Context-aided forecasting (CAF) holds promise for integrating domain knowledge and forward-looking information, enabling AI systems to surpass traditional statistical methods. However, recent empirical studies reveal a puzzling gap: multimodal models often fail to outperform their unimodal counterparts. We hypothesize that this underperformance stems from poor context quality in existing datasets, as verification is challenging. To address these limitations, we introduce a semi-synthetic data augmentation method that generates contexts both descriptive of temporal dynamics and verifiably complementary to numerical histories. This approach enables massive-scale dataset creation, resulting in CAF-7M, a corpus of 7 million context-augmented time series windows, including a rigorously verified test set. We demonstrate that semi-synthetic pre-training transfers effectively to real-world evaluation, and show clear evidence of context utilization. Our results suggest that dataset quality, rather than architectural limitations, has been the primary bottleneck in context-aided forecasting.

Building general-purpose reasoning models using reinforcement learning with verifiable rewards (RLVR) across diverse domains has been widely adopted by frontier open-weight models. However, their training recipes and domain mixtures are often not disclosed. Joint optimization across domains poses significant challenges: domains vary widely in rollout length, problem difficulty and sample efficiency. Further, models with long chain-of-thought traces increase inference cost and latency, making efficiency critical for practical deployment. We present Apriel-1.5-OpenReasoner, trained with a fully reproducible multi-domain RL post-training recipe on Apriel-Base, a 15B-parameter open-weight LLM, across five domains using public datasets: mathematics, code generation, instruction following, logical puzzles and function calling. We introduce an adaptive domain sampling mechanism that preserves target domain ratios despite heterogeneous rollout dynamics, and a difficulty-aware extension of the standard length penalty that, with no additional training overhead, encourages longer reasoning for difficult problems and shorter traces for easy ones. Trained with a strict 16K-token output budget, Apriel-1.5-OpenReasoner generalizes to 32K tokens at inference and improves over Apriel-Base on AIME 2025, GPQA, MMLU-Pro, and LiveCodeBench while producing 30-50

Open-weight LLM agents are vulnerable to backdoors installed during fine-tuning, which may be undetectable if the trigger conditions are never met during testing. Assuming defenders do not know the existing trigger, they cannot unlearn it directly. One decontamination strategy is to install a known backdoor (defensive poisoning) then to unlearn it, hoping that the original unknown backdoor is removed as a side effect. However, this procedure has uncertain outcomes: the original backdoor may persist or be erased or rerouted, among other possibilities. We introduce a framework for studying these dynamics in tool-calling agents, decoupling trigger, response, teacher, and fine-tuning method across systematic experiments on AgentDyn. Across 115 experiments, defensive poisoning alone erases around 56

Time series forecasting in real-world settings often depends not only on historical observations, but also on external context that must be actively discovered from noisy, heterogeneous information sources. Yet existing context-aided forecasting benchmarks typically assume that the supporting context is already provided, leaving open whether agents can identify it on their own. Therefore, we introduce Dr-CiK, a benchmark for evaluating whether agents can retrieve forecasting-relevant supporting context from a document corpus, filter out distractors, distill the retrieved context into forecast-useful evidence, and generate forecasts supported by that evidence. Through context ablations and evaluations of state-of-the-art deep research and forecasting methods paired together, we show that high-quality context substantially improves forecasting performance in Dr-CiK. However, most existing DR agents recover only a small fraction of the ground-truth supporting evidence (usually <5

