Science & Mathematics

Machine learning across materials science, chemistry, energy, and medicine increasingly relies on literature-extracted datasets due to a lack of curated databases. However, automated extraction introduces errors: text recognition misreads digits, units and notations are confused, values are misattributed, and LLMs hallucinate numbers. Drawing on our work building an electro-optic property database, we present a taxonomy of errors organized by their origin and signatures, alongside a layered framework for error detection. The framework combines schema and provenance checks, physical admissibility (bounds, symmetry, and governing equations), cross-source statistical consensus, model auditing, and suspicion-ranked review. In a production run, our verification gate halted 402 of 816 candidate values with typed reasons. Yet, an audit against curated references showed that 30 of 112 accepted values were defective; standard symmetry rules alone caught 21 of these. On measured BaTiO3 and KNbO3 tensors, constitutive identities caught 8 of 10 single-value errors and isolated the corrupted entries. In a controlled benchmark, the combined framework caught 81% of errors at 85% precision, including errors in single-report materials, bringing model accuracy on held-out data to within 3% of a model trained on clean data. Uncleaned data severely impairs discovery: 89% of the twenty largest values were errors, causing AI searches to prioritize false positives. Once bad numbers are controlled, missing measurement conditions emerge as the main limit, as distinct records become indistinguishable without full context. We outline directions for the field, including shared physics rule libraries and self-reporting databases.

Organisms must constantly weigh exploiting the resources they know against exploring for better ones. When foragers compete, the best behavior for each forager also depends on what its competitors do. How does competition change the strategic balance between exploration and exploitation? Here we address this question in a minimal model: two $ε$-greedy temporal-difference learners on a one-dimensional lattice, who start at a small reward at one end and are unaware of a larger reward at the other. For a lone forager, the optimal exploration rate increases monotonically with the value of the distant reward, and with its distance up to a critical distance. When two foragers share the lattice and split rewards, the choice of exploration rate becomes a game whose Nash equilibria have both foragers exploring, both staying, or one exploring while the other stays (anti-coordination). Under local best-response dynamics, pairs of foragers often converge on both exploring or both staying, even when anti-coordination would be socially optimal. This social dilemma arises for a wide range of parameters, and it persists even in a simplified model without explicit spatial structure. A minimal, naturalistic signal, in which one forager informs the other that it has found the distant reward, can remove many of the dilemmas in which both foragers explore, and can produce a Nash equilibrium whose collective payoff exceeds that of every outcome available without signaling.

AI agents are increasingly proposed as autonomous experimenters, yet the benchmarks that test them mostly offer cheap experiments that answer at once. Experiments in physical facilities are different: they take months, occupy scarce equipment and cannot be undone. We present SlowLab, a benchmark in which an agent runs a one-year campaign in four simulated greenhouse compartments on a site whose crop, facility and prices are hidden. The agent decides when to plant which climate policy, whether to stop a crop and which measurements to read while crops grow, and at the end recommends one policy, which a private evaluator scores in weather the agent never saw. In a preregistered study on 48 unseen sites, three low-cost language-model agents ended near a standard grower setting and clearly below a Bayesian-optimisation baseline that starts from that setting. They ran the facility as two synchronous batches, so measurements taken during the season never changed what they planted, and these measurements improved no method's result. Letting other methods re-read the evidence a campaign had collected did not yield significantly better recommendations, which points to where the models start and which experiments they try. Code is released under the MIT license.

Background The combination of hematoma location, expansion and final volume influence neurological outcome. The aim of this study was to derive and validate a quantitative and interpretable region-based NCCT image feature model for predicting hematoma expansion. Methods The Ethnic/Racial Variations of Intracerebral Hemorrhage(ERICH) study was used for derivation and the Virtual International Trials in Stroke Archive(VISTA) was used for validation. NCCT images at presentation and 24+/-6hours were pre-processed, segmented and categorized into lobar, basal ganglia or thalamic regions. Hematoma expansion was defined by region and according to its effect on clinical outcome. Transport-based morphometry (TBM) produced a unique transport-based representation from each NCCT hematoma image. Linear classifiers applied to transport representations were used to derive a predictive model. The regional TBM model's performance was compared to alternate methods using AUROC analyses. Results The derivation dataset included 574 patients, comprising 162 lobar, 257 basal ganglia and 155 thalamic hematomas. The validation dataset included 196 patients, comprising 31 lobar, 119 basal ganglia and 46 thalamic hematomas. A combined regional model predicted hematoma expansion in the validation dataset with an AUROC of 0.787. The principal image features which varied by location were size, heterogeneity, eccentricity and density distribution towards the hematoma periphery. The regional TBM model outperformed alternative clinician based and machine-learning methods. Conclusions TBM discriminated and visualized regional features of hematoma expansion from presentation NCCT scans. This provides preliminary evidence for regional radiographic features of hematoma expansion. It has the potential to improve hematoma expansion prediction and understanding of hematoma expansion pathophysiology.

