EvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification

Anthropic proposes the concept of skills for LLM agents to tackle multi-step professional tasks that simple tool invocations cannot address. A tool is a single, self-contained function, whereas a skill is a structured bundle of interdependent multi-file artifacts. Currently, skill generation is not only label-intensive due to manual authoring, but also may suffer from human--machine cognitive misalignment, which can lead to degraded agent performance, as evidenced by evaluations on SkillsBench. Therefore, we aim to enable agents to autonomously generate skills. However, existing self-evolving methods designed for tools cannot be directly applied to skills due to their increased complexity. To address these issues, we propose EvoSkills, a self-evolving skills framework that enables agents to autonomously construct complex, multi-file skill packages. Specifically, EvoSkills couples a Skill Generator that iteratively refines skills with a Surrogate Verifier that co-evolves to provide informative and actionable feedback without access to ground-truth test content. On SkillsBench, EvoSkills achieves the highest pass rate among five baselines on both Claude Code and Codex, and also exhibits strong generalization capabilities to six additional LLMs.

PHMForge: A Scenario-Driven Agentic Benchmark for Industrial Asset Lifecycle Maintenance

Large language model (LLM) agents are increasingly deployed for complex tool-orchestration tasks, yet existing benchmarks fail to capture the rigorous demands of industrial domains where incorrect decisions carry significant safety and financial consequences. To address this critical gap, we introduce PHMForge, the first comprehensive benchmark specifically designed to evaluate LLM agents on Prognostics and Health Management (PHM) tasks through realistic interactions with domain-specific MCP servers. Our benchmark encompasses 75 expert-curated scenarios spanning 7 industrial asset classes (turbofan engines, bearings, electric motors, gearboxes, aero-engines) across 5 core task categories: Remaining Useful Life (RUL) Prediction, Fault Classification, Engine Health Analysis, Cost-Benefit Analysis, and Safety/Policy Evaluation. To enable rigorous evaluation, we construct 65 specialized tools across two MCP servers and implement execution-based evaluators with task-commensurate metrics: MAE/RMSE for regression, F1-score for classification, and categorical matching for health assessments. Through extensive evaluation of leading frameworks (ReAct, Cursor Agent, Claude Code) paired with frontier LLMs (Claude Sonnet 4.0, GPT-4o, Granite-3.0-8B), we find that even top-performing configurations achieve only 68\% task completion, with systematic failures in tool orchestration (23\% incorrect sequencing), multi-asset reasoning (14.9 percentage point degradation), and cross-equipment generalization (42.7\% on held-out datasets). We open-source our complete benchmark, including scenario specifications, ground truth templates, tool implementations, and evaluation scripts, to catalyze research in agentic industrial AI.

Investigating Autonomous Agent Contributions in the Wild: Activity Patterns and Code Change over Time

The rise of large language models for code has reshaped software development. Autonomous coding agents, able to create branches, open pull requests, and perform code reviews, now actively contribute to real-world projects. Their growing role offers a unique and timely opportunity to investigate AI-driven contributions and their effects on code quality, team dynamics, and software maintainability. In this work, we construct a novel dataset of approximately $110,000$ open-source pull requests, including associated commits, comments, reviews, issues, and file changes, collectively representing millions of lines of source code. We compare five popular coding agents, including OpenAI Codex, Claude Code, GitHub Copilot, Google Jules, and Devin, examining how their usage differs in various development aspects such as merge frequency, edited file types, and developer interaction signals, including comments and reviews. Furthermore, we emphasize that code authoring and review are only a small part of the larger software engineering process, as the resulting code must also be maintained and updated over time. Hence, we offer several longitudinal estimates of survival and churn rates for agent-generated versus human-authored code. Ultimately, our findings indicate an increasing agent activity in open-source projects, although their contributions are associated with more churn over time compared to human-authored code.

