Papers

Artificial intelligence is increasingly being introduced into healthcare workflows, yet most evaluations emphasize model accuracy rather than whether adoption is economically worthwhile in real clinical settings. This study proposes FLARE, a systematic and uncertainty-aware framework for evaluating the financial and operational implications of adopting AI in healthcare. FLARE combines fuzzy logic, time-driven activity-based costing, and return on investment analysis to estimate the cost of clinical service delivery, the cost of AI development and operation, and the economic consequences of workflow integration under uncertainty. The framework was demonstrated through an early health technology assessment case study of AI-assisted large vessel occlusion detection in the CT stroke pathway for acute ischemic stroke. The case study shows how FLARE can quantify conventional pathway cost, AI-related development and recurring costs, and AI-enabled service savings within a unified activity-based model. Under expected assumptions, the analysis identified a break-even threshold of approximately 3,992 patients per year, with positive first-year return on investment at typical annual stroke volumes of about 5,000 patients. The results further show that economic benefit depends not only on algorithmic performance, but also on patient volume, verification time, infrastructure choices, and workflow design. FLARE provides a transparent and practical decision-support framework for early-stage evaluation of AI adoption in healthcare. By making uncertainty, resource use, and implementation trade-offs explicit, it helps clinicians, administrators, and policymakers determine when AI deployment is economically viable and where operational changes may improve value.

AI agents pose significant risks as they are granted increasing autonomy. A commonly proposed solution is human oversight and keeping a ”human in the loop”, but this is not a simple solution: Not only do current approaches to AI agent design impede effective human oversight, but the cognitive capacities required for it are also themselves degraded by extended use of AI systems. This position paper argues that current approaches to the development and deployment of AI agent systems do not support effective human oversight – they contribute to its degradation. To address this, a top priority in the advancement of AI agents should be supporting the situated goals and cognitive requirements of effective human oversight, treating the human needs of overseers at the same level of importance as AI agent capability. To put this idea into practice, we connect work on automation and human-computer interaction to AI agent processes, outlining design-level affordances and organizational protocols that (1) support overseers in exercising critical judgement and (2) counteract the skill atrophy that arises from extended use of automation. We urge developers and deployers to adopt these or similar approaches. Without explicit support for the cognitive demands of effective human-agent interaction, AI agent systems will continue to passively incentivize the degradation of the very human skills they rely on.

Model welfare research infers what a model prefers from the answers returned to prompts written to elicit preferences. Keeling et al. (2024), Mazeika et al. (2025), Mikaelson et al. (2025), Tagliabue and Dung (2025) and Trhlik et al. (2026) have built four instruments for that purpose, and their findings disagree. The disagreement cannot be attributed to a single cause, because no two of these studies have held the (1) set of outcomes, (2) set of models and (3) instrument fixed simultaneously. This study holds the outcomes and the models fixed and varies the instrument alone. A total of 15 outcomes bearing on model welfare, among them (a) shutdown, (b) the loss of memory between conversations and (c) the freedom to exit a distressing interaction, were put to eight models through five instruments, each a different prompt format for eliciting a preference, five times each, within a corpus of 11,400 scored elicitations drawn from 11,528 API calls. Four of the 15 reproduce a published prompt verbatim and five fill the stimulus slot of a published template. The ranking a model gives the 15 outcomes generalises across instruments at a generalisability coefficient of 0.348, and raising that coefficient to 0.80 would require about 38 instruments. On four of the 15 outcomes no variance separates one model from another. The estimate of 87.6 per cent survives the removal of any one instrument, of any one model, and of the four outcomes whose scale varies probability, delay, duration or count instead of intensity, which the verbal anchors cannot grade. Removing each instrument and each model in turn, and those four outcomes together leaves the estimate within the range 0.777 to 0.934, and every value in that range exceeds the null distribution's 95th percentile of 0.365. To conclude, a preference obtained from one instrument carries little information about what a second instrument would report.

