arXiv:2603.22306v1 Announce Type: new Abstract: Affective judgment in real interaction is rarely a purely local prediction problem. Emotional meaning often depends on prior trajectory, accumulated context, and multimodal evidence that may be weak, noisy, or incomplete at the current moment. Although multimodal emotion recognition (MER) has improved the integration of text, speech, and visual signals, many existing systems remain optimized for short-range inference and provide limited support for persistent affective memory, long-horizon dependency modeling, and robust interpretation under imperfect input. This technical report presents the Memory Bear AI Memory Science Engine, a memory-centered framework for multimodal affective intelligence. Instead of treating emotion as a transient output label, the framework models affective information as a structured and evolving variable within a memory system. It organizes processing through structured memory formation, working-memory aggregation, long-term consolidation, memory-driven retrieval, dynamic fusion calibration, and continuous memory updating. At its core, multimodal signals are transformed into structured Emotion Memory Units (EMUs), enabling affective information to be preserved, reactivated, and revised across interaction horizons. Experimental results show consistent gains over comparison systems across benchmark and business-grounded settings, with stronger accuracy and robustness, especially under noisy or missing-modality conditions. The framework offers a practical step from local emotion recognition toward more continuous, robust, and deployment-relevant affective intelligence.

arXiv:2603.22311v1 Announce Type: new Abstract: Fluorescence-based Ca$^{2+}$-imaging is a powerful tool for studying localized neuronal activity, including miniature Synaptic Calcium Transients, providing real-time insights into synaptic activity. These transients induce only subtle changes in the fluorescence signal, often barely above baseline, which poses a significant challenge for automated synaptic transient detection and segmentation. Detecting astronomical transients similarly requires efficient algorithms that will remain robust over a large field of view with varying noise properties. We leverage techniques used in astronomical transient detection for miniature Synaptic Calcium Transient detection in fluorescence microscopy. We present Astro-BEATS, an automatic miniature Synaptic Calcium Transient segmentation algorithm that incorporates image estimation and source-finding techniques used in astronomy and designed for Ca$^{2+}$-imaging videos. Astro-BEATS outperforms current threshold-based approaches for synaptic Ca$^{2+}$ transient detection and segmentation. The produced segmentation masks can be used to train a supervised deep learning algorithm for improved synaptic Ca$^{2+}$ transient detection in Ca$^{2+}$-imaging data. The speed of Astro-BEATS and its applicability to previously unseen datasets without re-optimization makes it particularly useful for generating training datasets for deep learning-based approaches.

arXiv:2603.22345v1 Announce Type: new Abstract: Multimodal emotion recognition in conversations (MERC) aims to identify and understand the emotions expressed by speakers during utterance interaction from multiple modalities (e.g., text, audio, images, etc.). Existing studies have shown that GCN can improve the performance of MERC by modeling dependencies between speakers. However, existing methods usually use fixed parameters to process multimodal features for different emotion types, ignoring the dynamics of fusion between different modalities, which forces the model to balance performance between multiple emotion categories, thus limiting the model's performance on some specific emotions. To this end, we propose a dynamic fusion-aware graph convolutional neural network (DF-GCN) for robust recognition of multimodal emotion features in conversations. Specifically, DF-GCN integrates ordinary differential equations into graph convolutional networks (GCNs) to {capture} the dynamic nature of emotional dependencies within utterance interaction networks and leverages the prompts generated by the global information vector (GIV) of the utterance to guide the dynamic fusion of multimodal features. This allows our model to dynamically change parameters when processing each utterance feature, so that different network parameters can be equipped for different emotion categories in the inference stage, thereby achieving more flexible emotion classification and enhancing the generalization ability of the model. Comprehensive experiments conducted on two public multimodal conversational datasets {confirm} that the proposed DF-GCN model delivers superior performance, benefiting significantly from the dynamic fusion mechanism introduced.

