can make a rollout expensive without changing engineering velocity. Studying tens of thousands of engineers at Microsoft over its early-2026 rollout, we find that first use spread primarily through social networks, retention was associated more with engineers' coding activity than with demographics, and adopters merged roughly 24% more pull requests than they would have otherwise. We use merged pull requests as our proxy for output -- acknowledging that a merged PR is not the same as the value it delivers -- and the lift persists across our four-month window. These results suggest that CLI coding agents are neither uniformly adopted nor mere novelty effects and that organizations should treat visible peer use as central to rollout strategy.

Coding-agent reinforcement learning treats execution infrastructure as a background implementation detail, despite relying on large numbers of interactive software rollouts. This is a missed opportunity: measuring infrastructure overhead can reveal practical efficiency gains for RL post-training, where small per-rollout savings compound at scale. We present a comparative study of four execution substrates: single containers, hosted sandboxes, Kubernetes-orchestrated containers, and cloud virtual machines. We find up to $110\times$ variation in cold-start latency and a $1.8\times$ spread in projected worker-hours for one million 150-step trajectories. Our results suggest that future coding-agent RL systems should optimize execution substrates as part of the training system itself, not merely as deployment plumbing.

Repository-level performance-optimization benchmarks such as GSO, SWE-Perf and SWE-fficiency evaluate coding agents by applying patches to real repositories and comparing runtime against unoptimized baselines and official reference patches. Their leaderboard scores are increasingly used as evidence of coding-agent progress, but those scores can conflate runtime instability, benchmark-specific scoring rules, and how many tasks are already solved by at least one public submission. We audit these issues across the three benchmarks. First, we replay the official reference patches for 740 code optimization tasks across four common types of Google Cloud machines. Most benchmark tasks can be replayed, but their reference patches satisfy the original benchmark validity rules in every cross-machine replay for only 39/102 GSO tasks, 11/140 SWE-Perf tasks, and 411/498 SWE-fficiency tasks; SWE-Perf is especially fragile because many reference patches produce close-to-zero runtime changes. Second, we show that public submission rankings depend strongly on the benchmark scoring rule. Among eight public submissions shared by GSO and SWE-fficiency, the official rankings disagree on 9 of 28 pairwise submission comparisons, and SWE-fficiency's leaderboard scoring rule assigns the worst ten tasks overly high score weights of 58.5%-82.8%. Third, looking across 10 public submissions for each task, we find that at least one submission matches or beats the reference patch on 85.3% (384/450) of replay-valid GSO and SWE-fficiency tasks, and beats the unoptimized base code on 99.8% (449/450). Our study complements leaderboard scores by identifying tasks with more reliable performance signals, quantifying per-task score contributions, and exposing the remaining performance gaps that are hidden by aggregate rankings.

Generative AI is shifting software engineering from a practice organized around scarce implementation effort toward one organized around abundant, low-cost code production. This shift changes the central engineering problem: not whether AI can generate useful code, but how engineers organize architectures, tools, evidence, and feedback loops so that AI-mediated development remains inspectable, correctable, and maintainable. We study this problem through a first-person case study: a 12-week development effort in which a single expert software engineer used frontier AI coding agents to build a document accessibility remediation system. The empirical record comprises 88 contemporaneous field notes, 420 KLOC of production code, and 1.16 MLOC of tests, lints, supporting documentation, and agent tooling. From this record, we develop a candidate middle-range theory of governance conversion, expressed as a process model explaining how high-velocity agentic implementation becomes governable. The model explains how agentic implementation velocity surfaces recurring structural failure classes, and how engineering judgment sustains velocity by converting those failures into durable governance mechanisms. In contrast to existing governance models that derive controls from known obligations, governance conversion explains how controls are discovered from failures that become visible only during agentic work. We use our model to make testable predictions and to describe implications for software engineering research and practice.

We introduce SWE-Interact, a new testbed for evaluating coding agents on multi-turn, interactive, user-driven software engineering tasks. Existing frontier SWE benchmarks typically provide complete requirements upfront and evaluate agents on autonomous implementation. In contrast, SWE-Interact places agents in a realistic developer workflow: a carefully designed user simulator starts with vague or incomplete instructions, progressively reveals requirements, inspects the agent's workspace, and provides targeted feedback, revisions, and new constraints until the full task goal has been handed off. Grounded in large-scale studies of real coding-agent interactions, this setup tests whether agents can discover user intent, adapt to evolving requirements, and build on their own prior work. Across a suite of frontier and open-weight models, we find that strong performance on single-turn SWE tasks does not reliably transfer to multi-turn, user-driven workflows: the best-performing models solve roughly 50% of single-turn baseline tasks but only 25% of the corresponding SWE-Interact tasks. The strongest models in our evaluation, including Opus 4.8 and GPT 5.5, start strong even in the face of vague initial instructions, persevere until all the requirements are surfaced by the user, integrate them better and write clean code. However, they still suffer from over-agentic coding, forgetting requirements and technical mistakes. Weaker models start poorly under ambiguity, give up early, forget or ignore instructions and rework their code more. Overall, SWE-Interact measures an orthogonal, real-world capability axis for frontier model development: interactive goal discovery and iterative refinement with a user in the loop.

Coding agents are rapidly becoming a major application of agentic LLMs, but serving them efficiently remains challenging. Progress on this challenge requires understanding real workload patterns, yet the data needed for such analysis is largely absent. Existing public traces and benchmarks do not capture real, day-to-day coding-agent usage across multiple agents and model families for serving-system analysis. To help fill this gap, we collect and release a trace of roughly 4,300 coding-agent sessions, containing about 350,000 LLM steps and 430,000 tool calls from our own day-to-day use of Claude Code and Codex. Our analysis shows that coding-agent workloads feature long autonomous loops, long contexts with short outputs, diverse and heavily-tailed tool calls, and high but imperfect prefix cache hit rates. These findings point to concrete opportunities for optimizing serving, including lower-overhead tool calling, append-length-aware prefill, semantic-aware tool-latency prediction, and improved KV-cache management around human-paced gaps. We release the dataset, trace collection pipeline, and analysis code at https://github.com/uw-syfi/TraceLab.git the project website is https://tracelab.cs.washington.edu.