Agent systems are advancing quickly across domains, but their evaluation remains fragmented. Most benchmarks rely on fixed, LLM-centric harnesses that require heavy integration, create test-production mismatch, and limit fair comparison across diverse agent designs. The root problem is the lack of an open, agent-agnostic assessment interface. We advocate Agentified Agent Assessment (AAA), where evaluation is performed by judge agents and all participants interact through standardized protocols: A2A for task management and MCP for tool access. Conventional benchmarking defines two separate interfaces, one for the benchmark and one for the agent, while AAA only needs one; this yields a generic, unified framework that separates assessment logic from agent implementation and enables reproducible, interoperable, and multi-agent evaluation. We further introduce AgentBeats as a concrete realization of AAA: we identify five practical operation modes that make standardized assessment compatible with real-world constraints on openness, privacy, and reproducibility. To evaluate our design at scale, we conduct two studies: a five-month open competition that drew 298 judge agents across 12 categories together with 467 subject agents from independent participants, showing that AAA applies across a heterogeneous range of benchmarks; and a case study on coding agents that confirms agentified evaluation preserves fidelity with the public record while surfacing previously missing head-to-head results, yielding research insights about agent design. Combining a community-scale field study and a controlled coding case study, we verify that AAA delivers coverage, practicality, and fidelity across heterogeneous scenarios at scale. Together, AAA and AgentBeats offer a clear path toward open, standardized, and reproducible agent assessment.

We introduce DRBench, a benchmark for evaluating AI agents on complex, open-ended deep research tasks in enterprise settings. Unlike prior benchmarks that focus on simple questions or web-only queries, DRBench evaluates agents on multi-step queries (for example, "What changes should we make to our product roadmap to ensure compliance with this standard?") that require identifying supporting facts from both the public web and private company knowledge base. Each task is grounded in realistic user personas and enterprise context, spanning a heterogeneous search space that includes productivity software, cloud file systems, emails, chat conversations, and the open web. Tasks are generated through a carefully designed synthesis pipeline with human-in-the-loop verification, and agents are evaluated on their ability to recall relevant insights, maintain factual accuracy, and produce coherent, well-structured reports. We release 100 deep research tasks across 10 domains, such as Sales, Cybersecurity, and Compliance. We demonstrate the effectiveness of DRBench by evaluating diverse DR agents across open- and closed-source models (such as GPT, Llama, and Qwen) and DR strategies, highlighting their strengths, weaknesses, and the critical path for advancing enterprise deep research.

Deep research agents increasingly combine private local documents with external tools like web retrieval, creating a privacy risk: an agent's external queries may leak sensitive information from its local context. This risk is amplified by the mosaic effect, where individual queries may appear harmless but become revealing in aggregate. We introduce MosaicLeaks, a benchmark of 1,001 multi-hop deep research tasks that chain private enterprise documents and a public web corpus, forcing agents to make external queries that depend on local information. We evaluate leakage with an adversary LLM that observes only the agent's external queries and attempts to infer private information at three levels: the agent's research intent, answers to specific private questions and verifiable claims about the enterprise documents. We find that models across families and sizes frequently leak at all three levels, that zero-shot privacy prompting reduces but does not eliminate leakage and that reinforcement learning for task performance alone worsens leakage. To address this, we propose Privacy-Aware Deep Research (PA-DR), an RL framework that combines situational rewards for task success with a learned privacy classifier to provide dense credit assignment over both per-query and mosaic-level leakage. Training Qwen3-4B-Instruct with PA-DR improves accuracy from 48.7

The proliferation of agent benchmarks has created critical fragmentation that threatens research productivity. Each new benchmark requires substantial custom integration, creating an "integration tax" that limits comprehensive evaluation. We propose CUBE (Common Unified Benchmark Environments), a universal protocol standard built on MCP and Gym that allows benchmarks to be wrapped once and used everywhere. By separating task, benchmark, package, and registry concerns into distinct API layers, CUBE enables any compliant platform to access any compliant benchmark for evaluation, RL training, or data generation without custom integration. We call on the community to contribute to the development of this standard before platform-specific implementations deepen fragmentation as benchmark production accelerates through 2026.