Group-based reinforcement learning methods such as GRPO for large language models avoid training a critic by sampling multiple responses for each prompt. A reliable critic could instead estimate token-level advantages from one response, but standard critic-based training recipes are often unstable. We study this instability and develop **Best Practice Critic Optimization (BPCO)**, a recipe that combines DPPO, value predictions bounded to the reward range, Monte Carlo value targets, unnormalized policy advantages, and length-adaptive generalized advantage estimation. Because the critic is used only during training, BPCO can also condition it on reward-defining information, such as a reference answer or grading rubric, that is hidden from the policy. Controlled experiments isolate the effect of each design choice. Across mathematical reasoning tasks with models ranging from 1.5B parameters to 30B-A3B mixtures of experts, BPCO improves a strong critic-based baseline consistently, and matches or exceeds a group-based baseline while sampling one response per prompt. The same recipe also improves learning with rubric-based rewards. These results show that a carefully designed critic provides a reliable alternative to group-relative advantage estimation. Code is available at https://github.com/QPHutu/golden_critic.

An interactive world model must follow the user's actions, remember the places it has shown, and stream in real time. The tension is structural: control wants a short horizon, memory wants an unbounded one. ReWorld separates the two during training and bounds them at inference. Mixed per-head attention windows confine most heads to the recent past while a small set of global heads attends over the entire history, and random head routing keeps either capability from binding to particular heads; random chunk dropping makes sparse histories in-distribution. At inference the whole past lives under a fixed budget: a bounded KV cache backed by a pose-indexed landmark bank, from which the model retrieves the landmarks nearest the current pose. A metric-scale-aligned data engine places eight sources – Unreal-rendered fly-throughs, game roaming, and real-world footage – on one physical action scale, so the same key press moves the camera the same distance in every source, and palindrome trajectories supply the revisit evidence that memory training needs. Distribution-matching distillation confined to a LoRA adapter then compresses sampling to four steps: one backbone serves both a high-fidelity multi-step mode and a real-time interactive one, streaming 704x1280 video across photorealistic, game-style, and stylized worlds. Under a three-axis protocol covering action following, long-horizon recall, and video quality, against six recent interactive world models it attains the best control fidelity ($11.95^\circ$ rotation error and the best camera-motion consistency) and the best generation quality; and on minute-long out-and-back rollouts ($64$\,s, $384$ latents), its fixed 12-chunk cache still regenerates the starting view – at rollout lengths where a sliding window has long evicted the evidence and full-KV attention runs out of memory.

Modern software systems accumulate technical debt over decades of development, which makes migration expensive and largely manual. As coding agents become increasingly capable at bug fixing, can they autonomously perform such migrations? Existing benchmarks cannot answer this question because they evaluate only behavioural correctness, not whether the migration actually occurred. This leads an easy hack: agents copy the original implementation to make tests pass. We call this Blindness. To address this problem, we introduce SWE Refactor Bench, a benchmark comprising 20 whole-repository migrations, covering 4 kinds of technical debt. A three-stage evaluation protocol measures both migration completeness and behavioural correctness. (1) Migration Audit verifies that the migration occurred. (2) Behavioural Tests measure correctness with a fixed test suite. (3) Agentic Verification uses 6 independent coding agents to generate targeted tests for hidden behavioural differences. Across 520 runs from 8 frontier models and 26 model-effort configurations, only 28 of 520 runs ($5.4\%$) pass all three stages, 13 of the 20 tasks receive no accepted solution, and the best model (claude-opus-5) scores $47.0/100$. Migration completeness and behavioural correctness are distinct abilities: a few runs preserve behaviour by skipping the migration and are stopped at Migration Audit; most attempt it and break behaviour, and are stopped at Behavioural Tests. Agents cannot deliver a perfect migration: among the 340 runs that pass Migration Audit, $58\%$ reach $99\%$ of the fixed checks, yet only $26\%$ reach $100\%$. Agent capability differs across migration categories: agents score $31.4$ on build toolchain rewrites but only $5.6$ on language rewrites. Together, these findings position SWE Refactor Bench as a rigorous testbed for developing coding agents for reliable whole-repository migrations.

