Papers

Multimodal large language models (MLLMs) often struggle with fine-grained visual perception when processing complete images, as critical evidence may only appear in local regions. On-policy self-distillation (OPD) enables transferring privileged visual knowledge from informative views to full-image policies, but querying the teacher for every rollout introduces substantial supervision costs. In this work, we propose BAS-OPD, a budget-aware selective OPD framework that allocates teacher supervision under limited query budgets. Instead of querying all rollouts, BAS-OPD selects informative samples while maintaining full-batch student generation. We explore random, uncertainty-based, and learned utility-based selection strategies, where the learned selector estimates query value from detached rollout statistics and online utility signals derived from student–teacher agreement and teacher confidence without additional student forward passes. BAS-OPD only changes training-time supervision allocation and preserves single-pass full-image inference. Experiments on fine-grained multimodal perception benchmarks demonstrate that BAS-OPD achieves strong performance while substantially reducing teacher supervision costs, highlighting the effectiveness of selective OPD under constrained budgets.

AI-based autonomous agents, typically hosted at data centers, must acquire state information from robots or edge devices in order to issue informed control decisions. Managing uncertainty about the state is particularly consequential in safety-critical settings, in which average-case guarantees are insufficient. In this context, we study a sequential decision maker process that jointly decides which actions to take and when to probe given access to an arbitrary state prediction model. We propose online conformal state probing (OCSP), an action and probing policy that certifies worst-case reliability levels without relying on distributional assumptions. OCSP is designed to provably control the missed query error (MQE), i.e., the fraction of instances where probing would have been beneficial, while minimizing the probing rate. OCSP can be applied to existing pre-trained value-based control policies without requiring retraining or fine-tuning. We validate OCSP through numerical simulations to verify theoretical guarantees and to assess performance trade-offs as a function of the calibration of the state predictor.

The connection between the Kolmogorov-Arnold representation theorem (KART) and neural network design has led to the development of Kolmogorov-Arnold Networks (KANs), with applications ranging from STEM problems to AI tasks. In this paper, we investigate the effectiveness of a KAN variant, SechKAN, which relies on hyperbolic secant (sech) functions as basis functions, with a 1D projection to reduce the number of parameters to a level comparable to MLPs. We evaluate SechKAN on three 1D classification datasets: UCI Human Activity Recognition (UCI HAR), ElectricDevices, and Crop, and compare it with several effective networks, including EfficientKAN, MLP, CNN1D, ResNet1D, and DSCNN1D, using approximately comparable parameter budgets. The results indicate that SechKAN achieves competitive performance across the three datasets, with particularly strong performance on Crop. Ablation studies further show that grid size and normalization affect performance, suggesting that SechKAN's effectiveness depends on the dataset and architectural choices. Our source code and experimental implementation are publicly available at: https://github.com/hoangthangta/SechKAN_1D.

Analog circuit sizing remains a challenging and time-consuming task due to the large design space, strong performance trade-offs, and increasing circuit complexity in scaled technologies. Although recent large language model (LLM)-based methods show promise in improving sample efficiency and interpretability, existing approaches often lack explicit circuit-topology understanding and are mainly evaluated on relatively simple analog building blocks. This paper presents a multi-agent LLM-based framework for complex analog circuit sizing. The proposed framework first analyzes the circuit topology and decomposes the netlist into functional blocks and substructures. It also extracts lightweight design knowledge for reuse. Based on the extracted topology and knowledge, a planner coordinates multiple role-specialized sizing agents to update design variables and achieve global performance specifications. This workflow mimics the collaborative process of an expert analog design team and provides a structured, interpretable, and simulation-driven optimization procedure. The framework was validated on eight circuits, with the largest design containing up to 55 transistors and 60 sizing variables. Notably, for the LDO benchmark, the proposed method achieved a 60% success rate with an average of 83 iterations, where classical optimizers failed to find feasible solutions. Further, ablation studies demonstrate that topology understanding, design-knowledge infusion, and agent specialization provide complementary benefits. The source code is available to support reproducibility.

Clinically useful early detection requires validated pre-recognition lead time. Yet event-based evaluations of longitudinal clinical AI can treat recognition-mediated care-process signals as shortcuts and recognition-dependent endpoints as reference standards, inflating apparent performance and lead time while undermining cross-center transport. Such results may serve prognosis without establishing detection before recognition. We define an interval-censored pre-recognition transition, an independent as-of reference standard, and a prespecified recognition proxy to make the claim testable.