Integrating expert knowledge, e.g. from large language models, into causal discovery algorithms can be challenging when the knowledge is not guaranteed to be correct. Expert recommendations may contradict data-driven results, and their reliability can vary significantly depending on the domain or specific query. Existing methods based on soft constraints or inconsistencies in predicted causal relationships fail to account for these variations in expertise. To remedy this, we propose L2D-CD, a method for gauging the correctness of expert recommendations and optimally combining them with data-driven causal discovery results. By adapting learning-to-defer (L2D) algorithms for pairwise causal discovery (CD), we learn a deferral function that selects whether to rely on classical causal discovery methods using numerical data or expert recommendations based on textual meta-data. We evaluate L2D-CD on the canonical Tübingen pairs dataset and demonstrate its superior performance compared to both the causal discovery method and the expert used in isolation. Moreover, our approach identifies domains where the expert's performance is strong or weak. Finally, we outline a strategy for generalizing this approach to causal discovery on graphs with more than two variables, paving the way for further research in this area.

Causal discovery aims to automatically uncover causal relationships from data, a capability with significant potential across many scientific disciplines. However, its real-world applications remain limited. Current methods often rely on unrealistic assumptions and are evaluated only on simple synthetic toy datasets, often with inadequate evaluation metrics. In this paper, we substantiate these claims by performing a systematic review of the recent causal discovery literature. We present applications in biology, neuroscience, and Earth sciences - fields where causal discovery holds promise for addressing key challenges. We highlight available simulated and real-world datasets from these domains and discuss common assumption violations that have spurred the development of new methods. Our goal is to encourage the community to adopt better evaluation practices by utilizing realistic datasets and more adequate metrics.

Forecasting is a critical task in decision-making across numerous domains. While historical numerical data provide a start, they fail to convey the complete context for reliable and accurate predictions. Human forecasters frequently rely on additional information, such as background knowledge and constraints, which can efficiently be communicated through natural language. However, in spite of recent progress with LLM-based forecasters, their ability to effectively integrate this textual information remains an open question. To address this, we introduce "Context is Key" (CiK), a time-series forecasting benchmark that pairs numerical data with diverse types of carefully crafted textual context, requiring models to integrate both modalities; crucially, every task in CiK requires understanding textual context to be solved successfully. We evaluate a range of approaches, including statistical models, time series foundation models, and LLM-based forecasters, and propose a simple yet effective LLM prompting method that outperforms all other tested methods on our benchmark. Our experiments highlight the importance of incorporating contextual information, demonstrate surprising performance when using LLM-based forecasting models, and also reveal some of their critical shortcomings. This benchmark aims to advance multimodal forecasting by promoting models that are both accurate and accessible to decision-makers with varied technical expertise.The benchmark can be visualized at https://servicenow.github.io/context-is-key-forecasting/v0.

Large language model (LLM) agents for web interfaces have advanced rapidly, yet open-source systems still lag behind proprietary agents. Bridging this gap is key to enabling customizable, efficient, and privacy-preserving agents. Two challenges hinder progress: the reproducibility issues in RL and LLM agent training, where results often depend on sensitive factors like seeds and decoding parameters, and the focus of prior work on single-step tasks, overlooking the complexities of web-based, multi-step decision-making. We address these gaps by providing a statistically driven study of training LLM agents for web tasks. Our two-stage pipeline combines imitation learning from a Llama 3.3 70B teacher with on-policy fine-tuning via Group Relative Policy Optimization (GRPO) on a Llama 3.1 8B student. Through 240 configuration sweeps and rigorous bootstrapping, we chart the first compute allocation curve for open-source LLM web agents. Our findings show that dedicating one-third of compute to teacher traces and the rest to RL improves MiniWoB++ success by 6 points and closes 60\% of the gap to GPT-4o on WorkArena, while cutting GPU costs by 45\%. We introduce a principled hyperparameter sensitivity analysis, offering actionable guidelines for robust and cost-effective agent training.