VibeGuard: A Security Gate Framework for AI-Generated Code

"Vibe coding," in which developers delegate code generation to AI assistants and accept the output with little manual review, has gained rapid adoption in production settings. On March 31, 2026, Anthropic's Claude Code CLI shipped a 59.8 MB source map file in its npm package, exposing roughly 512,000 lines of proprietary TypeScript. The tool had itself been largely vibe-coded, and the leak traced to a misconfigured packaging rule rather than a logic bug. Existing static-analysis and secret-scanning tools did not cover this failure mode, pointing to a gap between the vulnerabilities AI tends to introduce and the vulnerabilities current tooling is built to find. We present VibeGuard, a pre-publish security gate that targets five such blind spots: artifact hygiene, packaging-configuration drift, source-map exposure, hardcoded secrets, and supply-chain risk. In controlled experiments on eight synthetic projects (seven vulnerable, one clean control), VibeGuard achieved 100% recall, 89.47% precision (F1 = 94.44%), and correct pass/fail gate decisions on all eight projects across three policy levels. We discuss how these results inform a defense-in-depth workflow for teams that rely on AI code generation.

AEC-Bench: A Multimodal Benchmark for Agentic Systems in Architecture, Engineering, and Construction

The AEC-Bench is a multimodal benchmark for evaluating agentic systems on real-world tasks in the Architecture, Engineering, and Construction (AEC) domain. The benchmark covers tasks requiring drawing understanding, cross-sheet reasoning, and construction project-level coordination. This report describes the benchmark motivation, dataset taxonomy, evaluation protocol, and baseline results across several domain-specific foundation model harnesses. We use AEC-Bench to identify consistent tools and harness design techniques that uniformly improve performance across foundation models in their own base harnesses, such as Claude Code and Codex. We openly release our benchmark dataset, agent harness, and evaluation code for full replicability at https://github.com/nomic-ai/aec-bench under an Apache 2 license.

UK AISI Alignment Evaluation Case-Study

This technical report presents methods developed by the UK AI Security Institute for assessing whether advanced AI systems reliably follow intended goals. Specifically, we evaluate whether frontier models sabotage safety research when deployed as coding assistants within an AI lab. Applying our methods to four frontier models, we find no confirmed instances of research sabotage. However, we observe that Claude Opus 4.5 Preview (a pre-release snapshot of Opus 4.5) and Sonnet 4.5 frequently refuse to engage with safety-relevant research tasks, citing concerns about research direction, involvement in self-training, and research scope. We additionally find that Opus 4.5 Preview shows reduced unprompted evaluation awareness compared to Sonnet 4.5, while both models can distinguish evaluation from deployment scenarios when prompted. Our evaluation framework builds on Petri, an open-source LLM auditing tool, with a custom scaffold designed to simulate realistic internal deployment of a coding agent. We validate that this scaffold produces trajectories that all tested models fail to reliably distinguish from real deployment data. We test models across scenarios varying in research motivation, activity type, replacement threat, and model autonomy. Finally, we discuss limitations including scenario coverage and evaluation awareness.

GEMS: Agent-Native Multimodal Generation with Memory and Skills

Recent multimodal generation models have achieved remarkable progress on general-purpose generation tasks, yet continue to struggle with complex instructions and specialized downstream tasks. Inspired by the success of advanced agent frameworks such as Claude Code, we propose \textbf{GEMS} (Agent-Native Multimodal \textbf{GE}neration with \textbf{M}emory and \textbf{S}kills), a framework that pushes beyond the inherent limitations of foundational models on both general and downstream tasks. GEMS is built upon three core components. Agent Loop introduces a structured multi-agent framework that iteratively improves generation quality through closed-loop optimization. Agent Memory provides a persistent, trajectory-level memory that hierarchically stores both factual states and compressed experiential summaries, enabling a global view of the optimization process while reducing redundancy. Agent Skill offers an extensible collection of domain-specific expertise with on-demand loading, allowing the system to effectively handle diverse downstream applications. Across five mainstream tasks and four downstream tasks, evaluated on multiple generative backends, GEMS consistently achieves significant performance gains. Most notably, it enables the lightweight 6B model Z-Image-Turbo to surpass the state-of-the-art Nano Banana 2 on GenEval2, demonstrating the effectiveness of agent harness in extending model capabilities beyond their original limits.