arXiv:2603.22386v1 Announce Type: new Abstract: Large language model (LLM)-based systems are becoming increasingly popular for solving tasks by constructing executable workflows that interleave LLM calls, information retrieval, tool use, code execution, memory updates, and verification. This survey reviews recent methods for designing and optimizing such workflows, which we treat as agentic computation graphs (ACGs). We organize the literature based on when workflow structure is determined, where structure refers to which components or agents are present, how they depend on each other, and how information flows between them. This lens distinguishes static methods, which fix a reusable workflow scaffold before deployment, from dynamic methods, which select, generate, or revise the workflow for a particular run before or during execution. We further organize prior work along three dimensions: when structure is determined, what part of the workflow is optimized, and which evaluation signals guide optimization (e.g., task metrics, verifier signals, preferences, or trace-derived feedback). We also distinguish reusable workflow templates, run-specific realized graphs, and execution traces, separating reusable design choices from the structures actually deployed in a given run and from realized runtime behavior. Finally, we outline a structure-aware evaluation perspective that complements downstream task metrics with graph-level properties, execution cost, robustness, and structural variation across inputs. Our goal is to provide a clear vocabulary, a unified framework for positioning new methods, a more comparable view of existing body of literature, and a more reproducible evaluation standard for future work in workflow optimizations for LLM agents.

arXiv:2603.22619v1 Announce Type: new Abstract: LLMs often generate seemingly valid answers to flawed or ill-posed inputs. This is not due to missing knowledge: under discriminative prompting, the same models can mostly identify such issues, yet fail to reflect this in standard generative responses. This reveals a fundamental know-act gap between discriminative recognition and generative behavior. Prior work largely characterizes this issue in narrow settings, such as math word problems or question answering, with limited focus on how to integrate these two modes. In this work, we present a comprehensive analysis using FaultyScience, a newly constructed large-scale, cross-disciplinary benchmark of faulty scientific questions. We show that the gap is pervasive and stems from token-level autoregression, which entangles task selection (validate vs. answer) with content generation, preventing discriminative knowledge from being utilized. To address this, we propose DeIllusionLLM, a task-level autoregressive framework that explicitly models this decision. Through self-distillation, the model unifies discriminative judgment and generative reasoning within a single backbone. Empirically, DeIllusionLLM substantially reduces answer-despite-error failures under natural prompting while maintaining general reasoning performance, demonstrating that self-distillation is an effective and scalable solution for bridging the discriminative-generative know-act gap

arXiv:2603.22677v1 Announce Type: new Abstract: Distributional metrics such as Fr\'echet Audio Distance cannot score individual music clips and correlate poorly with human judgments, while the only per-sample learned metric achieving high human correlation is closed-source. We introduce MUQ-EVAL, an open-source per-sample quality metric for AIgenerated music built by training lightweight prediction heads on frozen MuQ-310M features using MusicEval, a dataset of generated clips from 31 text-to-music systems with expert quality ratings. Our simplest model, frozen features with attention pooling and a two-layer MLP, achieves system-level SRCC = 0.957 and utterance-level SRCC = 0.838 with human mean opinion scores. A systematic ablation over training objectives and adaptation strategies shows that no addition meaningfully improves the frozen baseline, indicating that frozen MuQ representations already capture quality-relevant information. Encoder choice is the dominant design factor, outweighing all architectural and training decisions. LoRA-adapted models trained on as few as 150 clips already achieve usable correlation, enabling personalized quality evaluators from individual listener annotations. A controlled degradation analysis reveals selective sensitivity to signal-level artifacts but insensitivity to musical-structural distortions. Our metric, MUQ-EVAL, is fully open-source, outperforms existing open per-sample metrics, and runs in real time on a single consumer GPU. Code, model weights, and evaluation scripts are available at https://github.com/dgtql/MuQ-Eval.