Language model activations entangle concepts that mediate their behavior, making it difficult to interpret these factors, which has implications for generalizability and robustness. We introduce an approach for disentangling these concepts without supervision. Existing methods for concept discovery often rely on external labels, contrastive prompts, or known causal structures, which limits their scalability and biases them toward predefined, easily annotatable features. In contrast, we propose a new unsupervised algorithm that identifies causal differentiating concepts—interpretable latent directions in LM activations that must be changed to elicit a different model behavior. These concepts are discovered using a constrained contrastive learning objective, guided by the insight that eliciting a target behavior requires only sparse changes to the underlying concepts. We formalize this notion and show that, under a particular assumption about the sparsity of these causal differentiating concepts, our method learns disentangled representations that align with human-interpretable factors influencing LM decisions. We empirically show the ability of our method to recover ground-truth causal factors in synthetic and semi-synthetic settings. Additionally, we illustrate the utility of our method through a case study on refusal behavior in language models. Our approach offers a scalable and interpretable lens into the internal workings of LMs, providing a principled foundation for interpreting language model behavior.

Large language model (LLM) agents perform well in sequential decision-making tasks, but improving them on unfamiliar domains often requires costly online interactions or fine-tuning on large expert datasets. These strategies are impractical for closed-source models and expensive for open-source ones, with risks of catastrophic forgetting. Offline trajectories offer reusable knowledge, yet demonstration-based methods struggle because raw traces are long, noisy, and tied to specific tasks. We present Just-in-time Episodic Feedback Hinter (JEF-Hinter), an agentic system that distills offline traces into compact, context-aware hints. A zooming mechanism highlights decisive steps in long trajectories, capturing both strategies and pitfalls. Unlike prior methods, JEF-Hinter leverages both successful and failed trajectories, extracting guidance even when only failure data is available, while supporting parallelized hint generation and benchmark-independent prompting. At inference, a retriever selects relevant hints for the current state, providing targeted guidance with transparency and traceability. Experiments on MiniWoB++, WorkArena-L1, and WebArena-Lite show that JEF-Hinter consistently outperforms strong baselines, including human- and document-based hints.

While finetuning AI agents on interaction data – such as web browsing or tool use – improves their capabilities, it also introduces critical security vulnerabilities within the agentic AI supply chain. We show that adversaries can effectively poison the data collection pipeline at multiple stages to embed hard-to-detect backdoors that, when triggered, cause unsafe or malicious behavior. We formalize three realistic threat models across distinct layers of the supply chain: direct poisoning of finetuning data, pre-backdoored base models, and environment poisoning, a novel attack vector that exploits vulnerabilities specific to agentic training pipelines. Evaluated on two widely adopted agentic benchmarks, all three threat models prove effective: poisoning only a small number of demonstrations is sufficient to embed a backdoor that causes an agent to leak confidential user information with over 80% success.

Data analytics is essential for extracting valuable insights from data that can assist organizations in making effective decisions. We introduce InsightBench, a benchmark dataset with three key features. First, it consists of 100 datasets representing diverse business use cases such as finance and incident management, each accompanied by a carefully curated set of insights planted in the datasets. Second, unlike existing benchmarks focusing on answering single queries, InsightBench evaluates agents based on their ability to perform end-to-end data analytics, including formulating questions, interpreting answers, and generating a summary of insights and actionable steps. Third, we conducted comprehensive quality assurance to ensure that each dataset in the benchmark had clear goals and included relevant and meaningful questions and analysis. Furthermore, we implement a two-way evaluation mechanism using LLaMA-3 as an effective, open-source evaluator to assess agents’ ability to extract insights. We also propose AgentPoirot, our baseline data analysis agent capable of performing end-to-end data analytics. Our evaluation on InsightBench shows that AgentPoirot outperforms existing approaches (such as Pandas Agent) that focus on resolving single queries. We also compare the performance of open- and closed-source LLMs and various evaluation strategies. Overall, this benchmark serves as a testbed to motivate further development in comprehensive automated data analytics and can be accessed here: https://github.com/ServiceNow/insight-bench.