AI-Generated Prior Authorization Letters: Strong Clinical Content, Weak Administrative Scaffolding

Prior authorization remains one of the most burdensome administrative processes in U.S. healthcare, consuming billions of dollars and thousands of physician hours each year. While large language models have shown promise across clinical text tasks, their ability to produce submission-ready prior authorization letters has received only limited attention, with existing work confined to single-case demonstrations rather than structured multi-scenario evaluation. We assessed three commercially available LLMs (GPT-4o, Claude Sonnet 4.5, and Gemini 2.5 Pro) across 45 physician-validated synthetic scenarios spanning rheumatology, psychiatry, oncology, cardiology, and orthopedics. All three models generated letters with strong clinical content: accurate diagnoses, well-structured medical necessity arguments, and thorough step therapy documentation. However, a secondary analysis of real-world administrative requirements revealed consistent gaps that clinical scoring alone did not capture, including absent billing codes, missing authorization duration requests, and inadequate follow-up plans. These findings reframe the question: the challenge for clinical deployment is not whether LLMs can write clinically adequate letters, but whether the systems built around them can supply the administrative precision that payer workflows require.

Needle in the Repo: A Benchmark for Maintainability in AI-Generated Repository Edits

AI coding agents can now complete complex programming tasks, but existing evaluations largely emphasize behavioral correctness and often overlook maintainability risks such as weak modularity or testability. We present Needle in the Repo (NITR), a diagnostic probe-and-oracle framework for evaluating whether behaviorally correct repository edits preserve maintainable structure. NITR distills recurring software engineering wisdom into controlled probes embedded in small, realistic multi-file codebases, each designed so that success depends primarily on one targeted maintainability dimension. Each probe is paired with a hidden evaluation harness that combines functional tests for required behavior with structural oracles that encode the targeted maintainability constraint and return interpretable diagnoses. Using NITR, we evaluate 23 coding configurations across GPT, Claude, Gemini, and Qwen families in both direct-inference and agent-based settings. Current AI coding systems remain far from robust: on average, configurations solve only 36.2% of cases, the best reaches 57.1%, and performance drops from 53.5% on micro cases to 20.6% on multi-step cases. The hardest pressures are architectural rather than local edits, especially dependency control (4.3%) and responsibility decomposition (15.2%). Moreover, 64/483 outcomes (13.3%) pass all functional tests yet fail the structural oracle. Under our harness, agent-mode configurations improve average performance from 28.2% to 45.0%, but do not eliminate these architectural failures. These results show that progress in code generation is not yet progress in maintainable code evolution, and that NITR exposes a critical failure surface missed by conventional evaluation.

APEX-EM: Non-Parametric Online Learning for Autonomous Agents via Structured Procedural-Episodic Experience Replay

LLM-based autonomous agents lack persistent procedural memory: they re-derive solutions from scratch even when structurally identical tasks have been solved before. We present \textbf{APEX-EM}, a non-parametric online learning framework that accumulates, retrieves, and reuses structured procedural plans without modifying model weights. APEX-EM introduces: (1) a \emph{structured experience representation} encoding the full procedural-episodic trace of each execution -- planning steps, artifacts, iteration history with error analysis, and quality scores; (2) a \emph{Plan-Retrieve-Generate-Iterate-Ingest} (PRGII) workflow with Task Verifiers providing multi-dimensional reward signals; and (3) a \emph{dual-outcome Experience Memory} with hybrid retrieval combining semantic search, structural signature matching, and plan DAG traversal -- enabling cross-domain transfer between tasks sharing no lexical overlap but analogous operational structure. Successful experiences serve as positive in-context examples; failures as negative examples with structured error annotations. We evaluate on BigCodeBench~\cite{zhuo2025bigcodebench}, KGQAGen-10k~\cite{zhang2025kgqagen}, and Humanity's Last Exam~\cite{phan2025hle} using Claude Sonnet 4.5 and Opus 4.5. On KGQAGen-10k, APEX-EM achieves 89.6\% accuracy versus 41.3\% without memory (+48.3pp), surpassing the oracle-retrieval upper bound (84.9\%). On BigCodeBench, it reaches 83.3\% SR from a 53.9\% baseline (+29.4pp), exceeding MemRL's~\cite{memrl2025} +11.0pp gain under comparable frozen-backbone conditions (noting backbone differences controlled for in our analysis). On HLE, entity graph retrieval reaches 48.0\% from 25.2\% (+22.8pp). Ablations show component value is task-dependent: rich judge feedback is negligible for code generation but critical for structured queries (+10.3pp), while binary-signal iteration partially compensates for weaker feedback.