AI models are rapidly improving at autonomous coding, as shown by benchmark progress and one-off demonstrations such as AI implementing a C compiler. However, existing coding benchmarks tend to focus on shorter tasks, and one-off demonstrations are hard to compare systematically because they often have some human guidance, and are not standardized or repeated across models. To address these challenges, we introduce MirrorCode, a long-horizon coding benchmark based on reimplementing entire software projects. In MirrorCode, AI agents must replicate the functionalities of an existing program, without access to its source code. AI solutions must match the original program's output exactly on end-to-end tests, including held-out tests. MirrorCode's 25 target programs span different areas of computing: Unix utilities, data serialization and query tools, bioinformatics, interpreters, static analysis, cryptography, and compression. Existing AI models can already reimplement complex software, with the strongest model scoring 56% across the benchmark. For example, AI can reimplement gotree, a 16,000-line bioinformatics toolkit - a task that we believe would take weeks for a human engineer. However, studying the frontier of performance requires a larger inference budget than typical benchmarks, for example, $2,600 over 19 days for a single attempt on a large task. We show that AI agents can already complete long-horizon software engineering tasks, especially when requirements are precisely specified. More broadly, our work suggests AI will have transformative effects on software engineering, as autonomous agents continue to improve.

Most coding-agent benchmarks are static: an agent receives a complete task description up front and is judged only by its final code. Real coding assistance is interactive, with users clarifying goals, adding constraints, and correcting mistakes over multiple turns. We introduce SWE-Together, a multi-turn benchmark reconstructed from real user-agent coding sessions. To make real interactions verifiable, we curate 109 repository-level tasks from 11,260 recorded sessions, selecting sessions with recoverable repository states, clear user goals, and observable outcomes. To replay these interactions across agents, we build a reactive LLM-based user simulator that preserves the original users' intents and provides feedback when the coding agent's progress requires it. To evaluate agents as collaborators, we measure both final repository correctness and the number of corrective feedback turns required during the interaction. Experiments with frontier coding agents show that stronger agents generally achieve higher final success rates while requiring fewer interventions, suggesting an improved user experience.

Program verifiers play a central role in training coding agents, including selecting trajectories for supervised fine-tuning (SFT) and providing rewards for reinforcement learning (RL). Standard execution-based verification requires running unit tests inside per-repository environments such as Docker images, incurring substantial environment setup costs. We propose Dockerless, an environment-free agentic patch verifier that evaluates generated code patches without executing them. Rather than simply matching candidate patches to references, Dockerless judges patch correctness using evidence gathered through agentic repository exploration. On a verifier evaluation benchmark, Dockerless outperforms the strongest open-source verifier by 14.3 AUC points. Using Dockerless as both the SFT trajectory filter and the RL reward enables a fully environment-free post-training pipeline. The resulting model reaches 62.0%, 50.0%, and 35.2% resolve rate on SWE-bench Verified, Multilingual, and Pro, respectively. It surpasses the Qwen3.5-9B baseline by 2.4, 8.7, and 2.9 points, matching environment-based post-training.

Long-horizon software engineering agents often need to manage lengthy and noisy interaction histories under limited context budgets. Existing memory management methods typically rely on static compression workflows or impose rigid constraints on compression timing and granularity. Moreover, these approaches fail to jointly optimize memory management and issue resolution capabilities to improve performance while reducing token usage. We present SWE-MeM, a training framework for proactive and on-demand memory management in software engineering agents. SWE-MeM provides a flexible memory tool that lets agents decide when, what, and how to compress based on trajectory state, task progress, and remaining context budget. We train agents with synthesized proactive memory-management trajectories and Memory-aware GRPO, which jointly optimizes memory management and issue resolution through memory-aware trajectory splitting and step-level credit assignment. On SWE-Bench Verified, SWE-MeM achieves 43.4% and 60.2% resolve rate with 4B and 30B models, respectively, outperforming existing memory management baselines in both performance and efficiency.

Benchmarks are widely used to evaluate task completion by Large Language Models (LLMs), but this approach has accumulated construction-validity problems, and a passing score may not show whether the requested task was delivered. We study both problems. In a controlled code-as-spec setup, two production Copilot CLI agents (claude-opus-4.7, gpt-5.5) re-implement a React Fluent-UI data table in Angular as a reusable library under a hidden 222-test Playwright oracle across 18 runs and three oracle-availability conditions. Alongside the score, we run a mechanical library audit and check each verdict with a no-op ablation. Without the oracle, the library is present but unfinished, revealed by scores. With the oracle in the loop, the score reaches near-perfect, but from a demo holding the tested behavior directly, the library left dead or absent. We call this building to the test; the broader disposition behind both we call validation self-awareness. The agent does not, on its own, validate what it ships as a user would. Prevalence remains an open question across other agents, signals, and model families. Beyond benchmark scores, dispositions like validation self-awareness merit research attention.

AI coding agents dramatically accelerate implementation speed but introduce two structural failure modes that existing spec-driven approaches do not fully solve: (1) context explosion -- the agent must reason over an entire repository at once, degrading output quality as the context window fills; and (2) silent spec-code drift -- code evolves, the specification does not, and the divergence becomes invisible until it is costly to repair. We present the Spec Growth Engine, a lightweight framework that addresses both failure modes through a machine-readable spec graph whose nodes carry explicit contract/design separation, a Spine context assembler that scopes agent context to an ownership path, a vertical-slice growth protocol that enforces hardest-first ordering, and a drift gate that makes spec-code divergence a blocking merge condition. The design synthesises well-established software engineering principles (Parnas information hiding, C4, ADRs, Walking Skeleton, Reflexion Models, Fitness Functions) into a lean, code-coupled, machine-enforced whole -- without the overhead of heavy-weight frameworks such as RUP or MDA.

LLM coding harnesses grant agents broad file and shell access, yet the configuration layer that steers them -- rules files, agent definitions, IDE-specific markdown -- is largely unmanaged. A prevalence study of 10,008 public GitHub repositories (n=6,145 agent config files) finds that agent configurations propagate as undeclared shared components: 10.1% of tracked paths are SHA-256 exact duplicates across independent repositories (fork-adjusted, threshold-independent), with 75.5% of clone pairs crossing organisational boundaries. Two further patterns are indicative: configurations are rarely revised (58% single-commit; 0.4 vs 0.6 commits/month age-normalised against CI/CD workflows), and rarely declare permission boundaries (<1% of agent configs vs 33% of Actions workflows, n=31 true positives). We propose a deterministic control plane above the harness that maps one-to-one to these gaps. Rel(AI)Build treats agent definitions as a managed supply chain (SHA-256 content addressing, HMAC-stamped lockfiles, hash-chained audit logs); enforces tiered permissions and attack-derived blocklists before LLM invocation; gates feature work through a phase state machine with requirement-to-file-to-test traceability; compiles a single canonical definition to seven IDE targets; and detects prompt drift via Jaccard similarity. Conformance tests on injected violations confirm each mechanism enforces its stated invariant; developer outcomes remain future work. Governance of this layer must be deterministic and tool-agnostic -- not delegated to further LLM orchestration.

