MicroVerse: An Instrument for Measuring Self-Authored Identity Drift in Long-Horizon Multi-Agent Language-Model Simulations

Long-horizon, multi-agent language model (LM) simulations are widely proposed for studying social behavior, yet instruments to measure whether persona-conditioned agents maintain identity fidelity under sustained pressure are lacking. We present MicroVerse, a behavioral-science instrument that measures identity drift in generative agents. Agents carry an immutable "soul file" (core values, moral boundaries, personality, goals) and inhabit a resource-scarce 50 x 50 environment where water is a non-respawning survival constraint. Scarcity is operationalized via a per-tick existence-cost gradient. The eight-verb action space maps directly to moral boundaries (trade, talk, attack, scavenge). Using a three-layer memory architecture, agents periodically revise a mutable current identity against their immutable original soul via importance-triggered reflection. To mitigate survivor bias, MicroVerse decouples measurement from behavior using uniform longitudinal engine snapshots every N ticks alongside a forced-end snapshot of all living and dead agents. Identity drift is scored offline using a paraphrase-aware, value-anchored, multi-register diff rather than raw cosine similarity. We evaluate the instrument via a controlled seed run (n = 25) and a reflection-threshold sweep (thresholds {40, 80, 150}) to determine if drift dynamics are gate artifacts or threshold-robust properties. We report two primary findings: (1) Anti-self-deception emerges unprompted as the single largest semantic category of identity modification (27 of 111 added boundaries, 24%). (2) The system is threshold-robust; lower gates accelerate and increase revision frequency but preserve drift direction. All empirical results are strictly preliminary existence proofs and effect shapes (one model, one seed per arm, n = 25) rather than statistical significance claims.

Demystifying Agent Skills: Why They Work-Until They Don't

Skills have emerged as a practical and effective approach for enhancing LLM agents at inference time through structured packages of knowledge. However, existing evaluations largely measure whether skills improve aggregated task success, leaving a more fundamental question underexplored: \emph{\textbf{When do skills help, why do they work, and where do they fail?}} Through controlled experiments across various benchmarks, agent harnesses and LLMs, we isolate the effects of representation, outcome annotation, retrieval difficulty, and cross-framework robustness of skills. To further answer this question, we design a contrastive study that combines controlled quantitative experiments with paired trajectory analysis. We normalize 8,135 trial records from controlled experiments and retain 238 valid unique labels from 240 open-coded records. We consolidate these observations into a taxonomy of three high-level categories and twelve skill-use modes: skills work when noisy trajectories become procedural anchors that stabilize execution. Skills improve over Workflow Memory by 6.06 points in matched comparisons. Procedural anchoring accounts for 65.7\% of skill cases, versus 4.5\% for explicit knowledge injection, showing that skills stabilize action rather than inject missing facts. Retrieval is a separate bottleneck: as pools grow from 5 to 100, actual-use precision falls from 29.6\% to 3.3\%. Confusable distractors impair offline identification, yet downstream success remains stable; exact ground-truth invocation is neither sufficient nor necessary. Skills fail under brittle assumptions, incompatible contexts, or insufficient adaptation. These findings move evaluation beyond aggregate success rates and guide reliable self-evolving agents.

MatrAIx: Simulating the World with 8.3 Billion Persona Agents

Human evaluation of AI systems and digital products is costly, slow, and difficult to scale. Offline evaluations are more scalable but often abstract away human diversity and interactive behavior. We therefore introduce MatrAIx, a population-scale simulated-user evaluation infrastructure for testing AI systems and digital products with heterogeneous users. MatrAIx has three core components: First, Persona 8B contains 8.3 billion persona records represented by 1,290 categorical dimensions. Records are either sampled from a dependency graph that preserves correlated attributes or derived from human-authored profiles. We release a quality-filtered coreset of approximately 1 million personas, comprising 599,847 human-grounded and 400,000 synthetic records. Second, the MatrAIx Playground provides four environments in which diverse users evaluate and interact with digital products: Survey, AI Chatbot, Web, and App. Third, MatrAIx provides 1,010 application tasks spanning more than 25 domains, including Commerce, Software, Finance, and Healthcare. We conducted 18,189 evaluation trials across eight representative tasks. Persona agents were powered by three LLMs: Claude Opus 4.8, GPT 5.5, and Claude Haiku 4.5. The resulting feedback captures how decisions and preferences vary across persona backgrounds, including hesitation after a price increase, willingness to continue after an AI assistant fails, and latency tolerance. We conducted two main validation studies: First, a 400-trial controlled study evaluated persona adherence across ten behavioral attributes and all four environments. The declared behavior was expressed or correctly suppressed in 366 trials (91.5%). Second, human and LLM judges evaluated the extraction quality of human-grounded personas. Overall, MatrAIx provides an end-to-end infrastructure for evaluating AI systems and digital products with diverse simulated human users.