Individuals are increasingly using AI for psychological support. One specific paradigm, AI-mediated cognitive reframing (AIM-CR), uses AI to automatically reframe users' negative thoughts ("I failed...") into more adaptive perspectives ("I am learning..."). While prior work suggests that AIM-CR tools reduce users' negative emotions, the complexities of AI automatically modifying users' personal narratives remain underexplored. In this work, we investigated these complexities through a mixed-methods study in which 28 participants engaged with an AIM-CR tool that reframed narratives about their stressors. Our findings suggest that participants had mixed perceptions of AIM-CR: although reframing reduced negative emotions for most participants, participants felt less ownership of, and less authenticity in, the reframed narratives. Participants perceived AIM-CR as a validating "mirror," as "another self" that could motivate or alienate them, or as an external social actor. These perceptions shaped therapeutic dynamics. We conclude by discussing design implications for future AIM-CR tools to better preserve user agency in narrative co-construction and more effectively support mental health and well-being.

Recent advances in vision-language-action (VLA) and world-action models (WAMs) have significantly improved robotic manipulation, yet deploying robots in the open world demands a higher level of autonomy beyond executing predefined tasks. Robot agents offer a promising paradigm for this transition, integrating task discovery, contextual reasoning, physical execution, and adaptive recovery into a closed interaction loop. However, existing benchmarks largely evaluate isolated capabilities, failing to capture the complexity of open-world robot autonomy. We introduce RobotAgentBench (RAB), a comprehensive benchmark for evaluating robot agents in realistic, open-world household environments. Through an agent-assisted, human-in-the-loop real-to-sim pipeline, RAB constructs 50 diverse household layouts with interactive objects and physically grounded tasks, encompassing 90 atomic tasks, 18 short-horizon tasks, 8 long-horizon tasks, and 4 open-ended scenarios. RAB provides a multi-level evaluation of robot agent capabilities: (1) task-level assessments systematically examine five complementary dimensions: task discovery, context reasoning, manipulation, failure recovery, and robustness; (2) scenario-level evaluation assesses how agents integrate these capabilities to autonomously fulfill high-level user needs. Furthermore, RAB enables systematic comparisons of standalone VLA/WAM models and diverse robot agent architectures under a unified planning-execution-verification framework. Extensive experiments reveal substantial gaps between manipulation and autonomy, demonstrate the advantages of agentic architectures and recursive self-improvement, and highlight the remaining challenges toward open-world robot autonomy.

Assistive agents in shared-control settings face a dual challenge: acting proactively to align with the human's intentions while remaining legible enough for the human to comprehend and fluently respond in real time. We present Dream2Assist, a model-based reinforcement learning framework for tightly-coupled shared decision making that addresses both sides of this challenge. Our approach extends a recurrent state-space world model with intent inference, enabling an assistive policy trained via fictitious co-play to anticipate and support discrete human objectives without overriding human agency. Beyond the computational framework, we describe the full deployment pipeline needed to translate a world-model-based policy into a safe, human-centered system in a resource-efficient way. Crucially, we address the sim-to-real-human gap via policy down-selection and reward restructuring within an iterative human-machine interface design. We validate the framework through three human-subjects studies and a preliminary on-vehicle deployment spanning two qualitatively distinct domains: high-speed racing (N=30) and urban driving with richer intent structure (N=10). Our results demonstrate that intent conditioning yields measurable improvements in torque alignment and collision rate. We surface key design insights and practices for deploying learning-based assistive agents in safety-critical, real-time human-robot teaming.