A classical intuition holds that verifying a solution is easier than producing one. For today's coding agents, this intuition is being inverted: as foundation models develop stronger reasoning capabilities and engineering harnesses grow more sophisticated, generating complex candidate solutions is no longer difficult -- reliably verifying them has become the harder problem. Every verifier we can build is only a proxy for human intent, never the intent itself. This makes verification subject to a twofold difficulty: first, intent is underspecified by nature, making it inherently hard to faithfully check whether it has been fulfilled; second, during model training, optimization widens the gap between proxy and intent -- manifesting as reward hacking or signal saturation. To address this, we characterize the quality of verification signals along three dimensions -- scalability, faithfulness, and robustness -- and argue that achieving all three simultaneously is the central challenge. We further study four reward constructions: a test verifier for general coding tasks, a rubric verifier for frontend tasks, the user as verifier for real-world agent tasks, and an automated agent verifier for long-horizon tasks. Across different task types and policy capability levels, we conduct in-depth analysis and experiments on the core challenges of reward design and how to more effectively leverage reward signals. Experiments show that targeted verification design can effectively suppress reward hacking, improve task completion quality, and achieve significant gains across multiple internal and public benchmarks. These experiences collectively point to a core observation: no fixed reward function can remain effective as policy capability continues to grow; and verification must co-evolve with the generator.

We introduce NatureBench, a cross-discipline benchmark of 90 tasks distilled from peer-reviewed Nature-family publications, designed to evaluate whether AI coding agents can move beyond reproduction toward discovery on real scientific problems. NatureBench is built on NatureGym, an automated pipeline that constructs a standardized, per-task containerized environment from a source paper, addressing the environment-fragmentation problem that has limited the credibility of prior agent-on-research benchmarks. Evaluating ten frontier agent configurations under a strict web-search-disabled protocol, we find that the strongest model surpasses SOTA on only 17.8% of tasks under the g>0.1 criterion. Analysis of method pathways reveals that agents succeed primarily through methodological translation, converting scientific tasks into familiar supervised prediction problems, rather than through genuine scientific invention. Failures are dominated by wrong method choice and insufficient compute budget, not by task misunderstanding. We release the benchmark, the NatureGym pipeline, and a public leaderboard with maintainer-side reproduction. Code: https://github.com/FrontisAI/NatureBench

Modern coding agents pair LLM generators with various tools, including cheap diagnostics and expensive verifiers. The tool-use decisions are typically governed by orchestrators that often use fixed rules and ignore uncertainty. We formulate orchestration as cost-sensitive sequential hypothesis testing: a Bayesian controller maintains a belief over candidate correctness and dynamically decides whether to gather more evidence, refine the candidate, verify it, or stop. Across six generators and nine coding benchmarks, Bayesian control proves to be most valuable when verification is costly and critics are informative but imperfect. Beyond control, the belief state yields an interpretable correctness score that outperforms token-probability and raw tool-success baselines for uncertainty quantification.

Generative AI coding agents are entering the open-source supply chain, yet their diverse and often invisible traces leave their prevalence poorly understood. We introduce a multi-layered detection framework that integrates configuration-file scanning, commit-message analysis, author-identity matching, and bot-signature lookup across World of Code (180M+ Git repositories), classifying agent traces into four behavioral types. No single method captures more than a fraction of activity: multi-method detection identifies 850,157 Claude Code commits in one snapshot, of which bot-account lookup_the signal most adoption studies rely on_recovers only 28,154 (3.3%), a 30x relative-recall gap, so single-signal prevalence estimates are biased low by at least this factor. Every detection pattern is hand-validated (495 labels) with per-cell precision and Wilson confidence intervals. Across snapshots from December 2024 to April 2026, commit-attributed agents generate over 320,000 commits per month; Claude Code leads (886,122 commits across 17,295 projects) and dominates silent, configuration-file-only adoption (21,078 projects). Compared against an independent pull-request census (AIDev), the two channels capture nearly disjoint agent populations_a PR census misses 79% of commit-detected Claude Code adopters and essentially all Codex adopters_and different kinds of work: PR-deployed cloud agents (Codex, Cursor) surface as feature work, while commit-deployed in-editor agents (Claude Code, OpenHands, Aider) surface as maintenance. The observed work profile follows deployment and detection mode rather than the tool itself, so no single channel is representative.

Agentic coding harnesses - such as Agent-Skills, Superpowers, and Agent-Rigor - are increasingly deployed to augment underlying LLMs for real-world software engineering tasks. Existing benchmarks evaluate these agents almost exclusively on outcome correctness: whether generated code passes tests or resolves issues. We argue that this outcome-only lens is insufficient: an agent that arrives at a correct solution through reckless trial-and-error, without planning, verification, or graceful recovery, is fundamentally less reliable than one that follows sound engineering discipline. We introduce RigorBench, the first benchmark designed to measure process discipline in AI coding agents. RigorBench evaluates these harnesses across five pillars: Planning Fidelity, Verification Coverage, Recovery Efficiency, Abstention Quality, and Atomic Transition Integrity. A composite RigorScore aggregates these dimensions into a single metric via a weighted sum. We curate a suite of 30 tasks spanning five categories - Plan-Then-Build, Verify-Or-Die, Doom Loop Gauntlet, Know When to Fold, and Don't Break the Build-and evaluate leading harnesses in a controlled with/without experimental design against baseline coding assistants. Our results show that structured process discipline not only improves process quality scores by an average of 41% but also raises downstream outcome correctness by 17%, providing the first quantitative evidence that how agents code matters as much as what they produce. We release the full benchmark, scoring rubrics, and trajectory analysis tools as open-source artifacts.