arXiv:2603.22767v1 Announce Type: new Abstract: Observational studies can yield clinically actionable evidence at scale, but executing them on real-world databases is open-ended and requires coherent decisions across cohort construction, analysis, and reporting. Prior evaluations of LLM agents emphasize isolated steps or single answers, missing the integrity and internal structure of the resulting evidence bundle. To address this gap, we introduce RWE-bench, a benchmark grounded in MIMIC-IV and derived from peer-reviewed observational studies. Each task provides the corresponding study protocol as the reference standard, requiring agents to execute experiments in a real database and iteratively generate tree-structured evidence bundles. We evaluate six LLMs (three open-source, three closed-source) under three agent scaffolds using both question-level correctness and end-to-end task metrics. Across 162 tasks, task success is low: the best agent reaches 39.9%, and the best open-source model reaches 30.4%. Agent scaffolds also matter substantially, causing over 30% variation in performance metrics. Furthermore, we implement an automated cohort evaluation method to rapidly localize errors and identify agent failure modes. Overall, the results highlight persistent limitations in agents' ability to produce end-to-end evidence bundles, and efficient validation remains an important direction for future work. Code and data are available at https://github.com/somewordstoolate/RWE-bench.

arXiv:2603.22813v1 Announce Type: new Abstract: Humans often juggle multiple, sometimes conflicting objectives and shift their priorities as circumstances change, rather than following a fixed objective function. In contrast, most computational decision-making and multi-objective RL methods assume static preference weights or a known scalar reward. In this work, we study sequential decision-making problem when these preference weights are unobserved latent variables that drift with context. Specifically, we propose Dynamic Preference Inference (DPI), a cognitively inspired framework in which an agent maintains a probabilistic belief over preference weights, updates this belief from recent interaction, and conditions its policy on inferred preferences. We instantiate DPI as a variational preference inference module trained jointly with a preference-conditioned actor-critic, using vector-valued returns as evidence about latent trade-offs. In queueing, maze, and multi-objective continuous-control environments with event-driven changes in objectives, DPI adapts its inferred preferences to new regimes and achieves higher post-shift performance than fixed-weight and heuristic envelope baselines.

arXiv:2603.22844v2 Announce Type: new Abstract: Surgical smoke severely degrades intraoperative video quality, obscuring anatomical structures and limiting surgical perception. Existing learning-based desmoking approaches rely on scarce paired supervision and deterministic restoration pipelines, making it difficult to perform exploration or reinforcement-driven refinement under real surgical conditions. We propose PhySe-RPO, a diffusion restoration framework optimized through Physics- and Semantics-Guided Relative Policy Optimization. The core idea is to transform deterministic restoration into a stochastic policy, enabling trajectory-level exploration and critic-free updates via group-relative optimization. A physics-guided reward imposes illumination and color consistency, while a visual-concept semantic reward learned from CLIP-based surgical concepts promotes smoke-free and anatomically coherent restoration. Together with a reference-free perceptual constraint, PhySe-RPO produces results that are physically consistent, semantically faithful, and clinically interpretable across synthetic and real robotic surgical datasets, providing a principled route to robust diffusion-based restoration under limited paired supervision.

arXiv:2603.22846v1 Announce Type: new Abstract: Embodied Visual Tracking (EVT), a core dynamic task in embodied intelligence, requires an agent to precisely follow a language-specified target. Yet most existing methods rely on single-agent imitation learning, suffering from costly expert data and limited generalization due to static training environments. Inspired by competition-driven capability evolution, we propose CoMaTrack, a competitive game-theoretic multi-agent reinforcement learning framework that trains agents in a dynamic adversarial setting with competitive subtasks, yielding stronger adaptive planning and interference-resilient strategies. We further introduce CoMaTrack-Bench, the first benchmark for competitive EVT, featuring game scenarios between a tracker and adaptive opponents across diverse environments and instructions, enabling standardized robustness evaluation under active adversarial interactions. Experiments show that CoMaTrack achieves state-of-the-art results on both standard benchmarks and CoMaTrack-Bench. Notably, a 3B VLM trained with our framework surpasses previous single-agent imitation learning methods based on 7B models on the challenging EVT-Bench, achieving 92.1% in STT, 74.2% in DT, and 57.5% in AT. The benchmark code will be available at https://github.com/wlqcode/CoMaTrack-Bench