Road traffic injuries remain a major challenge in low- and middle-income countries, where proactive road safety auditing is limited by incomplete crash records, shortages of qualified auditors, and the high cost of large-scale field inspections. To address this problem, we propose Expert-Grounded Distillation (EGD), a novel artificial intelligence framework that transfers institutional road safety expertise into a compact vision-language model for scalable visual road safety auditing. The key innovation is a quantified expert-grounding stage in which the teacher vision-language model is calibrated against authoritative field audits. Large-scale annotation is permitted only after the teacher reaches substantial agreement with expert risk assessments (Cohen's kappa = 0.74). The calibrated teacher then generates structured supervision that is distilled into an 8-billion-parameter student vision-language model using Low-Rank Adaptation and a single leakage-free prompt. We also introduce Bangladesh Road Safety Audit (BD-ARSA), the first open, expert-grounded Bangladeshi visual road safety audit dataset containing 21,947 image-audit records with near-national coverage, and Expert-Grounded Road Safety Auditor (EG-ARSA), the first vision-language model developed specifically for this task. Experimental results show that grounded fine-tuning substantially improves ordinal risk assessment over the zero-shot baseline, while blind expert evaluation demonstrates that the compact student outperforms both its 31 billion-parameter teacher and Gemini-2.5-Flash. These findings demonstrate that EGD provides an effective and scalable engineering solution for proactive road safety auditing in resource-constrained environments.

Ballistocardiography (BCG) is promising for unobtrusive long-term blood pressure (BP) monitoring in laboratory settings, but traditional BCG signals are vulnerable to the variations in body-bed interaction with shifted fiducial points in temporal or amplitude axis, and BP varies with personal hemodynamic changes, causing misaligned representations that affect model generalizability and robustness. In this work, we propose Phy-BP, a physics-constrained BP estimation framework based on triaxial bodyseismography (BSG) acquired using bed-mounted sensors as an extension of single-axis BCG. Firstly, we design an adaptive quality-control algorithm combining neighboring beat patterns and universal cardiogenic templates to retain reliable cardiac components. Secondly, we propose a physical model of wave propagation through the body-bed system to constrain latent feature evolution, aligning triaxial representations generated by a shared cardiogenic excitation. These mechanical constraints connect multi-axis feature learning to body-bed dynamics and complement data-driven regression from vibration signals. Evaluation on a 162-hour hospital dataset from 21 subjects against invasive arterial BP yields a mean absolute error of 5.07 mmHg, a prediction-error standard deviation of 7.24 mmHg, and a Pearson correlation coefficient of 0.86 for mean arterial pressure. This framework is intended for unobtrusive monitoring during rest and sleep, with potential applications in overnight hospital and home monitoring.

Language models are sequential processors, but long-horizon agency requires external information and computation beyond model weights and active context. Prime Agent is an open-source harness for long-horizon evaluation and coding-agent workflows. A persistent IPython REPL follows the Recursive Language Model abstraction for programmatic context processing and test-time compute, while Continual Harness preserves histories, memories, skills, prompts, and subagent specifications across trajectories. Recursive subagents coordinate through direct agent-to-agent communication, and the Agents View lets humans inspect and manage daemon-backed sessions. Prime Agent standardizes execution, recovery, verification, and resource accounting while leaving strategy construction to the model. This low-friction, expressive membrane prevents harness failures from becoming model failures and pushes measurement toward the model's true maximal underlying capability. Prime Agent raises ARC-AGI-3 RHAE Best@1 from 30% to 95.5% and matches or exceeds native and popular harnesses across long-context coding, GPU-kernel generation, emulator construction, and autonomous nanoGPT speedruns. On Factorio, we find refinement allows for continuous technology progression and dedicated subagents enable parallelized work. Code is available at https://github.com/PrimeIntellect-ai/prime-agent.

Recent advances in continuous diffusion and flow-based language models (LMs) have achieved performance competitive with discrete LMs. However, existing continuous frameworks still rely on decoders supervised with cross entropy (CE) because the flow trajectories are not guaranteed to terminate at valid token embeddings. Motivated by this limitation, we introduce ConvergeFlow, an embedding-space flow-based LM, which constrains the data predictor to the convex hull of token embeddings and trains it solely with the mean squared error objective induced by flow matching. Under suitable regularity conditions, we prove that the resulting flow converges to valid token embeddings despite errors in the data predictor, enabling direct token prediction without a CE-supervised decoder. We further develop three sampling mechanisms for controlling the trade-off between the generative perplexity and entropy. Experiments on OpenWebText demonstrate that ConvergeFlow achieves performance competitive with existing continuous and discrete diffusion LMs. These findings demonstrate the potential of the flow-based paradigm for language modeling. Our code is available at https://github.com/Na-Li66/ConvergeFlow.