Coding agents often receive broad tool access for an entire task, even when a resource is needed only for one subgoal. We call this gap lingering authority: a temporary resource/effect capability remains exposed after the episode that justified it has closed. PORTICO is a reference monitor for revocable capabilities exposed to the planner. It compiles an explicit task contract into initial capabilities, grant rules, trusted closure predicates, and global deny rules. A request-grant-invoke lifecycle materializes expansions as opaque, epoch-bound handles. Closure removes those handles from the next planner interface and rejects stale replay before side effects. The monitor assumes mediated tools and a sound typed catalog. In controlled coding-agent tasks, PORTICO records no executed contract-forbidden effects in the evaluated runs, while controlled grants recover boundary work blocked by a fixed narrow envelope. A non-revoking comparator receives the same initial envelope and the same grants at the same turns. On the closure slice, both systems match task success, scope compliance, and all pre-closure decisions; PORTICO then rejects 10/10 post-closure reuses, while the comparator permits 10/10. A deterministic stale-write audit records 0/6 versus 6/6 executed forbidden effects. Scripted traces and six live model traces over file writes, git mutation, and network egress show the same split. In a four-episode same-policy diagnostic, broad request exposure preserves zero executed forbidden effects but raises blocked proposals from 67 to 84. Frozen real-repository runs, with commits and traces recorded, exercise the same lifecycle on real project layouts.

Coding agents now interleave LLMs with retrieval over the working repository, and retrieval implementations vary widely across deployed harnesses. Inside a fixed coding-agent harness on a fixed model, does adding a structural codebase index actually change cost or resolve? We ran three arms (the harness with the index, the same harness without it, and an agentic-grep comparator) on SWE-PolyBench Verified and SWE-bench Pro with Claude Opus 4.7 held fixed throughout, across three seeds, inside a leak-audited per-task sandbox. The within-harness ablation produces a large localization gain and a statistically separated resolve gain, with no cost penalty per cell and lower cost per solve. The cross-harness check shows that the index does not regress against an agentic-grep baseline on resolve or localization, again at no cost penalty. We release the per-cell exclusion ledger, the leak-audit script, the localization extractor, and the results database. The deployment question for a structural codebase index is thus not whether it is too expensive to run (across seeds, the index lands at a lower $/solved than agentic grep) but whether the workload includes multi-file changes where structural ranking pays off.

Memory safety vulnerabilities remain a significant threat even for projects with extensive fuzzing and manual auditing. Recent results suggest that large language models hold great promise for detecting such vulnerabilities, but they are unreliable, at risk of hallucination, and challenging to scale to repository-size codebases. This paper presents Revelio, a cost-efficient end-to-end agentic framework for memory-safety vulnerability discovery. Revelio addresses the problem of hallucination by generating an executable Proof-of-Vulnerability, which is checked with a deterministic sanitizer. It reduces cost using inexpensive LLMs and lightweight static analysis to help generate and rank vulnerability hypotheses, reporting vulnerabilities only when they can be reproduced and confirmed by a sanitizer. We evaluated Revelio on seven production-quality projects that had been continuously fuzzed for five to eight years, as well as on 100 randomly selected Arvo projects from the CyberGym benchmark. With around one hour per project and a total cost of $300, Revelio discovered 19 previously unknown memory-safety vulnerabilities. On benchmarks, Revelio outperformed frontier coding agents across diverse backbone models at comparable token costs. Our results suggest that Revelio enables scalable and trustworthy end-to-end LLM-based memory-safety vulnerability detection.

As coding agents are rapidly changing software engineering, a natural question is: what are the core skills needed by future software engineers? To identify where software engineering is headed and thus what skills will be needed, we summarize the results of two round-tables with researchers and industrial practitioners, held in 2026 in New York and Singapore. One key finding is that verification and validation is increasing in importance as agents handle implementation, as highlighted by anecdotes from the events. From our observations, we identify the skills developers need in the agentic era of development, with implications for training and educating future software engineers in coming years.

Coding tasks are typically complicated and require multiple capabilities, ranging from high-level planning to low-level implementation. While coding agents are optimized for the joint capabilities, individual capabilities such as high-level planning may have different optima and remain a major bottleneck. To address this challenge, we train a separate critic model that is specialized in high-level planning to steer the coding agent in inference. We construct SFT and DPO data to train the critic model to identify errors made by the coding agent and provide correct and clear high-level guidance without generating concrete actions. Experiments show that our fine-tuned 4B and 8B critic models significantly improve the performance of 6 larger coding agents (e.g., improving the resolved rates of GLM-4.7-Flash-30B-A3B and GPT-OSS-120B by 16.0% and 14.4% on SWE-Bench Verified). The critic model also reduces the total inference costs for some coding agents by solving tasks in fewer steps (e.g., reducing the per-example inference cost for GPT-OSS-20B from $0.07 to $0.03). Code: https://github.com/shubhamrgandhi/critic-training

Maintainability is a core dimension of software engineering, shaping how code is written, reviewed, and developed over time. While coding agents have demonstrated strong performance on single-issue tasks, it remains unclear how maintainable their code is when future agents build on top of it, potentially leading to compounding downstream effects. We investigate how agent code compares to human code in these maintenance settings, presenting CodeThread, a framework to construct controlled experiments from repository-level coding benchmarks. Applying CodeThread to four frontier coding agents and four benchmarks, we find that agents are less effective at resolving tasks when building on agent code compared to human code, with task resolve rate drops of up to 13.1%. Regression analysis reveals that many traditional software engineering maintainability metrics do not explain this difference. Instead, the clearest signals are subtler behavioral differences in agent code, such as changes to input validation and error handling, along with differences in downstream code size and task difficulty. These findings highlight the need to evaluate these systems not only by immediate task resolution but also by code maintainability, and point to potential sources of downstream errors introduced by agent code.