In this paper, we introduce a new framework for characterizing the user skills required for chart authoring. Despite growing attention to authoring systems, we lack a conceptual framework that characterizes the diverse and multifaceted skills involved and helps identify opportunities for system design and development. Our initial investigation revealed that skill is a complex and elusive concept, and that existing theories on skills from other disciplines are too high-level to capture the importance of tasks and tools in data visualizations. To address this gap, we formulate the CAPED framework that characterizes skill as the ability to create a chart involving five dimensions pertinent to tasks and tools: input data, output chart, paradigm, abstraction, and expression. We demonstrate the framework's descriptive power by highlighting different skills involved in similar authoring situations and identifying the types of knowledge associated with chart authoring. We further present examples illustrating how the framework can be used to identify new research opportunities in supporting users with varying skills.

Latency-sensitive spoken agents must know not only which tool to call, but also when they have heard enough to act. Waiting for the turn to complete delays execution even when the request is already actionable. However, neither existing spoken agents nor spoken dialogue corpora define the earliest point at which a request becomes actionable. We introduce a synthetic spoken-dialogue pipeline that provides earliest-actionable-point supervision, marking when the observed speech grounds a tool and its required arguments. Through controlled task generation, speech synthesis and alignment, and gated annotation, we construct 26,694 dialogues totaling 786 hours across 48 domains, with disjoint training and test argument values. We additionally create an audio rendering of $τ^2$-bench for external evaluation. We train an omni-modal language model on this corpus, enabling causal, chunk-level decisions and partial-transcript generation for downstream call completion. The model achieves tool-state macro-F1 scores of 0.48 and 0.47 on held-out dialogues and the external benchmark, respectively. For correct calls, the estimated mean lead over a turn-end cascade, using the same formatter, is 1.8-2.0 seconds in-domain and 1.1 seconds on $τ^2$-bench. These results demonstrate a data-driven path toward spoken agents that act while listening. We will open-source the pipeline and the training scripts.

Language model agents often abandon correct work when a user challenges it, yet simply telling them to stand firm makes them ignore real mistakes. Once an agent reads a complaint, it tends to discount its own earlier checks in order to agree with the user. We introduce Thinking-in-Bets, a training-free method in which an agent writes a short private record of its main claims, the checks supporting them, and its confidence before reading user feedback. When challenged, the agent consults this Claim Checklist to keep verified work intact while investigating uncertain or newly challenged parts. We evaluate five Gemini models (3.5 Flash-Lite, 3.5 Flash, 3.6 Flash, 3.8 Flash, and 4.0 Argon) across eight benchmarks: SWE-Together, SWE-Interact, and DeepSWE for software engineering, Agents' Last Exam for professional reports, Humanity's Last Exam and SycEval for academic reasoning, Vals Finance for financial analysis, and Terminal-Bench for command-line tasks. Recording claims before criticism nearly eliminates false reversals in patch review and protects passing report drafts under mistaken pushback, whereas writing the same record after reading the complaint recovers very little of the gain. In multi-turn coding, pre-reply claim records substantially reduce unnecessary file edits after mistaken complaints, and gating the record so it is written only when the agent is uncertain lowers token overhead while fixing more real bugs than the baseline. Even in non-interactive tasks without user feedback, listing the key claims in a draft and re-checking the weakest one before submission improves both answer accuracy and confidence estimates across all tested models.

We study unweighted nonpreemptive throughput maximization: given jobs with processing times, release times, and deadlines, schedule a maximum-cardinality subset on identical machines. For every fixed $\varepsilon>0$, we give randomized algorithms with expected approximation ratios $17/13+\varepsilon$ in polynomial time and $21/17+\varepsilon$ in pseudopolynomial time. These improve the respective $4/3+\varepsilon$ and $5/4+\varepsilon$ guarantees of Armbruster, Grandoni, Tinguely, and Wiese [STOC'26]. Both results hold for an arbitrary number of identical machines. Our algorithms build on their configuration-LP and matching framework, which partitions time into blocks. For a job whose window meets multiple blocks, its boundary blocks are the first and last such blocks. Crossing boundary pairs, whose endpoints strictly interleave, permit additional assignments to sampled execution slots, while a noncrossing family can be coordinated using consistent joint distributions on at most three blocks. The exchange analysis accounts for fractional job assignments that must be erased before inserting an additional job. For the pseudopolynomial implementation, we project configurations onto selected job identities and use separate configuration distributions with common placement marginals. This retains efficient pricing while enforcing the correlations needed for coordination.