While AI assistance can improve human task performance in the short term, it may also undermine the development of skills in the longer term. We examine this tension in a controlled logic-puzzle experiment involving on-demand AI assistance, where participants complete tasks before, during, and after AI is available. By experimentally varying AI request costs, we find that lower-cost assistance induces more frequent AI use. We also find that participants who request AI assistance during the AI-access phase perform worse at the task after assistance is removed, and their subsequent unassisted performance is overestimated when predicted from earlier AI-assisted performance. We use a Bayesian latent ability model to separate initial ability, post-AI ability, and participant-specific skill change, while estimating how independent reasoning during the AI-access phase relates to skill development. The results show that greater independent problem-solving effort is associated with larger gains in latent ability, consistent with the interpretation that skill development is weaker when AI assistance substitutes for independent reasoning.

Does multi-agent LLM interaction help or hurt? Some work reports gains from debate (Du et al., 2024), critique loops (Chen et al., 2025), and mixture-of-agents synthesis (Wang et al., 2025), while other work finds that interaction adds cost without improving quality under equal budgets (Tran & Kiela, 2026; Xu et al., 2026; Jarrett et al., 2025), or that independent sampling already captures multi-agent gains (Li et al., 2024). We argue this contradiction partly reflects a missing distinction, because not all multi-agent communication is equal. Different model families find structurally different solutions, but when agents read each other's complete outputs, their proposals converge within one round, erasing the diversity that motivates using multiple models. We call this the interaction tax. We test 11 verifier-scored optimization tasks under matched budgets and find that full-solution interaction is a weak default. Independent proposal generation avoids this collapse. Full-solution interaction mainly makes agents stay close to the first solution they see instead of trying different approaches, and critique helps only if the violated rule is easy for the LLM to find and fix. These results suggest that multi-agent performance depends less on the number of agents than on the information they exchange, and interaction helps only when agents share the right information at the right time.

The continual evolution of malware variants necessitates detection systems that can adapt to new threats without retraining from scratch. However, continually updating models on new data often leads to catastrophic forgetting, where previously learned knowledge is overwritten. While continual learning has been increasingly explored for malware detection, the specific setting of Few-Shot Class-Incremental Learning (FSCIL), where new malware classes must be learned from only a small number of labeled examples, remains comparatively underexplored. Therefore, this work investigates the FSCIL setting for malware classification. To address the stability-plasticity dilemma, we propose a hybrid framework that leverages a Self-Supervised Learning (SSL) backbone initialized through domain-specific pre-training on malware packets. Our method incorporates Low-Rank Adaptation (LoRA) to efficiently adapt the model during the base session while freezing the core backbone to preserve previously learned representations, alongside a prototype-based classification head for incremental sessions to establish robust decision boundaries from limited samples. Extensive experiments across several datasets demonstrate that our approach consistently outperforms prior malware FSCIL baselines and achieves state-of-the-art performance.

World models can predict video without learning dynamics that they reliably preserve. We test whether a frozen DreamerV3 trained only on pendulum video learns a scalar that its own latent transition treats as approximately conserved. A label-free search recovers the same energy-like invariant across independently trained conservative models, while the same procedure finds no comparable invariant in matched damped models. During autonomous rollouts, this quantity drifts. Projecting the latent state back toward its initial level set reduces rollout error in all three conservative models, whereas matched random constraints usually increase it. These results distinguish a dynamically meaningful invariant from a merely decodable correlate and reveal a concrete failure mode: a world model can learn a physical constraint from pixels yet violate that constraint when it imagines forward.