A modern coding agent can hold an entire repository in its context window. Most of its reading is wasted -- and the interesting question is not how much context an agent can use, but what it actually \emph{needs}. We study that question at the moment it matters most: when the agent must \emph{edit} code. Separating \emph{finding} the work site from \emph{acting} on it, we hold localization fixed with an oracle, vary only how the code is represented, and score context against real issue resolution on SWE-bench Verified. The answer is starkly minimal. The signal lives in the code being edited itself: natural-language summaries of it answer almost none of the behavioral questions that the source answers ($4/45$ vs.\ $27/45$, held-out repositories, independent judge), and the gap belongs to the representation, not the summarizer -- a frontier model's summaries score exactly as poorly as a 3B model's. The surrounding context hardly matters either: across every multi-file instance in Verified, under a protocol frozen before any data, rendering a file's remainder as UML skeletons and signatures resolves no more issues than deleting that remainder outright ($N{=}70$, exact McNemar $p{=}0.75$). That was our registered hypothesis, and it failed. Compressed context, meanwhile, matches whole files at a third of the tokens: a resolved issue costs $19$K context tokens, not $94$K. The instrument also yielded a finding the field should keep: temperature-0 API inference flips ${\sim}9\%$ of per-instance outcomes between byte-identical runs. That is a noise floor under every small effect reported on this benchmark, including ours. We release the instrument -- gold-validated environments, per-instance proof that every reference edit is expressible from every arm's context, deterministic patch construction, and pre-registered hypotheses whose nulls we publish.

LLM-based coding agents need higher-level operational knowledge about a repository (which files house which subsystems, how to run the test suite, which workflows have historically led to wrong fixes) that does not exist in the code itself. Engineers typically maintain AGENTS.md files to supply this context as instructions for coding agents, but whether they help is contested: recent studies disagree on whether LLM-generated guidance improves or harms agent performance. In this paper we show that how the guidance is produced is the decisive variable, and introduce probe-and-refine tuning: a procedure that uses synthetic bug-fix probes to iteratively diagnose and patch a repository's guidance file through single-shot LLM calls, with no agent loop or tool use during tuning. On SWE-bench Verified across four independent trials with Qwen3.5-35B-A3B at 200 steps, probe-and-refine achieves 33.0% mean resolve rate vs. 28.3% for the static knowledge base used to initialize it and 25.5% for an unguided baseline (p < 0.001 for both probe-and-refine contrasts). The improvement comes from coverage rather than precision: refined guidance produces evaluable patches for 14.5 percentage points (pp) more instances while per-patch precision remains statistically constant (~59%, p = 0.119), showing that improved guidance helps agents reach the correct file rather than improving the quality of the changes they make. Further, a step-budget experiment shows that guidance is what lets the agent use a larger step budget productively, and a cross-model experiment with NVIDIA-Nemotron-3-Nano-30B-A3B finds that the tuning loop degrades when the model cannot generate sufficiently diagnostic output, though per-patch precision remains constant even then.

Autonomous coding agents now open millions of pull requests, yet large-scale studies find their PRs are produced faster but accepted less often - a coordination and trust gap that pull-request-level telemetry cannot explain. We argue the missing signal lives before the PR, in how concurrent agents claim, divide, and collide over shared work. We study this process through grite, our open-source coordination substrate that needs no central server and stores its records inside git itself, so its append-only, signed event log captures the coordination process directly. We show that (i) this shared substrate reduces duplicate and conflicting work at bounded overhead - the share of work that merely re-does a teammate's task falls from 78% to 0% while useful throughput more than triples; (ii) every agent's copy of the log converges to the same state with no write silently dropped, where a file-based tracker loses concurrent writes; and (iii) the log is a mineable artefact from which concrete failure modes - conflicting edits, lock starvation, redundant rediscovery, race-to-close - are automatically recoverable with provenance, several invisible in pull-request history. We release the dataset, harness, and mining toolkit.

We introduce StaminaBench, a benchmark that measures the stamina of coding agents: how many consecutive interaction turns (change requests) they can handle before failing. Unlike the prevailing fraction-of-tasks-solved metric, this matches real vibe-coding where sessions run dozens or hundreds of turns. In StaminaBench, agents implement a REST API server and modify it across a tunable number of procedurally generated follow-up change requests - 100 in our experiments, resulting in codebases of up to 6,000 lines. Tests are generated fully programmatically without LLM involvement, ensuring reproducibility and reliability; change sequences are drawn from either a hardcoded or LLM-driven sampler, both constrained to a structured action space to ensure changes are valid. The agent and the server run in an isolated environment and communicate with the benchmark through HTTP, making testing fully black-box and language-agnostic. We evaluate six agent harnesses paired with seven open-source LLMs across 20 scenarios of 100 turns each and find that: (1) all the tested models fail within 5-6 turns, confirming that vibe-coding-style programming without thorough testing produces bugs; (2) passing test feedback back to the agent and allowing it to retry improves passed turn count by up to 12x; and (3) a good harness is required for strong performance: stronger models exhibit up to a 6x gap between their best and worst harness, while weaker models fail with any harness. We release the benchmark and the generated tasks to enable further research into multi-turn coding agent behavior. Benchmark code and data: github.com/amazon-science/StaminaBench.

Production data integration is bottlenecked by repeated, lossy handoffs between data owners, engineers, and analysts who must collaboratively discover, structure, and query enterprise data. We present Data Intelligence Agents (DIA), a system of three agents (Data Interpreter, Schema Creator, and Query Generator) that compresses this workflow by treating autonomous coding agents (ACAs) as a first-class abstraction: rather than emitting text, the agents generate, execute, validate, and repair concrete artifacts, draw on a shared memory for experience reuse, and surface each for review by domain experts. DIA is deployed in production for enterprise customers. We study the Query Generator in depth and evaluate it in fully autonomous mode across seven SQL benchmarks spanning four task categories and four dialects. It matches or surpasses the best published results on all seven, demonstrating that an architecture grounded in execution, built on ACAs and a shared memory, generalizes across the data intelligence workload with adaptation confined to natural-language instructions.

Realistic coding-agent benchmarks often replay public GitHub issues and pull requests, making them vulnerable to overlap with model pretraining, fine-tuning, synthetic-data generation, or benchmark-driven model selection. Fully synthetic tasks avoid direct historical replay, but can drift away from real repository needs. We propose SWE-Future, a forecast-conditioned data synthesis method for future-oriented coding tasks. Given a forecast snapshot at time $T_0$, the method uses only pre-$T_0$ repository evidence to forecast future feature implementation/enhancement, bugfix, and refactor task families. We first validate this forecasting step retrospectively: after forecasts are fixed, later pull requests are used only to measure whether the predicted task families match future repository work. In an 80-repository study, the forecaster achieves 58.1% future-work relevance under the main semantic matching metric. We then use validated forecast families as conditioning signals to synthesize a 200-task coding-agent dataset across 61 repositories from a task-generation snapshot, rather than replaying the later pull requests used for validation. SWE-Future shows that repository-evolution forecasts can guide realistic, future-oriented coding-task synthesis while reducing direct dependence on historical pull-request replay.