A higher evaluation score does not always mean a better language model system. When optimization exploits an evaluator's mistakes, measured progress can conceal unchanged or deteriorating task performance. This failure can arise through parameter updates, selection among generated outputs, or revisions to persistent prompts. We develop a comparative framework for reward hacking across these three optimization substrates: weights, selection, and text. Building on the Proxy Compression Hypothesis and research on inference-time and in-context reward hacking, we examine how reachable behavior, optimization budgets, and persistent adaptation shape exposure to proxy error. We formalize a distance-dependent upper bound on evaluator disagreement and a capacity ordering for nested policy classes, then show why distance alone cannot establish a universal ranking of vulnerability. An exact finite-output illustration demonstrates how the location of a scoring defect changes the behavior favored by each method. We also map representative defenses across substrates, identifying which mechanisms transfer directly and which offer only functional analogies. Persistent prompts receive particular attention: their contents are inspectable, but the behavior induced by a small textual change may be difficult to anticipate. The formal analysis, numerical illustration, and published evidence together provide a basis for comparing optimization methods and identifying the conditions under which their defenses transfer. The resulting framework connects optimization choices to verification requirements: reliable improvement depends on controlling accessible failure modes and preserving evidence of task quality independent of the score being optimized.

Multi-task optimization (MTO) addresses a set of optimization tasks simultaneously, often suffering from inaccurate inter-task relationship estimation under limited evaluation budgets, leading to negative transfer. This paper introduces In-Context Guidance Multitask Optimization (ICG-MTO), a novel framework that leverages numerical foundational models to improve inter-task coupling estimation in few-shot scenarios. Unlike conventional methods that rely solely on scarce observed data, ICG-MTO employs a frozen foundational model to infer auxiliary guidance through in-context learning. The framework operates through three stages: constructing an algorithm-specific in-context query from evaluated solutions, using the foundational model to infer a guidance signal characterizing predictive relationships among tasks, and translating this signal into algorithm-specific guidance for maximum-a-posteriori coupling estimation. This approach provides regularization during the early, data-scarce stages of optimization and gradually relinquishes control as task-specific observations accumulate. We instantiate the framework in multitask Bayesian optimization as ICG-MTBO, using directional fitness-class queries to guide inter-task coupling estimation, and further instantiate it in MFEA-II using decision-space-overlap queries to guide random mating probability estimation. Experiments across synthetic benchmarks and a real-world robot arm control problem, together with evaluations under different acquisition functions and evolutionary multitasking, demonstrate the effectiveness and generality of ICG-MTO for few-shot multitask optimization.

Persuasive video generation (PVG) is a valuable yet under-explored research topic. Despite the significant advances in multimodal content generation, AI-empowered automated creation of human-made-like videos with substantial persuasiveness remains a formidable challenge. In this paper, we propose CogenPVG, a novel Cognitive-Enhanced reflective multi-agent framework tailored for Persuasive Video Generation task. Given the topic and stance from the user, we decouple the sophisticated generation process into four sequential stages: argument reasoning, storyboard planning, asset creation, and post-editing, imitating the workflow of human video producers. To ensure high persuasiveness, each stage is equipped with a pair of generator and critic agents, following a reflective refinement scheme grounded in a solid psychological theory of persuasion, the Elaboration Likelihood Model (ELM). In the argument reasoning stage, we generate highly logical and credible reasoning thoughts under the guidance of critical thinking theory, enabling cognitive enhancement via the central route of the ELM. For the other three stages, we generate and optimize multimodal assets, assembling them into a persuasive video guided by theories of heuristics, as the peripheral route of the ELM. To the best of our knowledge, CogenPVG is the first work focused on general persuasive topics, without being confined to commercial purposes. Extensive experiments and comprehensive analysis demonstrate that our framework achieves the best persuasion performance, thereby proving the effectiveness of our proposed multi-agent framework for the PVG task.

Visual attribution methods typically explain predictions using pixels, superpixels, or regular patches. These representations can localize important regions, but provide limited information about their structure. We introduce MorphoSHAP, a model-agnostic post-hoc method that instead uses morphological shapes as the players of a Shapley attribution game. Using the Tree of Shapes, each shape is described by its scale, geometry, and signed contribution, providing explanations of where the evidence lies, what type of structure carries it, and how strongly it affects the prediction. This shared morphological vocabulary enables spatial, textual, and global class-level explanations beyond image-specific heatmaps. To the best of our knowledge, MorphoSHAP is the first SHAP-based image attribution framework to combine these different forms of explanation. Across five diverse datasets and three architectures, MorphoSHAP achieves strong insertion/deletion performance and outperforms competing attribution methods on several benchmarks. Finally, a user study shows that MorphoSHAP provides explanations that are easy to use and are preferred over standard attribution baselines.

