arXiv:2605.13902v1 Announce Type: new Abstract: Breast cancer incidence rises with age and peaks across the menopausal transition, yet why some postmenopausal lobules persist, and why that persistence predicts cancer risk, remains unresolved. Incomplete age-related lobular involution is one of the strongest tissue-level predictors of subsequent breast cancer, but it is still commonly viewed as passive […]
BEAM: Binary Expert Activation Masking for Dynamic Routing in MoE
arXiv:2605.14438v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures enhance the efficiency of large language models by activating only a subset of experts per token. However, standard MoE employs a fixed Top-K routing strategy, leading to redundant computation and suboptimal inference latency. Existing acceleration methods either require costly retraining with architectural changes or suffer from severe […]
Coding Agent Is Good As World Simulator
arXiv:2605.14398v1 Announce Type: new Abstract: World models have emerged as a powerful paradigm for building interactive simulation environments, with recent video-based approaches demonstrating impressive progress in generating visually plausible dynamics. However, because these models typically infer dynamics from video and represent them in latent states, they do not explicitly enforce physical constraints. As a result, […]
On Strong Equivalence Notions in Logic Programming and Abstract Argumentation
arXiv:2605.14721v1 Announce Type: new Abstract: Strong equivalence between knowledge bases ensures the possibility of replacing one with the other without affecting reasoning outcomes, in any given context. This makes it a crucial property in nonmonotonic formalisms. In particular, the fields of logic programming and abstract argumentation provide primary examples in which this property has been […]
MetaGEM: Bottom-Up Reconstruction of Genome-Scale Metabolic Networks via Deep Enzyme-Metabolite Anchoring
arXiv:2605.14812v1 Announce Type: new Abstract: Genome-scale metabolic models (GEMs) are essential tools for systems biology and rational chassis design, but conventional top-down reconstruction depends heavily on sequence homology and often leaves unknown enzymes and metabolic dark matter unresolved. Direct reconstruction from metabolomics is also difficult because mapping observed metabolites to reactions is an ill-posed inverse […]
Cattle Trade: A Multi-Agent Benchmark for LLM Bluffing, Bidding, and Bargaining
arXiv:2605.14537v1 Announce Type: new Abstract: We introduce textscCattle Trade, a multi-agent benchmark for evaluating large language models (LLMs) as agents in strategic reasoning under imperfect information, adversarial interaction, and resource constraints. The benchmark combines auctions, hidden-offer trade challenges (TCs), bargaining, bluffing, opponent modeling, and resource allocation within a single long-horizon game lasting 50–60 turns. Unlike […]
SliceGraph: Mapping Process Isomers in Multi-Run Chain-of-Thought Reasoning
arXiv:2605.14619v1 Announce Type: new Abstract: Multi-run chain-of-thought reasoning is usually collapsed to final-answer aggregates, which discard howsampled trajectories share, split, and rejoin through intermediate computation. We propose SliceGraph, a post-hoc problem-model-cell graph built by mutual-kNN over sparse activation-key Jaccard similarity between CoT slices, and treat it as a measurement object for process geometry rather than […]
Deepchecks: Evaluating Retrieval-Augmented Generation (RAG)
arXiv:2605.14488v1 Announce Type: new Abstract: Large Language Models (LLMs) augmented with Retrieval-Augmented Generation (RAG) techniques are revolutionizing applications across multiple domains, such as healthcare, finance, and customer service. Despite their potential, evaluating RAG systems remains a complex challenge due to the stochastic nature of generated outputs and the intricate interplay between retrieval and generation components. […]
PyCSP3-Scheduling: A Scheduling Extension for PyCSP3
arXiv:2605.14559v1 Announce Type: new Abstract: PyCSP$^3$ provides a productive way to build constraint models for solving combinatorial constrained problems and export them to XCSP$^3$, preserving a complete separation between modeling and solving. However, it lacks native support for scheduling abstractions such as interval variables, sequence variables, and resource functions. As a result, scheduling models must […]
Monitoring Data-aware Temporal Properties (Extended Version)
arXiv:2605.14666v1 Announce Type: new Abstract: Dynamic systems in AI are often complex and heterogeneous, so that an internal specification is not accessible and verification techniques such as model checking are not applicable. Monitoring is in such cases an attractive alternative, as it evaluates desirable properties along traces generated by an unknown dynamic system. In this […]
AI Outperforms Humans in Personalized Image Aesthetics Assessment via LLM-Based Interviews and Semantic Feature Extraction
arXiv:2605.14761v1 Announce Type: new Abstract: Accurately predicting individual aesthetic evaluation for images is a fundamental challenge for AI. Various deep learning (DL)-based models have been proposed for this task, training on image evaluation data to extract objective low-level features. However, aesthetic preferences are inherently subjective and individual-dependent. Accurate prediction thus requires the extraction of high-level […]
Holistic Evaluation and Failure Diagnosis of AI Agents
arXiv:2605.14865v1 Announce Type: new Abstract: AI agents execute complex multi-step processes, but current evaluation falls short: outcome metrics report success or failure without explaining why, and process-level approaches struggle to connect failure types to their precise locations within long, structured traces. We present a holistic agent evaluation framework that pairs top-down agent-level diagnosis with bottom-up […]