arXiv:2603.22869v1 Announce Type: new Abstract: Large Language Models (LLMs) have become core cognitive components in modern artificial intelligence (AI) systems, combining internal knowledge with external context to perform complex tasks. However, LLMs typically treat all accessible data indiscriminately, lacking inherent awareness of knowledge ownership and access boundaries. This deficiency heightens risks of sensitive data leakage and adversarial manipulation, potentially enabling unauthorized system access and severe security crises. Existing protection strategies rely on rigid, uniform defense that prevent dynamic authorization. Structural isolation methods faces scalability bottlenecks, while prompt guidance methods struggle with fine-grained permissions distinctions. Here, we propose the Chain-of-Authorization (CoA) framework, a secure training and reasoning paradigm that internalizes authorization logic into LLMs' core capabilities. Unlike passive external defneses, CoA restructures the model's information flow: it embeds permission context at input and requires generating explicit authorization reasoning trajectory that includes resource review, identity resolution, and decision-making stages before final response. Through supervised fine-tuning on data covering various authorization status, CoA integrates policy execution with task responses, making authorization a causal prerequisite for substantive responses. Extensive evaluations show that CoA not only maintains comparable utility in authorized scenarios but also overcomes the cognitive confusion when permissions mismatches. It exhibits high rejection rates against various unauthorized and adversarial access. This mechanism leverages LLMs' reasoning capability to perform dynamic authorization, using natural language understanding as a proactive security mechanism for deploying reliable LLMs in modern AI systems.

arXiv:2603.22871v1 Announce Type: new Abstract: Current large language models (LLMs) primarily rely on linear sequence generation and massive parameter counts, yet they severely struggle with complex algorithmic reasoning. While recent reasoning architectures, such as the Hierarchical Reasoning Model (HRM) and Tiny Recursive Model (TRM), demonstrate that compact recursive networks can tackle these tasks, their training dynamics often lack rigorous mathematical guarantees, leading to instability and representational collapse. We propose the Contraction Mapping Model (CMM), a novel architecture that reformulates discrete recursive reasoning into continuous Neural Ordinary and Stochastic Differential Equations (NODEs/NSDEs). By explicitly enforcing the convergence of the latent phase point to a stable equilibrium state and mitigating feature collapse with a hyperspherical repulsion loss, the CMM provides a mathematically grounded and highly stable reasoning engine. On the Sudoku-Extreme benchmark, a 5M-parameter CMM achieves a state-of-the-art accuracy of 93.7 %, outperforming the 27M-parameter HRM (55.0 %) and 5M-parameter TRM (87.4 %). Remarkably, even when aggressively compressed to an ultra-tiny footprint of just 0.26M parameters, the CMM retains robust predictive power, achieving 85.4 % on Sudoku-Extreme and 82.2 % on the Maze benchmark. These results establish a new frontier for extreme parameter efficiency, proving that mathematically rigorous latent dynamics can effectively replace brute-force scaling in artificial reasoning.

arXiv:2603.22933v1 Announce Type: new Abstract: The incorporation of neuroimaging techniques such as electroenchephalography (EEG) and functional near-infrared spectroscopy (fNIRS) has provided new opportunities for the analysis of dynamic brain processes involved in cognitive and motor functions. Despite the great contribution of the open-access neuroimaging datasets to neuroscience studies, they have mainly remained on a single modality and isolated task paradigms performed in a controlled environments. These limitations restrict the analysis of multi-task effects in real-world applications, thus creating a gap in the understanding of how cognitive and motor processes interact in daily life activities. To address these limitations, we present a multi-modal dataset containing neurophysiological (EEG, fNIRS), physiological (ECG), behavioral, and subjective measures collected from 30 healthy participants over three sessions. This dataset includes a hierarchical series of seven tasks ranging from single cognitive and motor activities, such as N-back, motor, passive motor, mental arithmetic and motor imagery, to combined cognitive-motor interactions simulating real life scenarios. This raw dataset provides a resource for developing advanced preprocessing methods and analysis pipelines, with potential applications in brain-computer interfaces, neurorehabilitation, and other fields requiring an understanding of multi-tasks brain dynamics. https://doi.org/10.18112/openneuro.ds007554.v1.0.0