Fine-grained mixture-of-experts (MoE) architectures have become a mainstream design for open-weight LLMs, with hundreds of experts and increasingly many selected per token. This shift makes dynamic expert pruning an attractive route to cheaper inference. Yet existing evidence comes largely from coarser architectures and likelihood-scored multiple-choice benchmarks, leaving three central questions open in the fine-grained regime: how redundant per-token expert selection is, how effectively existing pruning methods exploit that redundancy, and what governs a model's sensitivity to pruning. We fill this gap with a systematic empirical study of twelve fine-grained MoE checkpoints spanning nine architecture families, with a core suite of eleven benchmarks covering knowledge QA, mathematics, code generation, and general reasoning. We find that expert selection is far more redundant than the field's operating points assume: uniformly retaining about two thirds of the selected experts preserves 98.8% of unpruned performance on average, requiring only a one-integer change and delivering 1.2-1.7x measured speedup across two serving backends. This simple baseline leaves little room for dynamic allocation at conservative budgets: even the best published rules differ from it by under 1% at matched expert budgets. Their value emerges under aggressive pruning, where the best rules recover up to 3.0% over uniform truncation, with gains concentrated in the generative tasks that suffer the sharpest degradation. Sensitivity to aggressive pruning also depends on the model: larger and thinking models are more resilient, whereas multimodal models are more vulnerable. Together, these findings reveal how much expert computation fine-grained MoEs can dispense with, and establish when dynamic allocation earns its complexity, informing both practical deployment and future pruning methods.

Runtime traces can appear transparent, but a closed-loop policy determines which states are visited and which failures become visible. We study a simulated hotel-pricing agent mapping time, inventory, and market state to discrete price actions under varying demand regimes. A fault may leave no aggregate trace when the policy rarely visits affected cells. We treat entry into aggregate-only fault interpretation as a diagnosability decision preceding scoring or localization. A reference-map gate requires repeated clean-policy support; a matched runtime gate then requires joint support in clean and current streams. Signal analysis occurs only after both pass. We calibrate false admission on a disjoint clean stream at the physical-component level and model detection by affected clean traffic rather than nominal cell coverage. In a frozen one-shot heldout, 55/72 (76.4%) regime-component units were reference-admitted, representing 20 physical components; 54/55 passed matched runtime admission, while the rejected unit abstained. Stable false admission was 0/20, with a one-sided exact 95% upper bound of 0.1391, meeting the frozen 0.20 criterion. Across 540 repeated unit-arm rows nested in those 20 clusters, affected clean traffic reduced negative log likelihood by 29.3% relative to cell coverage, a gain of 0.1264 nats per row (cluster-bootstrap 95% interval [0.0593, 0.1918]). Adding mask family and its interaction improved log loss by 0.0015 nats per row (one-sided upper bound 0.0066), below the frozen 0.01 practical-sufficiency margin. A development audit found that exact minimum hitting set and greedy selection chose identical supports in 12/12 scenarios because singleton evidence had resolved the conflicts. The result is a bounded rule for interpreting aggregate agent behavior: first establish exposure, then score change, and abstain when the trace cannot support the claim.

LLM agents increasingly work on long-horizon tasks, and the decisions they make along the way, such as which hypothesis to test or which implementation to build on, determine the outcome of the whole run. Making these decisions well is becoming a key capability for both engineering and research agents. We refer to the ability to make good long-horizon decisions as the taste of an agent. While existing benchmarks measure the end-to-end success of agents on long-horizon tasks, none of them measures the taste of an agent. To address this problem, we build Taste-Bench, a benchmark of taste questions constructed automatically from trajectories that agents produced in engineering and research tasks. Each question presents a decision fork, a point in a trajectory where multiple directions are available and one of them leads to a better outcome, and the evaluated model chooses among these directions without seeing what happens after the fork. We mine these forks automatically from parallel attempts at the same task and from detours inside a single trajectory, without needing human annotation. We evaluate frontier models on Taste-Bench and find that the best model answers only 59.7% of the questions correctly. We further find that forks whose deciding evidence appears later in the trajectory are much harder for every model, and that a larger reasoning budget does not improve the accuracy. Finally, we show that taste can be trained. We distill the judgment of a teacher that has seen the outcome into a student model, and the student makes better decisions on unseen tasks and improves end-to-end success on held-out SWE-bench Pro tasks.

