arXiv AI
Jun 30
When Models Know When They Do Not Know: Calibration, Cascading, and Cleaning
arXiv:2601. 07965v2 Announce Type: replace Abstract: When a model knows when it does not know, many possibilities emerge.
Benchmarks and evaluation
Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv AI
Jun 30
StarDojo: Benchmarking Open-Ended Behaviors of Agentic Multimodal LLMs in Production-Living Simulations with Stardew Valley
arXiv:2507. 07445v3 Announce Type: replace Abstract: Autonomous agents navigating human society must master both production activities and social interactions, yet existing benchmarks rarely evaluate these skills simultaneously.
arXiv AI
Jun 30
Does Role Specialization Matter for Explanation Faithfulness in Mixture-of-Experts?
arXiv:2606. 29613v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures have recently been extended with role-based mechanisms for interpretability.
arXiv AI
Jun 30
GROW$^2$: Grounding Which and Where for Robot Tool Use
arXiv:2606. 30632v1 Announce Type: cross Abstract: Can the robot use a plate to cut a cake if no knife is available?
arXiv Machine Learning
Jun 30
Blackknife: Hard-Label Query-Limited Black-Box Attacks on Heterogeneous Graph Neural Networks
arXiv:2606. 29240v1 Announce Type: new Abstract: Heterogeneous graph neural networks (HGNNs) have achieved strong performance in modeling complex graph-structured data with multiple node and relation types.
arXiv Machine Learning
Jun 30
CAREBench: A Child-Safety Risk Benchmark for Language Models
arXiv:2606. 29685v1 Announce Type: new Abstract: How can we evaluate whether frontier AI systems recognize child-safety risks before they escalate into explicit harm?
arXiv AI
Jun 30
SABER-Math: Automated Benchmark for Information Retrieval Evaluation in Mathematics
arXiv:2606. 29894v1 Announce Type: cross Abstract: As agentic AI systems tackle more complex mathematical tasks, they increasingly rely on information retrieval (IR) to search problem databases, theorem libraries, and educational resources.
arXiv AI
Jun 30
Few-Shot Domain Incremental Learning via Continual Vision-Language Consolidation
arXiv:2606. 30190v1 Announce Type: cross Abstract: Existing domain-incremental learning (DIL) strategies call for massive amounts of data to adapt to new domains and suffer from the overfitting problem in the case of data scarcity.
arXiv AI
Jun 30
Self-Organized Conformal Prediction: Reducing Regional Coverage Gaps with Unsupervised Group Discovery
arXiv:2606. 29403v1 Announce Type: cross Abstract: Conformal prediction guarantees marginal coverage, but pooled calibration averages over heterogeneous regions and can mask regional undercoverage in safety-critical subgroups.
arXiv AI
Jun 30
Hierarchical Experimentalist Agents
arXiv:2606. 29315v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to take actions in the real world and support human decision-making, yet most agents rely on parametric knowledge, fixed post-training data, retrieval, or search.
arXiv Machine Learning
Jun 30
Never Skip a Batch: Dense Learning of Temporal GNNs via Adaptive Pseudo-Supervision
arXiv:2505. 12526v2 Announce Type: replace Abstract: Temporal graph networks suffer from irregular supervision in realworld dynamic graphs, as most minibatches contain few labeled events.
arXiv Machine Learning
Jun 30
CADS: Conformal Adaptive Decision System for Cost-Efficient Image Classification
arXiv:2605. 16401v2 Announce Type: replace-cross Abstract: While high-capacity AI models have advanced state-of-the-art performance, their practical deployment is often hindered by high inference costs, environmental impact, and a "one-size-fits-all" approach that ignores varying sample complexity.
arXiv AI
Jun 30
ADEPT: An Entropy-Driven Dual-Strategy Agent for Interactive Video Retrieval
arXiv:2606. 28326v1 Announce Type: cross Abstract: This research aims to solve the challenge of video retrieval from massive datasets, caused by ambiguous user queries.
arXiv AI
Jun 30
HippoSpark: An On-Demand Experience System for LLM Reasoning
arXiv:2606. 29929v1 Announce Type: new Abstract: Distilling historical trajectories into reusable experience to enhance future problem-solving has become a focal point of recent LLM research.
arXiv AI
Jun 30
FD$^2$: A Dedicated Framework for Fine-Grained Dataset Distillation
arXiv:2603. 25144v2 Announce Type: replace-cross Abstract: Dataset distillation (DD) compresses a large training set into a small synthetic set, reducing storage and training cost, and has shown strong results on general benchmarks.
arXiv Machine Learning
Jun 30
Solver-Integrated Adversarial Attacking and Training of Neural Operators
arXiv:2510. 18989v2 Announce Type: replace Abstract: Neural operators are commonly utilized as fast surrogates for numerical solvers in PDE problems, mapping input functions to solution functions.
arXiv Machine Learning
Jun 30
Position: RL Researchers Need to Distinguish Between Solving Simulators and Using Simulators as a Proxy
arXiv:2606. 28433v1 Announce Type: new Abstract: One goal in reinforcement learning (RL) research is to understand general-purpose sequential decision-making, using benchmark simulators as a proxy for learning in deployment settings.
arXiv AI
Jun 30
CaveAgent: Transforming LLMs into Stateful Runtime Operators
arXiv:2601. 01569v4 Announce Type: replace Abstract: LLM-based agents are increasingly capable of complex task execution, yet current agentic systems remain constrained by text-centric paradigms that struggle with long-horizon tasks due to fragile multi-turn dependencies and context drift.
arXiv AI
Jun 30
On the Spectral Structure and Objective Equivalence of Orthogonal Multilabel Fisher Discriminants
arXiv:2605. 03283v2 Announce Type: replace-cross Abstract: We provide a unified theoretical analysis of Linear Discriminant Analysis with simultaneous multilabel scatter matrix formulations and Stiefel orthogonality constraints.
arXiv Machine Learning
Jun 30
Vision-driven Preference Synthesis for Mitigating Hallucinations in VLMs
arXiv:2606. 28401v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have shown strong performance in visual understanding, yet they still suffer from hallucinations, generating content that is not grounded in the image.