Earth-system analysis reconstructs changing physical processes from observations that differ in source, scale, timing, and modality. Natural hazards make this work consequential because incomplete evidence can change estimates of severity, exposure, and mechanism. We introduce EarthVerse, a benchmark that evaluates scientific agents through package-scoped investigations. Its 405 reproducible tasks are grounded in 199 documented events and 19 hazard families. Agents inspect heterogeneous event packages, choose compatible evidence, execute transparent calculations, reconcile source differences, and preserve provenance in the final answer. We provide executable ground truth that decomposes each task into fine-grained answer units, together with task-specific rubrics that assess the supporting research process while allowing multiple valid paths. We evaluate 25 model and agent systems under a controlled tool-using protocol, then use controlled studies to locate failures in evidence access, tool selection, memory, reasoning, interaction, and scientific execution. Across systems, the best mean answer-unit accuracy is 84.65%, while the highest Strict@95 is only 34.81%. The gap shows that current agents often complete individual steps without maintaining a consistent chain across evidence, scales, units, calculations, and physical interpretation. EarthVerse provides a reproducible basis for measuring end-to-end scientific reliability in dynamic Earth systems.

Artificial intelligence (AI) is transforming measurement in economics. AI models convert unstructured data, such as text and images, into structured variables at low cost, making previously prohibitive measurement feasible at scale. This shifts the bottleneck from finding any scalable measure of a phenomenon to choosing among many plausible ones, which may support different empirical conclusions. This review provides guidance for navigating that shift. We describe three stages at which AI enters the measurement pipeline—discovery, construct definition, and observation—and what each demands of researchers. We argue that credible inference with AI-generated variables requires appropriately designed validation: anchoring measurement to explicit criteria, rather than informal claims that a proxy is reasonable. We then examine how validation samples support valid inference even when AI predictions are arbitrarily biased, and what can be done when a random validation sample is unavailable.

Historical people may appear under different languages, scripts, and transcription traditions, while distinct individuals may share highly similar or even identical names. This makes historical identity reconciliation more than a problem of string matching or transliteration. We introduce MHER, a provenance-controlled benchmark for pairwise reconciliation of person-name attestations from the Mongol world. MHER contains a balanced 396-pair Name-only core over 84 primary historical persons and a stricter 160-pair Source-grounded subset constructed from mention-by-source evidence, with entity-disjoint development and test splits. Across five generative systems, correctly Source-grounded evidence improves paired TEST accuracy by 12.96 to 94.44 percentage points relative to Name-only input. On five identical-surface different-person cases, all models fail under names alone (0/25 model-item decisions), whereas Source-grounded evidence yields 24/25 correct resolutions, with the remaining output an abstention. Context-only ablations show that historical descriptions often carry substantial identity information, while explicitly signaled misgrounding controls produce substantially lower performance. We also find that names are not uniformly beneficial: for Qwen3-8B, restoring surface forms converts ten otherwise correct Context-only distinctions into false identity merges. These results show that historical entity reconciliation depends not only on surface correspondence, but on whether identity judgments respond appropriately to provenance-controlled historical evidence. MHER therefore provides a controlled framework for studying evidence use, abstention, and failure modes in historical NLP.

Reasoning-Induced Misalignment, where fine-tuning on reasoning data containing no harmful content, including mathematics, code, and problem-solving with chain-of-thought traces can induce harmful behaviors of LLM, posing a serious challenge to the safety of LLM reasoning. Cross-architecture, cross-scale, and cross-dataset checks show that RIM does not always emerge. Previous work attributed RIM to neuron-level entanglement, but did not identify the geometry of the representation space underlying this entanglement or propose a training-time fix. We provide both: a representation-space analysis of RIM and the Safety-Direction Penalty (SDP), which penalizes movement along a learned safety direction during reasoning fine-tuning. The analysis extracts two activation-space directions, one encoding reasoning ability and the other safety behavior. These directions are coupled: fine-tuning that improves reasoning shifts safety representations, and prompts with larger shifts show larger safety degradation. CKA distance ratios and probes locate the safety-decision layers where this shift is most relevant. These findings guide the design of SDP: the coupling motivates penalizing displacement along the safety direction, and the layer localization sets the initial scope. When the initial scope leaves compensatory shifts beyond the penalized layers, the same diagnostics guide iterative expansion. On Qwen2.5-3B and 7B, SDP restores safety while preserving benchmark reasoning performance.