Time Series Foundation Models (TSFMs) promise a paradigm shift toward zero-shot forecasting by eliminating task-specific training. However, existing works often overlook trade-offs between predictive accuracy and probabilistic calibration. This paper presents a benchmark study of six TSFMs evaluated on energy, traffic, and financial datasets. We contrast their performance against statistical baselines and a supervised DL model. The study reveals that while TSFMs outperform statistical methods and supervised models, they are subject to a fundamental trade-off between point accuracy and probabilistic reliability. Specifically, xLSTM architectures provide robust probabilistic calibration across horizons. In contrast, patch-based transformers offer competitive accuracy but face calibration issues at long horizons, while transformer-based models exhibit context saturation points for optimal zero-shot reasoning. These findings offer evidence-based guidance for balancing generalization and uncertainty quantification in real-world deployments.

HopChain has shown on still images that multi-hop data synthesis improves vision-language reasoning, because long chain-of-thought reasoning exposes errors that compound across steps, while most data used for reinforcement learning with verifiable rewards (RLVR) rarely demands a chain of visual evidence, so these weaknesses are likely to stay unexposed. We observe the same problem in video, where this framework has not yet been explored. We therefore build Video-HopChain, a dataset of 22,550 multi-hop video questions over 13,378 videos, together with a held-out benchmark of 1,000 questions. Each question chains three to six yes/no questions about moments in one video, and each yields one of two integers depending on its answer. The final answer is the sum of these integers, so an exact match on that sum gives the verifiable reward that RLVR needs. We first train Qwen3-VL-8B with GRPO on a standard video dataset, and a second stage on Video-HopChain then raises the mean over eight video understanding and reasoning benchmarks from 55.4 to 57.9 and improves every one of them. Training on such a dataset, however, exposes a known limitation of GRPO: its learning signal comes from the reward variance within a group, so hard questions whose rollouts are all incorrect and easy questions whose rollouts are all correct both leave the group with no gradient. To recover these groups at the same compute budget, we introduce Confidence-Gated Exploration (CGE). With 8 rollouts per question, CGE samples the first 4 as usual. If these 4 are either all correct or all incorrect, it samples the last 4 with the policy's most confident token masked inside the reasoning span, and removes the masked positions from the loss while all 8 rollouts enter the advantage. With CGE, the mean rises further to 59.3. We release the dataset, the checkpoint, and the data generation and training code.

Graphical User Interface (GUI) Agents autonomously interact with software to fulfill user requests, where GUI navigation stands out as the most critical and challenging capability. Mastering this capability demands a complex synergy of step-wise decision-making, state-action alignment, and long-horizon planning. While directly mixing these corresponding navigation tasks seems intuitive to simultaneously acquire these skills, such a direct combination is severely bottlenecked by inconsistent optimization objectives and profound data heterogeneity. To overcome these barriers, we propose the MaP (stands for “Masked Trajectory Prediction”), a unified framework that seamlessly harmonizes divergent GUI navigation tasks. By modeling multi-turn GUI interactions as a trajectory and defining training objectives through component masking and prediction, MaP shifts the optimization from task-specific marginal distributions to a consistent objective. Furthermore, to handle the data heterogeneity across multiple navigation tasks, we design a role-aware adapter learning module that dynamically routes each token to a specialized representation space. Extensive experiments on five representative GUI navigation benchmarks demonstrate that MaP effectively mitigates gradient conflicts and significantly outperforms the direct mixture training, establishing a robust paradigm for multi-task GUI navigation.

AI planning studies how an agent can reach a goal by executing a sequence of actions. To plan correctly, the agent needs an action model describing when each action can be executed and how it changes the world. Constructing such models by hand requires domain expertise, and can be costly and error-prone. Action models can instead be learned from available data using existing neurosymbolic approaches, but they currently assume access to complete traces of fully observable images . These approaches fail to learn action models under partial observability where some of the images might not be present or are not fully informative of the current state of the world. Hence, this paper proposes NeSyAM, a novel neurosymbolic modeling paradigm for action model learning under partial observability. In addition, the paper presents a unified variational framework for theoretically analysing the limitations of existing methods compared to our proposed approach. NeSyAM is then tested extensively on six visual planning domains and three observation regimes to show it consistently recovers relevant parts of the true action model under partial observability.