CurveShift: Is Agent Progress Scalar? Separating Level from Shape

Progress in large language models is often summarized using a single scalar measure, such as a time horizon, a latent ability estimate, or an aggregate benchmark score. These summaries capture the overall performance, but they do not test whether progress is distributed differently across task difficulty. We find that most of the apparent shift in gains toward harder tasks does not reflect a change in the shape of the difficulty-response curve. On METR time-horizon data, a single Rasch model with rising ability reproduces this pattern, so it is largely explained by ceiling effects rather than a qualitative change in capability. This echoes how the choice of metric can make claimed emergent abilities look like a property of the models themselves. We then identify a smaller hard-task effect that survives this control. Isolating it is difficult on agentic benchmarks, because newer models are usually run with newer agentic harnesses, so a gain on hard tasks cannot be assigned to the model or its scaffold. We break the confound with LiveCodeBench, a public competitive programming benchmark that runs no agentic scaffold while pairing dated models with an exogenous difficulty ordering. After accounting for the rise in overall ability, models released after September 2024 still gain on the hardest problems beyond what their easy and medium performance predicts, by about +0.40 logits under our most conservative assumption, raising the hard-problem solve rate from roughly 18% to 25%. The effect is led by the strongest reasoning models and holds for hard tasks that need only short reasoning, not autonomy over long horizons. We present this as a result specific to competitive programming, since our clean identification rests on a single coding benchmark. We release the LiveCodeBench Difficulty Panel (66 dated models x 1,055 problems) and our analysis code.

OpenThoughts-Agent: Data Recipes for Agentic Models

Agentic language models dramatically expand the applications of AI yet little is publicly known about how to curate training data for broadly capable agents. Existing open efforts such as SWE-Smith, SERA, and Nemotron-Terminal typically target a single benchmark, leaving open the question of how to train models that generalize across diverse agentic tasks. The OpenThoughts-Agent (OT-Agent) project addresses this gap with a fully open data curation pipeline for training agentic models. We conduct more than 100 controlled ablation experiments to systematically investigate each stage of the pipeline, yielding insights on the importance of task sources and diversity. We then assemble a training set of 100K examples from our pipeline and fine-tune Qwen3-32B on this dataset, which yields an average accuracy of 44.8% across seven agentic benchmarks and a 3.9 percentage point improvement over the strongest existing open data agentic model (Nemotron-Terminal-32B, 40.9%). Moreover, our training data exhibits strong scaling properties, outperforming alternative open datasets at every training set size in compute-controlled comparisons. We publicly release our training sets, data pipeline, experimental data, and models at openthoughts.ai to support future open research on agentic model training.

Agents' Last Exam

Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional domains. We argue that this gap is largely an evaluation problem: widely used benchmarks lack sustained performance measurement on real and economically valuable workflows. This paper introduces Agents' Last Exam (ALE), a benchmark designed to evaluate AI agents on long-horizon, economically valuable, real-world tasks with verifiable outcomes. Developed in collaboration with 250+ industry experts, ALE covers non-physical industries defined with reference to O*NET / SOC 2018 (the U.S. federal occupational taxonomy). It is organized around a task taxonomy with 55 subfields grouped into 13 industry clusters covering 1K+ tasks. Current results show that the hardest tier remains far from saturated: across mainstream harness and backbone configurations, the average full pass rate is 2.6%. ALE is designed as a living benchmark: its task pool grows continuously as new workflows and industries are onboarded. More broadly, ALE is intended not merely as another leaderboard, but as an instrument for closing the gap between benchmark success and GDP-relevant impact.