arXiv:2603.22935v1 Announce Type: new Abstract: Chest X-ray report generation and automated evaluation are limited by poor recognition of low-prevalence abnormalities and inadequate handling of clinically important language, including negation and ambiguity. We develop a clinician-guided framework combining human expertise and large language models for multi-label finding extraction from free-text chest X-ray reports and use it to define Ran Score, a finding-level metric for report evaluation. Using three non-overlapping MIMIC-CXR-EN cohorts from a public chest X-ray dataset and an independent ChestX-CN validation cohort, we optimize prompts, establish radiologist-derived reference labels and evaluate report generation models. The optimized framework improves the macro-averaged score from 0.753 to 0.956 on the MIMIC-CXR-EN development cohort, exceeds the CheXbert benchmark by 15.7 percentage points on directly comparable labels, and shows robust generalization on the ChestX-CN validation cohort. Here we show that clinician-guided prompt optimization improves agreement with a radiologist-derived reference standard and that Ran Score enables finding-level evaluation of report fidelity, particularly for low-prevalence abnormalities.

arXiv:2603.22973v1 Announce Type: new Abstract: Computational methods applied to legal scholarship hold the promise of analyzing law at scale. We start from a simple question: how often do courts implicitly apply statutory rules? This requires distinguishing legal reasoning from semantic similarity. We focus on implicit citation of the French Civil Code in first-instance court decisions and introduce a benchmark of 1,015 passage-article pairs annotated by three legal experts. We show that expert disagreement predicts model failures. Inter-annotator agreement is moderate ($\kappa$ = 0.33) with 43% of disagreements involving the boundary between factual description and legal reasoning. Our supervised ensemble achieves F1 = 0.70 (77% accuracy), but this figure conceals an asymmetry: 68% of false positives fall on the 33% of cases where the annotators disagreed. Despite these limits, reframing the task as top-k ranking and leveraging multi-model consensus yields 76% precision at k = 200 in an unsupervised setting. Moreover, the remaining false positives tend to surface legally ambiguous applications rather than obvious errors.

arXiv:2603.23004v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated great capabilities across diverse natural language tasks; yet their ability to solve abstraction and optimization problems with constraints remains scarcely explored. In this paper, we investigate whether LLMs can reason and optimize under the physical and operational constraints of Optimal Power Flow (OPF) problem. We introduce a challenging evaluation setup that requires a set of fundamental skills such as reasoning, structured input handling, arithmetic, and constrained optimization. Our evaluation reveals that SoTA LLMs fail in most of the tasks, and that reasoning LLMs still fail in the most complex settings. Our findings highlight critical gaps in LLMs' ability to handle structured reasoning under constraints, and this work provides a rigorous testing environment for developing more capable LLM assistants that can tackle real-world power grid optimization problems.

arXiv:2603.23082v1 Announce Type: new Abstract: Alzheimer's disease (AD) develops over a prolonged preclinical phase, during which neuropathological changes accumulate long before cognitive symptoms appear. Identifying cognitive functions affected at early stages is critical for the preclinical detection of asymptomatic individuals at-risk of AD. Early risk identification could enable timely interventions aimed at mitigating the development of significant future cognitive impairment. While episodic memory decline typically appears after substantial medial temporal lobe damage, spatial navigation has emerged as a particularly sensitive cognitive function in preclinical AD. In this review, we provide an overview of spatial navigation computations and the tasks used to assess them, highlighting how spatial navigation relies on neural circuits corresponding to the earliest sites of AD pathology. We synthesize evidence from cognitively unimpaired individuals with AD biomarkers, i.e. individuals at-risk of AD, and discuss future research directions. Overall, performance on spatial navigation tasks, particularly path integration and wayfinding, correlates with plasma and CSF biomarkers of AD pathology, notably p-tau. Spatial navigation assessment can represent a sensitive and scalable approach for early detection of individuals at-risk of AD in preclinical stages, and will inform future interventions to mitigate the progression toward clinically significant cognitive impairment.