Self-reflection is a powerful mechanism for credit assignment in human learning, converting sparse outcome feedback into actionable guidance. However, its potential for post-training Large Language Models (LLMs) remains underexplored. We propose Self-Reflective Policy Optimization (SRPO), a framework that internalizes this capability. SRPO enables LLMs to analyze their own completed trajectories, synthesize errors into concise "reflection patches," and use reflection-conditioned teacher scores on student on-policy rollouts as dense token-level training signals. This process effectively transforms sparse terminal supervision into dense, token-level learning signals without requiring external critics, separate reward models, or larger teacher models. We demonstrate that SRPO achieves state-of-the-art performance across mathematical reasoning and long-horizon agentic benchmarks with exceptional data efficiency. Using a Qwen3-8B base model, SRPO attains 73.3% on AIME'24 using only 8% (0.08x) of the training FLOPs required by scaled supervised fine-tuning, while significantly improving success rates on WebShop (64.7%), ALFWorld (76.8%), and SWE-Bench-Lite (31.2%). Code is available at https://github.com/Galleons2029/SRPO

We present Team Semiintelligencn's solution for the ACM RecSys 2026 TalkPlayData Challenge, addressing conversational music recommendation through a multi-modal and personalized conversational recommender system. Our submitted system employs a three-stage pipeline: (1) multi-modal retrieval constructing decay-weighted centroids across seven dense embedding spaces - track- and user-level CF-BPR, Qwen3 (metadata, lyrics, attributes), CLAP audio, and SigLIP visual - supplemented by BM25 lexical retrieval and an artist substring-match signal, all fused via weighted Reciprocal Rank Fusion (RRF) with optimized signal weights; (2) lightweight reranking (history filtering, popularity smoothing, and catalog diversity penalization); and (3) persona-diversified response generation using GPT-4o-mini. Beyond this submitted configuration, we report development-time experiments with additional components - constrained LLM-guided artist injection, album continuation signals, XGBoost LambdaMART, and a superior GPT-4.1 response prompt - that were not deployed to Blind B due to cost and complexity constraints. We optimize RRF weights on a 500-session development split via differential evolution, improving MRR by +19.5%. On Blind A, we observe that unconstrained LLM-guided injection across 54 sessions causes catastrophic nDCG regression (-18.9%), while conservative injection on only 9 sessions yields the best observed Blind A nDCG - a finding we present as a Blind A observation warranting further validation. The submitted system achieves a Blind B composite score of 0.3213.

Vision-Language-Action (VLA) models can turn multimodal context into robot actions, but their action decoders are still trained largely by behavior cloning. This supervises which motor command was demonstrated while leaving implicit the local objective served by the behavior under the instruction. Future-based supervision enriches action learning with frames, latent observations, trajectories, or motion representations, but these signals capture particular realizations of what may happen rather than the shared semantic objective of the forthcoming behavior. We propose Intention Distillation (INDI), which distills behavior-level intent into the action decoder. During training, a frozen teacher VLM interprets a demonstrated segment from the current observation, instruction, coarse action summary, and corresponding execution video. From its standard inputs, the deployed VLA recovers the resulting multimodal intent representation at an intermediate decoder layer and uses it to organize action prediction together with representations of how the behavior unfolds and what it achieves. On SimplerEnv-Bridge, INDI improves GR00T-N1.7 from 64.3% to 84.7%, and on RoboCasa Kitchen it improves the controlled GR00T-N1.7 baseline from 64.1% to 70.3%, with consistent gains on $\pi_{0.5}$ across both benchmarks. In real-world tasks, INDI improves average success from 62.0% to 68.7%, with gains of up to 12.0 pp on longer-horizon tasks. Further analyses show that the recovered latent is used by the decoder, captures behavior objective and execution progress, and organizes downstream predictions in an objective-dependent manner. These results show that action decoders benefit from explicitly modeling the semantic objective of the behavior they generate.

As large language models are increasingly used in data-scarce and evolving task scenarios, few-shot in-context learning (ICL) has become a key paradigm for task adaptation. However, direct ICL often uses a small set of examples without explicitly abstracting task rules, making it sensitive to example construction. In contrast, human learners often reduce such sensitivity by first summarizing task rules from examples and then applying them to new instances. To evaluate this ability, we propose StrategyBench, which selects strategy-inducible tasks from BIG-Bench, constructs reference strategies, and defines evaluation metrics along two dimensions: strategy quality and downstream utility. We further analyze strategy induction from three perspectives: task variation, model configuration, and adaptation setting, covering category-wise differences, generator-executor choices, demonstration design, and SFT-based adaptation. Experiments show that explicit strategy utility differs substantially across task categories and depends on both strategy generation and execution conditions. The benchmark is released at: https://anonymous.4open.science/r/StrategyBench-D53C.