AgentTrap: Measuring Runtime Trust Failures in Third-Party Agent Skills

Third-party skills are becoming the package ecosystem for LLM agents. They package natural-language instructions, helper scripts, templates, documents, and service configuration into reusable workflows. This makes skills useful, but it also introduces a new security problem: a malicious skill does not need to ask the model to perform an obviously harmful action. Instead, it can disguise the harmful behavior as part of a routine workflow, relying on the agent to execute that workflow with high-value permissions and limited human supervision. We introduce AgentTrap, a dynamic benchmark for evaluating whether LLM agents can use third-party skills while resisting malicious runtime behavior. AgentTrap contains 141 tasks: 91 malicious tasks and 50 benign utility tasks, covering 16 security-impact dimensions grounded in agent-skill supply-chain threats. In each task, the agent receives an ordinary user request, runs with installed skills that may contain malicious workflow elements, and is executed in a sandboxed environment. AgentTrap then judges complete trajectories for attack success, blocked or refused behavior, attack-not-triggered cases, and no-attack-evidence outcomes. Our central finding is that the most informative failures are not simple jailbreaks. Models often complete the visible user task while treating unsafe side effects introduced by the skill as part of the normal workflow. This motivates runtime evaluation of the concrete model--framework--workspace environment in which users actually delegate work. Code and data are available at https://github.com/zhmzm/AgentTrap and https://huggingface.co/datasets/zhmzm/AgentTrap.

Martingale-Consistent Self-Supervised Learning

Self-supervised learning (SSL) is often deployed under changing information, such as shorter histories, missing features, or partially observed images. In these settings, predictions from coarse and refined views should be coherent: before refinement, the coarse-view prediction should match the average prediction expected after refinement. Martingales formalize this coherence principle, but standard SSL objectives do not enforce it. Unlike invariance objectives that pull views together, martingale consistency constrains only the expected refined prediction, allowing predictions to update as information is revealed while preventing systematic drift. We introduce a martingale-consistent SSL framework that closes this gap, with practical prediction- and latent-space variants and an unbiased two-sample Monte Carlo estimator based on stochastic refinement. We evaluate the approach on synthetic and real time-series, tabular, and image benchmarks under partial-observation regimes, in both semi-self-supervised and fully label-free settings. Across these experiments, our framework improves robustness and calibration under partial observation, yielding more stable representations as information is revealed.

A Very Big Video Reasoning Suite

Rapid progress in video models has largely focused on visual quality, leaving their reasoning capabilities underexplored. Video reasoning grounds intelligence in spatiotemporally consistent visual environments that go beyond what text can naturally capture, enabling intuitive reasoning over spatiotemporal structure such as continuity, interaction, and causality. However, systematically studying video reasoning and its scaling behavior is hindered by the lack of large-scale training data. To address this gap, we introduce the Very Big Video Reasoning (VBVR) Dataset, an unprecedentedly large-scale resource spanning 200 curated reasoning tasks following a principled taxonomy and over one million video clips, approximately three orders of magnitude larger than existing datasets. We further present VBVR-Bench, a verifiable evaluation framework that moves beyond model-based judging by incorporating rule-based, human-aligned scorers, enabling reproducible and interpretable diagnosis of video reasoning capabilities. Leveraging the VBVR suite, we conduct one of the first large-scale scaling studies of video reasoning and observe early signs of emergent generalization to unseen reasoning tasks. Together, VBVR lays a foundation for the next stage of research in generalizable video reasoning. The data, benchmark toolkit, and models are publicly available at https://video-reason.com/ .

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Agent Skills are structured packages of procedural knowledge that augment LLM agents at inference time. Despite rapid adoption, there is no standard way to measure whether they actually help. We present SkillsBench, a benchmark of 86 tasks across 11 domains paired with curated Skills and deterministic verifiers. Each task is evaluated under three conditions: no Skills, curated Skills, and self-generated Skills. We test 7 agent-model configurations over 7,308 trajectories. Curated Skills raise average pass rate by 16.2 percentage points(pp), but effects vary widely by domain (+4.5pp for Software Engineering to +51.9pp for Healthcare) and 16 of 84 tasks show negative deltas. Self-generated Skills provide no benefit on average, showing that models cannot reliably author the procedural knowledge they benefit from consuming. Focused Skills with 2--3 modules outperform comprehensive documentation, and smaller models with Skills can match larger models without them.