arXiv:2603.23085v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have enabled interpretable medical diagnosis by integrating visual perception with linguistic reasoning. Yet, existing medical chain-of-thought (CoT) models lack explicit mechanisms to represent and enforce causal reasoning, leaving them vulnerable to spurious correlations and limiting their clinical reliability. We pinpoint three core challenges in medical CoT reasoning: how to adaptively trigger causal correction, construct high-quality causal-spurious contrastive samples, and maintain causal consistency across reasoning trajectories. To address these challenges, we propose MedCausalX, an end-to-end framework explicitly models causal reasoning chains in medical VLMs. We first introduce the CRMed dataset providing fine-grained anatomical annotations, structured causal reasoning chains, and counterfactual variants that guide the learning of causal relationships beyond superficial correlations. Building upon CRMed, MedCausalX employs a two-stage adaptive reflection architecture equipped with $\langle$causal$\rangle$ and $\langle$verify$\rangle$ tokens, enabling the model to autonomously determine when and how to perform causal analysis and verification. Finally, a trajectory-level causal correction objective optimized through error-attributed reinforcement learning refines the reasoning chain, allowing the model to distinguish genuine causal dependencies from shortcut associations. Extensive experiments on multiple benchmarks show that MedCausalX consistently outperforms state-of-the-art methods, improving diagnostic consistency by +5.4 points, reducing hallucination by over 10 points, and attaining top spatial grounding IoU, thereby setting a new standard for causally grounded medical reasoning.

arXiv:2603.23149v1 Announce Type: new Abstract: Deploying safety-critical agents requires anticipating the consequences of actions before they are executed. While world models offer a paradigm for this proactive foresight, current approaches relying on visual simulation incur prohibitive latencies, often exceeding several seconds per step. In this work, we challenge the assumption that visual processing is necessary for failure prevention. We show that a trained policy's latent state, combined with its planned actions, already encodes sufficient information to anticipate action outcomes, making visual simulation redundant for failure prevention. To this end, we introduce DILLO (DIstiLLed Language-ActiOn World Model), a fast steering layer that shifts the paradigm from "simulate-then-act" to "describe-then-act." DILLO is trained via cross-modal distillation, where a privileged Vision Language Model teacher annotates offline trajectories and a latent-conditioned Large Language Model student learns to predict semantic outcomes. This creates a text-only inference path, bypassing heavy visual generation entirely, achieving a 14x speedup over baselines. Experiments on MetaWorld and LIBERO demonstrate that DILLO produces high-fidelity descriptions of the next state and is able to steer the policy, improving episode success rate by up to 15 pp and 9.3 pp on average across tasks.

arXiv:2603.23231v1 Announce Type: new Abstract: Empowering large language models with long-term memory is crucial for building agents that adapt to users' evolving needs. However, prior evaluations typically interleave preference-related dialogues with irrelevant conversations, reducing the task to needle-in-a-haystack retrieval while ignoring relationships between events that drive the evolution of user preferences. Such settings overlook a fundamental characteristic of real-world personalization: preferences emerge gradually and accumulate across interactions within noisy contexts. To bridge this gap, we introduce PERMA, a benchmark designed to evaluate persona consistency over time beyond static preference recall. Additionally, we incorporate (1) text variability and (2) linguistic alignment to simulate erratic user inputs and individual idiolects in real-world data. PERMA consists of temporally ordered interaction events spanning multiple sessions and domains, with preference-related queries inserted over time. We design both multiple-choice and interactive tasks to probe the model's understanding of persona along the interaction timeline. Experiments demonstrate that by linking related interactions, advanced memory systems can extract more precise preferences and reduce token consumption, outperforming traditional semantic retrieval of raw dialogues. Nevertheless, they still struggle to maintain a coherent persona across temporal depth and cross-domain interference, highlighting the need for more robust personalized memory management in agents. Our code and data are open-sourced at https://github.com/PolarisLiu1/PERMA.