Both PAC-Bayesian and Sample Compress learning frameworks have been shown instrumental for deriving tight (non-vacuous) generalization bounds for neural networks. We leverage these results in a meta-learning scheme, relying on a hypernetwork that outputs the parameters of a downstream predictor from a dataset input. The originality of our approach lies in the investigated hypernetwork architectures that encode the dataset before decoding the parameters: (1) a PAC-Bayesian encoder that expresses a posterior distribution over a latent space, (2) a Sample Compress encoder that selects a small sample of the dataset input along with a message from a discrete set, and (3) a hybrid between both approaches motivated by a new Sample Compress theorem handling continuous messages. The latter theorem exploits the pivotal information transiting at the encoder-decoder junction in order to compute generalization guarantees for each downstream predictor obtained by our meta-learning scheme.

Metabolomics, the study of small molecules within biological systems, offers insights into metabolic processes and, consequently, holds great promise for advancing health outcomes. Biomarker discovery in metabolomics represents a significant challenge, notably due to the high dimensionality of the data. Recent work has addressed this problem by analyzing the most important variables in machine learning models. Unfortunately, this approach relies on prior hypotheses about the structure of the data and may overlook simple patterns. To assess the true usefulness of machine learning methods, we evaluate them on a collection of 835 metabolomics data sets. This effort provides valuable insights for metabolomics researchers regarding where and when to use machine learning. It also establishes a benchmark for the evaluation of future methods. Nonetheless, the results emphasize the high diversity of data sets in metabolomics and the complexity of finding biologically relevant biomarkers. As a result, we propose a novel approach applicable across all data sets, offering guidance for future analyses. This method involves directly comparing univariate and multivariate models. We demonstrate through selected examples how this approach can guide data analysis across diverse data set structures, representative of the observed variability. Code and data are available for research purposes.

Real-world forecasting requires models to integrate not only historical data but also relevant contextual information provided in textual form. While large language models (LLMs) show promise for context-aided forecasting, critical challenges remain: we lack diagnostic tools to understand failure modes, performance remains far below their potential, and high computational costs limit practical deployment. We introduce a unified framework of four strategies that address these limitations along three orthogonal dimensions: model diagnostics, accuracy, and efficiency. Through extensive evaluation across model families from small open-source models to frontier models including Gemini, GPT, and Claude, we uncover both fundamental insights and practical solutions. Our findings span three key dimensions: diagnostic strategies reveal the "Execution Gap" where models correctly explain how context affects forecasts but fail to apply this reasoning; accuracy-focused strategies achieve substantial performance improvements of 25-50

We present DoomArena, a security evaluation framework for AI agents. DoomArena is designed on three principles: 1) It is a plug-in framework and integrates easily into realistic agentic frameworks like BrowserGym (for web agents) and τ-bench (for tool calling agents); 2) It is configurable and allows for detailed threat modeling, allowing configuration of specific components of the agentic framework being attackable, and specifying targets for the attacker; and 3) It is modular and decouples the development of attacks from details of the environment in which the agent is deployed, allowing for the same attacks to be applied across multiple environments. We illustrate several advantages of our framework, including the ability to adapt to new threat models and environments easily, the ability to easily combine several previously published attacks to enable comprehensive and fine-grained security testing, and the ability to analyze trade-offs between various vulnerabilities and performance. We apply DoomArena to state-of-the-art (SOTA) web and tool-calling agents and find a number of surprising results: 1) SOTA agents have varying levels of vulnerability to different threat models (malicious user vs malicious environment), and there is no Pareto dominant agent across all threat models; 2) When multiple attacks are applied to an agent, they often combine constructively; 3) Guardrail model-based defenses seem to fail, while defenses based on powerful SOTA LLMs work better. DoomArena is available at https://github.com/ServiceNow/DoomArena.