Using large language models (LLMs) to simulate diverse human populations has the potential to transform many aspects of computational social science, yet many evaluations score the average response rather than the spread of opinion within real groups. Here, we develop a diagnostic framework that measures point accuracy alongside dispersion retention, the ratio of predicted to human standard deviation ($\dr$), on 10{,}000 respondent–question pairs from the World Values Survey (WVS) spanning twelve countries and six continents. We evaluate eleven zero-shot language models and five variants fine-tuned on WVS data with SFT, DPO, and GRPO. We identify a failure mode we term consensus collapse, where alignment training compresses outputs toward one stereotype per group. Along the post-training trajectory from the Llama~3.1 70B base to the Tulu~3 checkpoints, the first stage, supervised instruction tuning, removes half of the spread with minimal accuracy gain ($\dr$ 1.22 to 0.59; accuracy $+0.9$ points), the later stages do not restore it, and a gap opens between WEIRD and non-WEIRD countries that survey fine-tuning then deepens while pursuing higher point accuracy. The most accurate model (Tulu~3 70B-DPO fine-tuned on WVS, 57.9%) keeps half the human spread overall ($\dr = 0.50$) and 11% of it for Nigeria, against 0.70–0.87 for WEIRD countries. Raising the sampling temperature to 1.0 leaves the Wasserstein-1 distance ($\wone$) to human distributions unchanged for both fine-tuned DPO models, and GRPO on Qwen~3.5 9B does not restore the spread under either an accuracy reward or a distribution-shaped reward. Mixing the aligned model with an unaligned prior raises $\dr$ from 0.51 to 0.62 on a held-out split but leaves Nigeria at 0.36. Point accuracy alone therefore misjudges these simulators, and current post-training trades diversity for consensus.

Applying large language models to Traditional Chinese Medicine (TCM) prescription generation reveals three clinically critical gaps: models produce end-to-end mappings without auditable reasoning following the li-fa-fang-yao paradigm (SR Gap), treat each encounter in isolation without follow-up adjustment via sui zheng jia jian (LA Gap), and fail to enforce absolute contraindication rules such as Shi Ba Fan (SC Gap). We propose a progressive four-stage framework (SFT $\to$ PG-CoT $\to$ Dynamic $\to$ K-RL) that addresses each gap: PG-CoT constrains CoT distillation under the li-fa-fang-yao paradigm to produce auditable diagnostic chains, Dynamic SFT models patient trajectories with explicit transition reasoning, and K-RL encodes deterministic pharmacological rules as rule-based DPO preference signals. Across 12 fine-tuned models and 6 zero-shot baselines, our framework substantially improves prescription quality over zero-shot baselines—with a 7B model (Mistral-7B) surpassing zero-shot GPT-5 on all three TCM evaluation metrics.

Omni-modal models have expanded multimodal interaction across vision, audio, speech, and language. However, their training is predominantly organized around semantic descriptions and general-purpose objectives, leaving physical attributes, interaction states, and causal mechanisms only partially specified. This gap is not simply a matter of modality coverage: adding more modalities does not by itself provide the supervision needed to connect observations with the physical structure of the world. We present OmniFysics-Nano-V2, a compact omni-modal model for physical-world perception and understanding. The model supports image, video, audio, speech, and text inputs within a shared reasoning framework, together with text and speech generation. To address the lack of explicit physical supervision, we construct a dual-branch physics-aware data pipeline that grounds salient objects in structured physical attributes and aligns visual changes with acoustic events, intermediate responses, and interaction outcomes. To address homogeneous training objectives, we curate reinforcement-learning prompts by reward diversity and adopt a two-stage Group Relative Policy Optimization curriculum that progresses from general task correctness to fine-grained physical perceptual reasoning. Experiments across multimodal, audio-visual, and physical reasoning benchmarks show that the proposed data and training strategy improves physical-world understanding while preserving broad omni-modal competence. The proposed model achieves leading result on 17 of 21 benchmarks against SOTA omni-modal models. By equipping AI systems with both omni-modal and physical-world perception capabilities, OmniFysics-Nano-V2 is poised to become a cornerstone of next-generation Physical AI.

