arXiv:2602.04129v2 Announce Type: replace-cross Abstract: Heterogeneous multi-robot systems are increasingly used in long-horizon missions requiring coordinated planning across diverse capabilities. However, existing planning approaches struggle to construct accurate symbolic representations and maintain plan consistency in dynamic environments. Classical PDDL planners require manually crafted symbolic models, while LLM-based planners often ignore agent heterogeneity and environmental uncertainty. […]
Meta-LegNet: A Transferable and Interpretable Framework for Surface Adsorption Prediction via Self-Defined Adsorption-Environment Learning
arXiv:2605.04102v1 Announce Type: cross Abstract: A central challenge in computational catalysis is the identification of low-energy and chemically plausible adsorption configurations, as these directly affect adsorption energies, reaction pathways, and catalytic performance. Existing approaches generally rely on enumerating candidate adsorption sites followed by iterative refinement through density functional theory calculations or machine-learning-based relaxations. However, such […]
LOCARD: An Agentic Framework for Blockchain Forensics
arXiv:2604.04211v2 Announce Type: replace-cross Abstract: Blockchain forensics inherently involves dynamic and iterative investigations, while many existing approaches primarily model it through static inference pipelines. We propose a paradigm shift towards Agentic Blockchain Forensics (ABF), modeling forensic investigation as a sequential decision-making process. To instantiate this paradigm, we introduce LOCARD, the first agentic framework for blockchain […]
Governed Capability Evolution for Embodied Agents: Safe Upgrade, Compatibility Checking, and Runtime Rollback for Embodied Capability Modules
arXiv:2604.08059v3 Announce Type: replace-cross Abstract: Embodied agents are increasingly expected to improve over time by updating their executable capabilities rather than rewriting the agent itself. Prior work has separately studied modular capability packaging, capability evolution, and runtime governance. However, a key systems problem remains underexplored: once an embodied capability module evolves into a new version, […]
TNStream: Applying Tightest Neighbors to Micro-Clusters to Define Multi-Density Clusters in Streaming Data
arXiv:2505.00359v2 Announce Type: replace-cross Abstract: In data stream clustering, systematic theory of stream clustering algorithms remains relatively scarce. Recently, density-based methods have gained attention. However, existing algorithms struggle to simultaneously handle arbitrarily shaped, multi-density, high-dimensional data while maintaining strong outlier resistance. Clustering quality significantly deteriorates when data density varies complexly. This paper proposes a clustering […]
MalPurifier: Enhancing Android Malware Detection with Adversarial Purification against Evasion Attacks
arXiv:2312.06423v3 Announce Type: replace-cross Abstract: Machine learning (ML) has gained significant adoption in Android malware detection to address the escalating threats posed by the rapid proliferation of malware attacks. However, recent studies have revealed the inherent vulnerabilities of ML-based detection systems to evasion attacks. While efforts have been made to address this critical issue, many […]
Understanding Transformers through the Lens of Pavlovian Conditioning
arXiv:2508.08289v2 Announce Type: replace-cross Abstract: Transformer architectures have revolutionized artificial intelligence (AI) through their attention mechanisms, yet the computational principles underlying their success remain opaque. We present a novel theoretical framework that reinterprets the core computation of attention as Pavlovian conditioning. Our model finds a direct mathematical analogue in linear attention, which simplifies the analysis […]
ProFit: Leveraging High-Value Signals in SFT via Probability-Guided Token Selection
arXiv:2601.09195v3 Announce Type: replace-cross Abstract: Supervised fine-tuning (SFT) is a fundamental post-training strategy to align Large Language Models (LLMs) with human intent. However, traditional SFT often ignores the one-to-many nature of language by forcing alignment with a single reference answer, leading to the model overfitting to non-core expressions. Although our empirical analysis suggests that introducing […]
ProtDBench: A Unified Benchmark of Protein Binder Design and Evaluation
arXiv:2605.04118v1 Announce Type: new Abstract: Recent advances in de novo protein binder design have enabled increasing experimental validation, yet reported in silico metrics remain difficult to interpret or compare across studies due to non-standardized evaluation protocols. We introduce ProtDBench, a standardized and throughput-aware evaluation framework for protein binder design. ProtDBench defines unified benchmark tasks, evaluation […]
Tree-Conditioned Edit Flows for Ancestral Sequence Reconstruction
arXiv:2605.04119v1 Announce Type: new Abstract: Ancestral sequence reconstruction (ASR) aims to infer extinct protein sequences at internal nodes of a phylogenetic tree. Classical ASR methods are typically based on continuous-time Markov substitution models, but they treat sites largely independently and handle insertions and deletions only weakly or not at all. We introduce a tree-conditioned edit-flow […]
From Individual-Based Models to Macroscopic Dynamics of Antimicrobial Resistance
arXiv:2605.04117v1 Announce Type: new Abstract: We introduce and discuss a kinetic framework describing the time evolution of the statistical distributions of a population divided into the compartments of susceptible, infectious, recovered, and resistant in the presence of a microbial infection driven by susceptible infectious interactions. Our main objective is to quantify the impact of excessive […]
Regularized Centered Emphatic Temporal Difference Learning
arXiv:2605.04100v1 Announce Type: new Abstract: Off-policy temporal-difference (TD) learning with function approximation faces a structural tradeoff among stability, projection geometry, and variance control. Emphatic TD (ETD) improves the off-policy projection geometry through follow-on emphasis, but the follow-on trace can have high variance. We revisit this tradeoff through Bellman-error centering. Although centering naturally removes a common […]