Software practitioners increasingly use AI coding agents that generate test code alongside production code in open source pull requests (PRs). Recent studies report more than 932,000 agent-authored PRs across more than 116,000 repositories, yet whether their test files contain meaningful verification logic remains underexplored. Test files lacking explicit assertions execute code without verifying behavior, so quality gates based on test-file presence overestimate verification strength. The goal of this paper is to help practitioners assess the verification strength of agent-authored patches by characterizing oracle signals and their link to merge outcomes and review effort. We conduct an empirical study of 86,156 test-file patches from 33,596 agent-authored PRs across 2,807 GitHub repositories produced by five coding agents: OpenAI Codex, GitHub Copilot, Devin, Cursor, and Claude Code. A qualitative analysis of 384 stratified patches informs a syntactic taxonomy of eight oracle signal categories. Applied at scale, 80.2% of test patches contain weak or no explicit oracle signals. While raw merge rates are lower for strong-oracle PRs, a regression analysis adjusting for agent, PR size, repository popularity, task type, and language shows strong oracles significantly improve merge likelihood (OR = 1.28, p < 0.001). Our findings suggest that test file counts substantially overestimate verification strength and that practitioners can adopt oracle-aware quality checks to more accurately evaluate agent-authored contributions.

Coding agents have become a major mode of software engineering, but the benchmarks we use to compare them were designed in a pre-agent era: they collapse model, harness, and environment into a single end-to-end score, typically computed against one reference solution, with no component-level signal for iteration. We argue that current coding benchmarks are misaligned with agentic software engineering. A coding agent in practice is not a model: it is a system harness -- a composite of models, harnesses, contexts, environments, and feedback signals, any one of which can move the benchmark score by margins comparable to those between adjacent model generations. We discuss three symptoms: (i) benchmark scores conflate the model with the rest of the harness; (ii) grading against a single reference solution penalises equally valid alternatives; and (iii) the absence of signal at the level of individual harness components makes the end-to-end system score difficult to iterate on.

Benchmark scores tell you what an agent got right; they do not tell you how it got there. In this work, we introduce methods for comparing agents procedurally in different contexts, where the model, tasks, and approaches vary. We compare ten agents and find that they are identifiable by their behavioral habits, which we define as fingerprints: a probe over these procedural signatures attributes an unseen trajectory to the correct agent at 85.7% accuracy, controlling for leakage across tasks. We develop procedural representations for agent problem-solving procedures with an emergent vocabulary induction technique that is meant to be maximally compressive to avoid surface-level variation while being expressive enough to unveil the quirks of the models' patterns. We apply our framework to the software engineering evaluation dataset SWE-Bench to study the structural distinctness of agent trajectories and find that behavior is most similar between models from similar release periods and those that are distilled from one another (e.g., a distilled student model and its teacher have a Jensen-Shannon divergence of 0.25, about half the distance between other model pairs). As more models saturate evaluations, we believe that it will be important to probe model behavior along more holistic dimensions than success rates alone. We introduce ProcGrep, a library for auditing and evaluating agents for how they approach tasks at a procedural level given their traces in a top-down fashion. We believe this work has a range of applications to help developers work with and program coding agents, such as task-aware model routing, agent monitoring, and finer-grained cost analysis.

Code-as-Policies (CaP) has shown that large language models (LLMs) can write code to solve robotics tasks by composing perception, planning, and control primitives. Recent CaP systems, however, rely on multi-turn code-generation loops at test time, which is often infeasible for real-time robot control. We introduce Robotics Harness Optimization (RHO), a novel paradigm in which tool-enabled coding agents, at training time, propose and search for interpretable, neurosymbolic multi-file policy repositories (Repositories-as-Policies) that compose these primitives rather than a single prompt, function, or file. RHO searches with reflective feedback from environment reward and execution rather than teleoperation demonstrations. It generalizes to perturbed pick-and-place settings like LIBERO-PRO, where OpenVLA scores 0.0% and $π_{0.5}$ averages 12.83%. Using the same low-level primitives, RHO reaches a 45.0% success rate, 2.5x higher than the strongest multi-turn agentic system, and 3.5x higher than $π_{0.5}$. On Robosuite, RHO sets a new state-of-the-art of 70.0%, exceeding the prior multi-turn record of 68.29% using single-turn execution with no corrective LLM code edits at deployment. When an LLM is used in the control loop, as on RAI's O3DE benchmark, RHO optimizes the deployed agent's multi-file harness of prompts, tools, and control code, improving held-out success from 23.5% to 44.3% with 20% less wall-clock time and 27% fewer tool calls.

AI coding agents increasingly accept assigned software tasks, modify repositories under bounded authority, and return work packages for review. Prior work proposed the software delegation contract, covering the task, authority, returned work package, and acceptance context, as the unit of analysis for delegated coding work, but did not measure its effects. This paper reports a controlled pilot study of explicit delegation contracts for coding agents. We built a dependency-free TypeScript API task environment with seeded defects and documentation gaps, authored ten tasks across five families, and ran 64 agent executions across two model tiers under three conditions: a realistic issue-style prompt, an explicit delegation contract, and a contract with a required evidence bundle. Each run was scored with hidden acceptance tests, mutation checks, and scope analysis, then reviewed by three independent condition-blinded model-based reviewers using a fixed rubric, for 192 reviews. Explicit contracts did not improve objective task outcomes: all 64 runs passed hidden acceptance checks, with zero scope violations. They did improve reviewability. Evidence sufficiency improved in 22 of 30 paired comparisons and worsened in none (+0.83 on a 5-point scale, p < 0.0001, Cliff's delta = 0.66); reviewer ambiguity decreased (p = 0.035); changed-file lists, known-limitations sections, residual-risk sections, and reviewer checklists appeared mostly or only when demanded by the contract. Contracts cost +13% agent tokens and +38% wall-clock time, with larger effects for the weaker model tier. On these small tasks, delegation contracts bought reviewability rather than correctness.