Class-balanced replay controls class frequency but does not determine the interval between successive replay appearances of a class. We study this interval, the rehearsal gap, separately from the class marginal and class co-occurrence, and introduce randomised-pass replay (RPR), which visits each resident class once per shuffled pass. For a fixed set of C resident classes and replay batch size b less than or equal to C, RPR preserves the balanced time-averaged class marginal and bounds every gap by 2*ceil(C/b)-1; a churn-conditional bound applies while the resident set changes. The scheduler uses no future class information and adds no replay examples or forward passes. In a linear-head ER-ACE diagnostic, joint absence from the incoming and replay batches produces a one-sided classifier-bias gradient. Longer absence episodes are associated with larger negative bias displacement, and removing the incoming-loss mask attenuates the scheduling effect. In the primary ER-ACE experiments, RPR improves final average accuracy by 0.72-1.67 percentage points relative to independent class-balanced retrieval under reservoir storage, with positive effects also observed under balanced storage. Pretrained ViTs show positive effects on the tested LT10 streams with small replay batches, while matched larger-batch controls show no material effect. Fixed-cycle and reused-pass controls change more than one temporal statistic, so the experiments do not isolate rehearsal-gap length from all other forms of temporal dependence. The accuracy effects depend on the learner and operating regime.

Self-supervised learning for combinatorial optimization has emerged as a promising paradigm for solving discrete optimization problems with neural networks, but a central challenge remains: handling hard combinatorial constraints within continuous, gradient-based training. Continuously extending combinatorial objectives to convex domains is a powerful technique, yet existing approaches often require projection steps that constrain neural network outputs to lie inside the feasible polytope and rely on ad-hoc and problem-specific constructions. We propose a general framework in which the neural network is allowed to predict arbitrary continuous vectors that could potentially lie outside of the feasible polytope. These predictions are then approximated by sparse convex combinations of feasible solutions using a geometric decomposition algorithm based on Frank–Wolfe methods and approximate Caratheodory results. This decomposition induces an a.e.-differentiable, self-supervised loss defined as the expected value of the discrete objective. The same procedure provides an automatic rounding guarantee at inference time. We demonstrate strong empirical performance across multiple combinatorial problems, including the Quadratic Assignment Problem, Maximum Coverage, and the Traveling Salesperson Problem.

Language models are increasingly trained on the outputs of other models, forming chains that we call lineages, in which a trait present in one generation can pass to the next. Prior work on subliminal learning has shown that a teacher's trait can transmit to a student through filtered data carrying none of the trait's content. However, the evidence covers only a single training step. We study whether such a trait holds or fades across lineages. We instill the trait into three copies of Qwen2.5-7B-Instruct and iterate the training step to depth ten from each, reading every generation two ways on the same held-out prompts: a keyword screen that looks for expressions of the trait in the model's output, and an activation probe that projects each model's displacement from the base onto a direction built from the other lineages' teachers. We report two findings. First, the trait persists through ten generations across three lineages. The instilled models express it on every completion; the keyword-screen rate falls to 55.6% after the first step and to 21.1% by generation ten. The base itself matches the screen on none of its 300 completions. Second, the trait can be present internally while absent behaviorally. When the model's default system prompt is removed at evaluation, the generation-ten students' keyword-screen rate is zero on every prompt while the probe score stays positive on every prompt. Steering the untreated base with the displacement of a generation-ten student, which is trained and measured under the default system prompt, induces screened expression of the trait even with the system prompt removed, while that same student shows no expression of the trait with the system prompt removed.

Though artificial intelligence (AI) increasingly transforms modern medicine, its integration into Traditional Chinese Medicine (TCM) has been relatively slow, primarily due to TCM's reliance on holistic, subjective diagnostic methods—namely Inspection, Auscultation and Olfaction, Inquiry, and Palpation(I-AOI-P)—which are difficult to align with quantitative, standardized medical systems. In this work, we introduce a Unification Framework for Multimodal Data (UFMD), which automatically processes tongue and pulse images into structured, clinically standard descriptions, integrating multi-source diagnostic information into a unified digital record of I-AOI-P process. Building on this structured data, we create LingLan-14B, a TCM-specific large language model fine-tuned via supervised learning to emulate the diagnostic logic and workflow of I-AOI-P process. Experimental results show that our method significantly enhances diagnostic accuracy, achieving a relative improvement of 103.5% over the baseline (62.72% vs. 30.82%) and reaching an F1-score of up to 82%.

