4706 papers
This paper critiques the current limitations of alignment-focused safety cases for frontier AI by drawing on established methodologies from safety-critical industries to propose a more robust, defensible framework, illustrated through a case study on deceptive alignment and CBRN capabilities.
This paper proposes a multi-level meta-reinforcement learning framework that systematically compresses Markov decision processes into hierarchical structures with skill-based curriculum learning to decouple sub-tasks, reduce stochasticity, and enable efficient transfer of skills across different problems and levels.
This paper introduces a large language model (LLM) framework that automates the control and measurement of superconducting qubits by dynamically generating and invoking tools based on a knowledge base, thereby enabling rapid deployment of standard protocols and the flexible implementation of novel experimental procedures.
This paper introduces Test-Driven AI Agent Definition (TDAD), a methodology that compiles tool-using LLM agents from behavioral specifications by iteratively refining prompts against executable tests, thereby ensuring measurable behavioral compliance and robustness against silent regressions through mechanisms like hidden test splits and semantic mutation testing.
Scale-Plan is a scalable framework that leverages large language models to filter irrelevant perceptual information and construct compact, task-relevant representations from natural language instructions, thereby enabling efficient and reliable long-horizon planning for heterogeneous multi-robot teams while outperforming existing baselines on the new MAT2-THOR benchmark.
This paper empirically demonstrates that coverage-based retrieval metrics serve as reliable early indicators of information coverage in RAG-generated responses, particularly when retrieval objectives align with generation goals, across diverse text and multimodal benchmarks.
This paper introduces Fish Audio S2, an open-source text-to-speech system that leverages a multi-stage training pipeline to enable multi-speaker, multi-turn generation with natural-language instruction following, while providing production-ready weights and an efficient SGLang-based inference engine.
This paper introduces GenGNN, a modular message-passing framework that demonstrates expressive neural backbones like transformers are not strictly necessary for discrete graph generation, as diffusion models using GenGNN achieve competitive validity and superior inference speed on various datasets.
MASEval introduces a framework-agnostic library that shifts multi-agent evaluation from a model-centric to a system-centric approach, demonstrating through extensive experiments that implementation decisions regarding topology and orchestration impact performance as significantly as model selection.
The paper presents MuCTaL, a lightweight multi-cancer tumor localization framework trained on four cancer types that achieves high performance on training data and demonstrates generalization to unseen tumor types, enabling scalable deployment for digital pathology applications.
This paper introduces the LLM Delegate Protocol (LDP), an AI-native communication framework that enhances multi-agent system efficiency and governance by exposing model identity and reasoning profiles as first-class primitives, demonstrating significant reductions in latency and token usage alongside improved security and recovery capabilities in experimental evaluations.
This paper establishes that human preference for equally optimal combinatorial packing solutions is reliably driven by three quantifiable structural properties—alignment with greedy heuristics, simple within-bin composition, and ordered visual representation—thereby providing a concrete framework for designing interpretable algorithmic support systems.
This paper presents a controlled study using the Budget-Constrained Agentic Search (BCAS) framework to quantify how search depth, retrieval strategies, and completion budgets impact the accuracy and cost of Agentic RAG systems across six LLMs and three benchmarks, offering practical configuration guidelines for budget-constrained deployments.
This paper introduces FSbuHD, a novel feature selection model for hybrid information systems that addresses the computational and noise limitations of traditional fuzzy rough set theory by reformulating the problem as an optimization task based on combined object distances, demonstrating superior efficiency and effectiveness in both normal and optimistic states across UCI datasets.
This paper introduces NetDiffuser, a novel framework that leverages a feature categorization algorithm and diffusion models to generate natural adversarial examples that effectively deceive deep learning-based network intrusion detection systems while preserving traffic validity.
This paper introduces Transfer-Informed Betting (TIB), a novel method that combines betting-based confidence sequences with cross-domain transfer learning to achieve tighter, data-efficient risk guarantees for selective prediction, demonstrating significant coverage improvements over existing bounds across multiple benchmarks and applications.
FedLECC is a lightweight client selection strategy for federated learning under non-IID data that groups clients by label-distribution similarity and prioritizes those with higher local loss, thereby significantly improving test accuracy while reducing communication rounds and overhead.
This paper introduces a fully differentiable approach to discovering Strong Lottery Tickets by employing continuously relaxed Bernoulli gates to optimize sparsity via gradient descent on frozen weights, achieving significantly higher sparsity with minimal accuracy loss compared to existing non-differentiable methods like edge-popup.
This paper argues that citation visibility in generative search should be treated as a stochastic distribution requiring uncertainty estimates rather than a fixed value, demonstrating through empirical analysis of multiple AI platforms that single-run measurements are misleadingly precise and that robust statistical sampling is essential for accurate domain performance assessment.
This paper introduces a novel framework utilizing vision-language foundation models (Gemma 3 and Qwen3-VL) to automatically generate JSON simulation configurations for digital twin agriculture by interpreting drone imagery, demonstrating their potential to scale functional-structural plant modeling while highlighting current limitations in visual reasoning and reliance on contextual priors.