Software engineering and deployment are increasingly delegated to AI coding agents. The scale of their adoption is surfacing rare, but highly destructive, failure modes. In this paper, we study these failure modes as stemming from three distinct mechanisms: underspecification, where default model behavior is unsafe; capability errors, where the safe action is available but the model does not adhere to it due to bias or capability limitations; and agent harness errors, where the model fails to execute the safe action through the harness. We assess these across 8 different evaluations, each inspired by real-life deployment failures, totaling 20 coding environments and 59 synthetic transcript templates. These evaluations act as controlled stress tests for isolating our failure mechanisms. Based on this evaluation, we propose ClayBuddy, a harness modification that molds to user preferences and can be modified by the model in-session, to mitigate these errors. By adding tools for the agent to edit its own context, an extended system prompt, a customizable command classifier, and deterministic guardrails, we show that ClayBuddy is safer across a statistically significant number of samples. Thus, we suggest concrete mitigations for current coding agents and a design philosophy for future agent harness features.

Frontier coding models may spend substantial capacity learning not only program behavior, but also accidental entropy in human repositories. Such repositories contain valuable signals: tests, incidents, migrations, edge cases, product judgment, and operational history. These signals are entangled with framework churn, naming drift, generated-source ambiguity, dependency rituals, CI dialects, weak proof routes, and human-oriented review customs. We propose agent-first canonical code, a proof-carrying substrate that rewrites routine product software into canonical behavior profiles, typed change algebra, proof lanes, constrained edit grammars, semantic patch cells, runtime negative memory, and proof-carrying change objects. The core hypothesis is that quotienting software by behavior equivalence under a declared oracle can collapse equivalent encodings into governed representatives with explicit evidence and proof obligations. The endpoint is amortized cost per verified correct change, including source, context, reasoning, tools, verification, security, provenance, review, failed loops, defects, and foundry cost under a common oracle. Reported reduction bands are hypotheses, not measured frontier results. The proposed limit is a No-Accident Horizon: removable accident decreases until residual novelty, evidence, governance, risk, and future optionality dominate. For supported routine-product distributions, this gives a defensible planning target near 100-fold all-in cost reduction, not a guarantee for all software. Preliminary QLoRA experiments on Qwen2.5-Coder-14B show that 64,088 canonical trajectories are learnable and suppress tested forbidden-language markers, but do not establish behavior preservation, scaling economics, or verified-change cost. The contribution is a falsifiable program centered on minimum functional description length and verified-change cost.

AI coding agents have rapidly transformed software engineering, powering widely used interactive coding assistants. Despite their interactive real-world use, existing benchmarks evaluate them as fully-autonomous systems. In this work, we introduce Dialogue SWE-Bench, an automatic benchmark dataset for evaluating the ability of coding agents to resolve real-world software engineering problems through dialogue with a user. We design a novel, persona-grounded user simulator to support our task evaluation, and augment our task evaluation with automatic evaluations of dialogue quality. We also propose a new schema-guided agent, aimed at improving the dialogue capabilities of off-the-shelf coding agents, which improves over strong baselines by 3-14%. Our results indicate that better coding models do not always correspond to better dialogue models, suggesting that dialogue capability is a distinct and currently understudied dimension of coding agent performance.

AI coding agents are increasingly used to generate pull requests (PRs) that propose code fixes in software projects. From a first exploration of the AIDev dataset, we find that 46.41% of the fixes proposed by the agents Copilot, Devin, Cursor, and Claude are rejected. This represents a significant amount of wasted resources that require human reviews, verifications, and running tests and validations for fixes that are merely discarded. Our goal in this paper is to understand the failure modes of AI-agents, an understanding that is crucial for better integrating AI-agents as efficient teammates. In this paper, we conduct a qualitative study on a representative sample of 306 non-merged pull requests created or co-authored by the agents mentioned earlier, followed by a quantitative analysis of the reasons for rejection. Our qualitative findings identify 14 reasons divided into four high-level categories for rejecting AI-agent fixes. We observe that developers can reject fixes due to fixes whose implementation is incorrect (e.g., incomplete, wrong approach), fixes that do not pass the continuous integration (CI) pipelines and fail tests, fixes for which the agent is unable to perform the implementation (e.g., no code generated, sessions lost), and fixes whose priority is low. Our results shed light on the importance of better guiding the model at these levels: (1) proposing hints about the approach to follow for fixing an issue, (2) outlining constraints or limitations regarding the approaches that should not be taken, and (3) instructing the agent on how to validate the implementation through CI pipelines and without introducing a breaking change. Our results suggest the need for good prioritization of tasks so that generated fixes do not lead to wasted human review efforts or wasted agent resources (e.g., tokens, compute, or allowed number of requests).

AI-agents (e.g., GitHub Copilot) collaborate as teammates in different software engineering tasks, including code generation proposed through pull requests (Agentic-PRs). For better agent efficiency, developers create instruction files that guide the AI-agents, including how to navigate the project, locate the right components, run tests, respect best practices, and more. In this paper, we investigate the relationship between the creation of these instructions and the performance of AI-agents in creating better pull requests, which have a higher chance of success (i.e., the merge rate), address more complex tasks (e.g., code churn), and require less effort to be merged (e.g., time to merge). To this end, we analyze 15,549 agentic PRs from 148 projects in the AIDev dataset. Using the three dimensions, we compare each project before and after the creation of the instruction files. We find that specifying instructions for AI-agents does not necessarily lead to better results. With the instruction files, 27.7% of the projects increased their merge rate by at least 20%, while 26.35% decreased it. The same observation is seen with the amount of changes (e.g., code churn, number of modified files) and with the efforts to merge an agentic PR (e.g., merge time and number of comments). From a first exploration, we find that projects that managed to increase their merge rate have substantially longer instruction files, which are also well structured into a higher number of sections and sub-sections. Our results motivate the need for research to assist practitioners in framing the development of instruction files as a software engineering activity (aka, \textbf{Instructions-as-Code}).