Multi-source knowledge graphs (KGs) need query mechanisms that expose reliability and exploit domain structure. This paper presents TCMaster, a property-graph query substrate for confidence-aware traversal and workload-guided physical design over Traditional Chinese Medicine KGs. TCMaster integrates pharmacopoeias, prescriptions, molecular databases, and LLM-extracted micro-semantics into a KG with approximately 221K entities and 723K base edges. It annotates edges with provenance-level confidence, rewrites Cypher queries with confidence predicates, ranks multi-hop paths under PRODUCT, MIN, or weighted-average policies, and uses ontology skew through direction selection, herb-attribute bitmaps, and materialized shortcut edges. On Neo4j, direction selection improves attribute lookup by a factor of 1.47, shortcuts accelerate high-fanout target counting by a factor of 4.42, confidence filtering removes 39.3 percent of low-quality heterogeneous paths, and KG retrieval improves TCMbench QA accuracy by 20.0 percentage points.

Purpose: To develop and evaluate an interpretable artificial intelligence (AI) framework for glaucoma screening from low-cost portable, handheld retinal fundus photographs in a West African population and to compare its performance with clinical tabletop fundus imaging. Methods: We used data from a community-based study of 681 participants (1,362 eyes) in Nigeria, comprising 414 glaucoma, 478 glaucoma suspect, and 470 non-glaucoma eyes. Fundus photographs were acquired using the low-cost handheld, portable Volk Viva retinal camera and the Canon CR-2-AF tabletop camera. We fine-tuned component models separately to each device to perform vessel segmentation, cup and disc boundary segmentation, and feature extraction to detect optic nerve head features. A final classification model combined these components to classify scans as glaucoma, glaucoma suspect or non-glaucoma. Feature-weight analysis and Gradient-weighted Class Activation Mapping were used for interpretation. Results: The models performed well on both Volk Viva and Canon CR-2-AF images: Vessel segmentation: 0.98 Dice Coefficient (DC) (Volk) and 0.94 DC (Canon); Cup and disc segmentation: 0.95 DC (Volk) and 0.96 DC (Canon); Optic nerve head feature detection: area under the receiver operating characteristic curve (AUCs) of 0.83$\pm$0.03 (Volk) and 0.87$\pm$0.04 (Canon); Classification model: AUCs of 0.85$\pm$0.01 (Volk) and 0.93$\pm$0.01 (Canon). Reports for each image, present model decision confidence scores and decision-rationale visualizations to support clinical interpretation. Conclusions: Volk Viva results were reasonably comparable to Canon CR-2-AF in the component models and not far behind in classification. This shows that interpretable AI combined with low-cost, portable imaging may enhance community-level glaucoma screening, especially in settings with limited specialist access and resources.

Long-horizon assigned work requires an LLM agent to track the state of a task: which steps are done, blocked, cancelled, or open to repetition. Agent systems either keep this state as text in the prompt and rely on the model to read that text, or move the state into a module that enforces it, and each system is evaluated as a whole, so no one knows how much reliability comes from the state being shown, told, or enforced. We fix the task rules, the model, and paired episodes and vary how strongly task state reaches the agent: a raw transcript, an exact checklist, per-turn directives from a state machine compiled from the brief and advanced only by execution receipts, or an enforcement gate on that machine that refuses state-violating actions; every episode is scored by exact payload matching against dynamic ground truth. Across three models, two reasoning regimes, and two domains, four findings hold without per-turn reasoning: displaying accurate state is unreliable, an unverified ledger the agent writes itself beats an accurate checklist it is shown, directives help in proportion to the model's obedience, and enforcement needs no obedience but is bounded by the correctness of its state and by the matcher that maps requests to steps; per-turn reasoning at a 235B agent compresses these separations without repairing the text rungs. The same gate, compiled from $\tau^2$-bench's airline policy, raises a 235B agent's pass$^1$ from 0.39 to 0.54 and changes nothing for a 35B agent that rarely violates the policy; on PM-Bench, where acting turns on recognizing a cue rather than on state, showing the record is the best rung–matching or beating both gates and reversing the ledger-over-checklist finding–and enforcing the matcher's judgement drops a 35B agent below its raw transcript. Enforcement pays when failures are state-decidable and frequent, and hurts when the gate's judgement is wrong.