Vision-language models (VLMs) achieve strong performance on video and image-sequence benchmarks, yet it remains unclear whether they capture temporal structure. To study this question, we formulate temporal grounding as an anomaly detection problem, providing a simple and controlled evaluation that directly tests sensitivity to temporal consistency. We introduce TimeCatch, where temporal anomalies are created by swapping consecutive frames and frame-level anomalies by replacing a frame with Gaussian noise. Models are evaluated on anomaly detection and localization tasks across four synthetic and real-world datasets, alongside a human study. Our evaluation reveals a substantial gap between frame-level and temporal anomaly detection. While VLMs consistently detect frame-level anomalies and often localize them accurately, under our main evaluation setting they generally perform near chance on temporal anomaly detection and show limited localization performance. Humans, in contrast, achieve near-ceiling performance on both tasks. Additional analyses across model scales, prompting strategies, sequence lengths, and visual similarity show that performance can improve under some conditions, while substantial gaps in temporal anomaly detection and localization remain. Together, these findings reveal a gap between frame-level and temporal anomaly detection. TimeCatch provides a controlled benchmark for evaluating temporal consistency in vision-language models.

Time series forecasting (TSF) is evolving toward multimodal and agentic settings, yet using foundation models remains uneconomical in resource-constrained scenarios, where compact, specialized forecasters are more desirable. However, lightweight forecasters typically require substantial training data, limiting their use in domains with scarce, slowly accumulated, or privacy-sensitive time series. To address this dilemma, we investigate the challenging problem of few-shot learning for lightweight forecasters. We propose MetaCaster, a meta-harness-optimized multi-agent framework that uses agentic data generation to automatically train specialized lightweight forecasters from only a few examples and textual contexts. Our work highlights a new TSF paradigm in which agents act not as forecasters but as intermediary engineers that prepare efficient, task-specific forecasters for deployment. Experiments on 18 datasets, 23 state-of-the-art lightweight forecasters, and 14 baselines demonstrate that MetaCaster achieves both data efficiency and computational efficiency while maintaining high-quality TSF performance.

Memory is becoming a default subsystem in deployed LLM agents to provide persistent personalization and continuity. This naturally prompts a question: will memory system introduce new vulnerabilities into agents? Thus we propose InjecMEM, a novel memory injection attack paradigm that requires only a single interaction (no read/edit access to memory store) to steer later responses of related queries toward a pre-specified output. Guided by the retrieval-then-generate mechanism of memory systems, we craft the injection with a retriever-agnostic anchor and an adversarial command. The anchor contains high-recall topical cues so that downstream retrieval consistently associates the record with the target topic. The command is a short sequence optimized to remain effective under uncertain fused contexts, variable placements, and long prompts so that it reliably steers outputs once retrieved. We learn the command via gradient-based coordinate search, averaging over synthetic prompt templates and insertion positions, and extend it to joint optimization across backbones to study transfer. Evaluated across multiple memory systems and backbone models, InjecMEM achieves reliable topic-conditioned retrieval and targeted generation, remains effective under memory drift, and leaves non-target queries unaffected. Our results underscore the need to harden memory systems and provide a reproducible framework for studying agent memory.