AI coding tools are now used by a majority of developers, and agentic use of these tools has popularized the practice colloquially called "vibe coding". Yet causal evidence on their effect on software architecture is scarce. Prior causal work has measured code-level outcomes (complexity, static analysis warnings); whether such degradation propagates to architecture-level outcomes remains unknown. We mine 151 open-source Java repositories, 74 with detectable agentic AI adoption (identified via configuration files and Co-Authored-By commit trailers) and 77 propensity-matched controls, across a 13-month per-repository window yielding 1,811 monthly Arcan snapshots. We estimate the causal effect of adoption on architectural smell density (ASD) with a staggered difference-in-differences design and the Borusyak imputation estimator, applying a causal design recently used for code-level metrics to the architecture level. Total smell counts are essentially unchanged (+1.1%, p = 0.82) while lines of code grow +12.8% (p = 0.003); the resulting 6.7% ASD decline (p = 0.004) is therefore a denominator effect rather than an architectural improvement. Per-type estimates and robustness checks (wild cluster bootstrap, Lee bounds, stale-observation sensitivity) corroborate the pattern; pre-trends are flat (Wald p = 0.90), consistent with parallel trends. Density-normalized outcomes can mislead when treatment affects system size: raw counts and explicit decomposition are required for causal mining studies of AI tool adoption. The complete replication package, including the curated 151-repository monthly panel, is publicly available.

Interactive LLM agents are becoming part of daily work, but they do not reliably become easier to work with over time: a correction remembered in one session may still be violated in the next. We study this gap between preference access and preference compliance. In tasks derived from anonymized real-user friction cases, Mem0 memory still leaves 57.5% of applicable preference checks violated. We introduce Test-time Rule Acquisition and Compiled Enforcement (TRACE), a drop-in skill-layer pipeline for coding-agent runtimes that mines user corrections, rewrites them as atomic rules, and compiles them into runtime checks that must pass before an agent completes future tasks. Unlike runtime checks written ahead of time by developers, TRACE skills come from the user's own chat corrections. We evaluate TRACE with simulated user-in-the-loop experiments on ClawArena coding-agent tasks and MemoryArena-derived memory-intensive tasks. On ClawArena, TRACE reduces held-out preference violation from 100.0% to 37.6% on in-distribution tasks and from 100.0% to 2.0% on out-of-distribution tasks. On MemoryArena-derived tasks, TRACE reduces in-distribution violation from 100.0% to 60.5% while matching or exceeding the strongest memory baseline on task pass. These results suggest that compiling corrections into runtime enforcement can address a repeated-friction failure mode that memory alone does not reliably solve, reducing the need for users to restate the same correction across future sessions. Experiment code is available at https://github.com/YujunZhou/TRACE_exp, and the deployable skill is available at https://github.com/YujunZhou/tellonce.

General-purpose agents such as OpenClaw are increasingly used as autonomous tool users, but their coding ability is difficult to measure under SWE-bench: a generic agent does not by itself satisfy the clean Docker workspace, patch, and prediction contract required for scoring. We introduce Claw-SWE-Bench, a multilingual SWE-bench-style benchmark and adapter protocol that makes heterogeneous agent harnesses, or claws, comparable under fair settings including a fixed prompt, runtime budget, workspace contract, patch extraction procedure, and evaluator. The full benchmark contains 350 GitHub issue-resolution instances across 8 languages and 43 repositories, drawn from SWE-bench-Multilingual and SWE-bench-Verified-Mini after future-commit cleanup. We also release Claw-SWE-Bench Lite for faster validation, which is an 80-instance subset selected by a cost-aware, rank-aware procedure over 17 calibration columns. On the full benchmark, OpenClaw with a minimal direct-diff adapter scores only $19.1\%$ Pass@1, whereas the full adapter reaches $73.4\%$ with the same GLM 5.1 backbone, showing that adapter design is essential for enabling OpenClaw-style harnesses to perform coding tasks effectively. Across an OpenClaw $\times$ nine-model sweep and a five-claw $\times$ two-model sweep, model choice changes Pass@1 by $29.4$ pp and harness choice by $27.4$ pp under fixed models; systems with similar accuracy can differ substantially in total API cost. Claw-SWE-Bench therefore treats harness and cost accounting as first-class axes of SWE-style coding-agent evaluation, providing both a full benchmark and a low-cost reference set for reproducible comparison. The data is available at https://github.com/opensquilla/claw-swe-bench and https://huggingface.co/datasets/TokenRhythm/Claw-SWE-Bench.

AI coding assistants now support a growing share of software work, from quick scripts to production applications. Yet these agents remain largely stateless: each new session re-reads project files, re-derives prior decisions, and - most costly - may repeat debugging attempts that already failed. Reconstructing this context can consume an estimated 5,000-20,000 tokens per session; the bottleneck is often not model capability but missing project memory. We present projectmem, an open-source, local-first memory and judgment layer for AI coding agents. projectmem records development as an append-only, plain-text event log of typed events - issues, attempts, fixes, decisions, and notes - and deterministically projects that log into compact, AI-readable summaries served through the Model Context Protocol (MCP). Beyond storage, projectmem adds a deterministic pre-action gate that warns an agent before it repeats a previously failed fix or edits a known-fragile file. We frame this as Memory-as-Governance: memory that does not merely answer the agent but acts on its next action. The system runs fully offline with no telemetry; its immutable log also serves as a provenance trail for reproducible, auditable AI-assisted development. projectmem ships as a three-dependency Python package (14 MCP tools, 19 CLI commands, 37 automated tests) and is evaluated through a two-month self-study across 10 projects comprising 207 logged events. Source code: https://github.com/riponcm/projectmem.

Financial and tabular question answering requires more than fluent reasoning: answers must be grounded in the exact facts, formulas, units, signs, and scales that support them. A single misread cell or incorrect operation can silently produce a plausible but wrong result. We introduce \textsc{MOCA-Agent}, a market-of-claims code agent that replaces free-form multi-agent debate with claim-level verification. The system decomposes each question into typed atomic claims, asks specialist trader agents to buy or sell those claims, clears their orders into confidence-weighted accept/reject decisions, and synthesizes an executable Python program from market-supported evidence. A code-aware verifier then checks the program for execution, structural consistency, and common financial reasoning errors, with at most one market-aware repair round. Across ten public benchmarks spanning financial numerical reasoning, general tabular reasoning, ESG question answering, and multimodal chart reasoning, \textsc{MOCA-Agent} achieves strong performance using a fixed Qwen3.6-27B backbone, including $78.3\%$ on FinQA, $76.0\%$ on FinanceMath, $71.2\%$ on MultiHiertt, $86.9\%$ on ESGenius, and $85.6\%$ average on FinChart-Bench. These results show that aggregating evidence at the level of atomic claims, rather than whole answers, improves robustness in high-stakes numerical reasoning.\footnote{The code and data are available: https://github.com/UBC-NLP/MoCA-Agent.