Dataflow streaming systems, like Apache Flink and Spark Streaming, are integral to modern business analytics, providing real-time insights across industries. However, for emerging hybrid edge-cloud analytics pipelines, neither processing everything in the cloud nor static edge offloading can reliably sustain the target rate under dynamic WAN conditions and limited edge resources. In this paper, we explore how these datacenter-centric platforms can be extended to support such hybrid analytics pipelines. Our goal is to maintain full transparency for user applications, while retaining built-in fault tolerance, out-of-order processing, and existing ecosystem integrations. Achieving this is challenging because existing dataflow engines assume homogeneous resources, rely on static task placement, and do not support adaptation under dynamic network and edge conditions. We introduce Sluice, an adaptive data stream processing system for hybrid clouds, compatible with dataflow streaming engines. Sluice's key contributions are: (i) an automatic query rewriter that decomposes applications into independent, fault-tolerant segments, and (ii) a live routing mechanism that shifts computations between edge and cloud without pausing execution while preserving event-time semantics. We implement Sluice on Apache Flink and evaluate it on a physical testbed with Raspberry Pi devices, as well as on a large simulated testbed of 100 VMs. Across five real-world applications, our results show that Sluice seamlessly shifts computations between edge and cloud, while consistently achieving higher throughput than baseline systems.

Effective tutoring requires determining not only what information to provide, but also which form of assistance to deliver. A tutor may address the same student error using various pedagogical strategies, adapting its approach as the interaction progresses. We introduce Comparative Pedagogical Supervision (CPS), a training framework to learn to select the optimal strategy and feedback for student learning. We evaluate CPS on math and science reasoning datasets. After five tutoring turns, CPS outperforms the strongest fixed-strategy baselines. The learned tutor transfers across datasets, and its strategy selection can also inform a separate API-based tutor.

Vision-language models are shifting from offline passive understanding toward online proactive interaction. However, prevailing methods largely rely on explicit requests while miss the implicit user intent (e.g., "where should I click next?" while a user navigate a website), meanwhile fail to update the state simultaneously as user requests might update continuously. These limitations make them less suited to intent-aware interaction in practical. To address these challenges, we introduce StreamVibe-Bench, a new benchmark serving as testbed for user intent interaction, with 4.1K evaluation samples and 85K training samples spanning explicit, implicit, and dynamic intents. Building on this benchmark, we develop StreamVibe-VL, a streaming proactive model that infers implicit user intents from continuous observations and dynamically tailors its interactions as these intents evolve. We further introduce StreamVibe-Harness, which maintains user intents as persistent states with a fleixble lifecycles via a hierarchical memory to track the latest user intent and environmental state. Our experiments reveal three key findings: (i) StreamVibe-VL preserves strong general video understanding while improving response timing and answer quality by 10.7% over other baselines; (ii) existing proactive models remain limited in understanding user intent and deciding when to respond, especially under implicit and dynamic intents; and (iii) StreamVibe-Harness further improves response consistency and adaptation over sustained interaction, resulting in a 12.3% gain in proactive interaction.

Video world models trained on large-scale robot data promise a safe and scalable approach for learning and evaluating policies that act in the physical world. However, they still struggle with long-horizon rollouts and out-of-distribution generalization, and they remain computationally demanding at inference time. Typically, video world models make predictions in the latent space of a reconstruction-trained autoencoder, which however is not directly optimized for dynamics modeling. On the other hand, world models designed for latent planning usually optimize latents to be predictable, but they forgo accurate prediction of observations in pixel space. In this paper, we show that it is possible to achieve the best of both worlds: a latent geometry optimized to make future prediction as simple as possible without sacrificing accurate prediction of future observations. More precisely, we find that temporal objectives for representation learning, paired with a past-conditioned decoder architecture, lead to consistent improvements in generative video world models at the same training budget. The gains include up to 5x cheaper inference, over 7x faster training, and 15-24% lower pixel and perceptual errors out of distribution and over long horizons. Our world models also agree more closely with real-world policy evaluation when using a vision-language model to judge task success from their pixel-space predictions. Overall, our study indicates that temporal predictability is an important design criterion for the latent space of video world models, and provides concrete guidance on how to incorporate it into the training of autoencoders.