Large language model (LLM) agents must generalize from tools seen during training to unseen tools at deployment. A key challenge is tool trialing, i.e., excessive trials waste the interaction budget, whereas selective trials enable exploration of unfamiliar tools. Existing outcome-based post-training leaves wasteful trials unguided, while turn-level supervision may suppress necessary exploration. We introduce ToolCompass, a post-training framework that guides tool trialing by organizing tool-call representations according to shared functions. Specifically, ToolCompass models each function class as a von Mises–Fisher distribution and jointly reduces intra-function variation across domains and increases inter-function separation. This structure transfers experience from seen tools to functionally similar unseen tools, directing exploration away from unrelated alternatives. ToolCompass requires no ground-truth call traces or unseen-tool access and incurs no inference overhead. Experiments on AppWorld and FTRL show consistent gains across GRPO, RFT, and DMPO. improves AppWorld OOD task success by up to 10.71 percentage points over vanilla post-training and performs best among competitive baselines on both benchmarks.

Marketers now deploy generative AI agents as synthetic consumers to pretest visual assets such as logos, packaging, and advertising at a fraction of human-panel cost. However, this procedure assumes that a model seeing a visual cue can also perceive its consumer meaning, which is largely untested. We stress-test the assumption using six canonical visual marketing experiments, varying the two levers managers control: model generation (GPT-4o-mini vs. GPT-5.4-mini) and input format (plain text vs. JSON). Every resulting configuration passed the manipulation checks; however, none of the configurations reproduced more than two of the six human effects, and the remainder were nonsignificant. The one exception was a significant reversal of the human pattern. Providing conceptual or empirical evidence through in-context learning steers average responses toward the human effect. Yet steering has a limit: even when it succeeds, a configuration reproduces less than half of the natural spread of human responses and so understates consumer heterogeneity. We integrate these results into an AI governance protocol (Calibrate, Intervene, Deploy) that delineates when synthetic consumers can responsibly screen creatives and when human panels remain necessary.

Lower cost open source robots and reinforcement learning (RL) simulation tools create new opportunities for precollege students to engage with contemporary robotics. However, translating a complete research workflow, spanning mechanical assembly, electrical setup, simulation, policy learning, system identification, and physical deployment, into a coherent course for novice learners remains challenging. We present an integrated robotics course framework that organizes these activities around a shared robotic artifact. The framework combines parallel disciplinary tracks, sequencing based on technical dependencies, progressive integration of simulation and hardware, layered performance checkpoints, and structures for balancing collaborative work with individual accountability. We illustrate the framework through a high school curriculum organized around a robot project in which pairs of students assemble an open source humanoid robot, train a walking policy in simulation, and deploy it on the physical platform. The framework was developed through an iterative design process that included formative review by five experts in robotics research, engineering, secondary STEM education, and curriculum design. Expert feedback highlighted three central design tensions: authenticity versus cognitive load, system integration versus timely visible progress, and team construction versus individual accountability. These tensions informed the final framework presented in this paper. This work offers a structured approach for adapting robotics research workflows into interdisciplinary precollege courses; future classroom studies are needed to examine implementation and student learning.

As large language models (LLMs) scale rapidly, dense full-parameter adaptation becomes increasingly expensive, motivating sparse and modular architectures such as Mixture-of-Experts (MoE) models. This shift raises a key question for parameter-efficient fine-tuning (PEFT): at what granularity should parameters be selected and updated? Existing PEFT methods such as LoRA operate on predefined weight matrices, while expert-level sparse tuning methods update entire selected experts. However, we observe that activated experts are internally sparse, with only a small fraction of intermediate channels strongly responding to downstream tasks, indicating that expert-level adaptation is still too coarse. We propose NSFT (Neural Sub-expert Fine-Tuning), a fine-grained PEFT framework that refines MoE adaptation from experts to sub-experts. NSFT decomposes each expert along the intermediate dimension into structured channel groups and selects task-relevant sub-experts by combining routing importance with intra-expert activation saliency. To optimize sparse partial updates, NSFT further introduces learning-rate scaling and dynamic gradient scaling to compensate for the reduced effective update magnitude. Experiments on OLMoE and Ling-mini-2.0 across challenging domain-specific tasks and general benchmarks show that NSFT consistently outperforms representative PEFT and expert-level sparse tuning baselines, while using substantially fewer trainable parameters and preserving competitive general capability. These results suggest that sub-expert-level adaptation is a more precise and efficient PEFT paradigm for MoE LLMs.