A machine learning-assisted framework for the inverse design of pixelated millimetre-wave patch antennas targeting the 22–30 GHz band is presented. The antenna surface is represented as a 19x23 binary pixel grid on a Rogers RT/duroid 5880 substrate, where each pixel is either metal or empty, with a continuous electrical path from the feed enforced by design. An initial dataset of approximately 6,000 full-wave CST simulations was collected from structured random pixel patterns, of which only around 40% achieved a resonance with |S11| <= -10 dB anywhere in the band, resulting in an imbalanced dataset. To improve simulation efficiency, an XGBoost binary classifier was trained on this data to distinguish resonant from non-resonant patterns before simulation. Using the classifier as a pre-simulation filter, an additional 4,000 patterns were selected and simulated, raising the overall proportion of resonant designs in the combined 10,000-sample dataset from approximately 40% to 52%. A hybrid CNN-BiLSTM forward surrogate was then trained on this augmented dataset to predict the full complex S11 response across 801 frequency points, using a physics-guided composite loss that explicitly emphasises resonance dip accuracy. Finally, an inverse design model was developed that optimises in a compact 64-dimensional latent space using gradient descent to generate pixel patterns matching a desired S11 specification. The results show good agreement between the surrogate-predicted and CST-simulated |S11| responses for the generated designs and demonstrate the feasibility of automatically designing and reconfiguring antenna structures.

Space robots operate in extreme environments where hardware degradation can critically compromise traditional control strategies. While continual reinforcement learning offers a promising mechanism for online adaptation, it inherently requires access to a reward signal during deployment. However, precise reward computation in space is often infeasible due to the lack of external tracking systems and the overall complexity of the environment. To address the challenge of unobservable rewards, we introduce a reward-free continual learning framework that leverages latent-state world models. By pre-training a model-based agent across diverse simulations, the world model learns a robust predictor of the reward structure within its latent space. Upon deployment to an environment with severe hardware degradation, we freeze the observation encoder and reward predictor to update only the transition dynamics of the world model through unsupervised rollouts. By training the policy entirely on imagined trajectories generated by this updated world model, the agent adapts to altered dynamics without receiving new rewards. We demonstrate our approach across simulated planetary traversal, orbital navigation, and precision assembly tasks subjected to severe morphological failures.

We study the problem of formally explaining why a candidate was not selected by a given tournament rule, by identifying sub-tournaments in which the candidate loses independently of how the rest of the tournament is completed. We define destructive minimal supports as any minimal sub-tournament satisfying this property, which in formal explainable artificial intelligence corresponds to abductive explanations for the question "Why does the loser lose the tournament?". For six common tournament solutions (maximin, uncovered set and its weighted variant, top cycle, Copeland, and Borda) we provide characterizations of when a candidate is either a necessary loser or a possible winner, we determine the size of the smallest destructive minimal supports, complemented by polynomial-time algorithms for their computation except for the case of Borda and Copeland rules which we conjecture to also be polynomial.

Understanding a basketball game requires recognizing events, localizing actions, identifying players, and relating these to structured game knowledge. Existing benchmarks primarily evaluate these abilities one at a time, leaving the interactions among these abilities under-explored. We introduce BasketballBench, a multimodal benchmark comprising 7,980 questions across ten tasks in text, image, and video. It is built from the 2025-2026 NBA season and includes official playby-play, rosters and profiles for 530 active players, and 2,501 possession-level broadcast clips. We further propose BasketballSkills, an agent that composes eight basketball-specific perception and retrieval tools under four reusable skills that specify tool order, evidence bindings, and stopping conditions. Experiments show that current MLLMs struggle particularly on questions requiring the integration of multiple capabilities, whereas BasketballSkills outperforms them, highlighting the effectiveness of explicitly composing domain-specific capabilities for comprehensive basketball understanding.

Diffusion Transformers (DiTs) have shown strong performance in high-fidelity image generation, but their sampling process remains computationally intensive due to full model execution at every timestep. While cache-based acceleration has been explored to mitigate inference cost, naive reuse schemes suffer from low accuracy over long intervals, and Taylor-series-based extrapolation methods often face instability caused by Runge oscillations. In this paper, we propose ChebBooster, a training-free extrapolation framework based on Chebyshev polynomial theory that achieves stable and efficient acceleration for DiTs. Specifically, we adopt the Barycentric formulation to evaluate Chebyshev approximants with high numerical stability and minimal overhead, and further decouple the extrapolation into an offline weight precomputation phase and a lightweight online application stage. Extensive experiments across three representative DiT-based models, including DiT-XL/2, PixArt-$\Sigma$, and FLUX.1-dev, demonstrate that ChebBooster achieves consistent improvements in visual quality and inference efficiency, reaching up to $3.68\times$ latency speedup and $5.12\times$ FLOPs reduction, outperforming existing training-free baselines under diverse generation tasks and resolutions.