Variational inference with normalizing flows provides a flexible posterior approximation for Bayesian model calibration, but struggles when the posterior has several modes separated by regions of low probability mass. We study this behavior in a two-parameter twin experiment and regularize the variational objective. Un...
In finance, the answer that matters is usually the current one: prices, rates, and disclosures hold only as of a given day, so retrieving up-to-date facts is a core capability of a financial agent. Yet most financial benchmarks overlook timeliness. They fix each answer at annotation time, so the gold goes stale as mark...
Sinuo Wang, Wentao Zhao, Jiacheng Lu et al.· 0 citations
Scaling supervised training for working agents requires diverse professional tasks that yield reliable expert demonstrations. However, missing or inconsistent task information can obstruct teacher execution and weaken the resulting supervision. We propose WorkFactory, a scalable framework for constructing coherent and...
Ziyang Zeng, Tingyang Chen, Jia Deng et al.· 0 citations
The resulting knowledge model provides a machine-actionable foundation for querying, consistency checking, and mechanistic explanation of SFE processes, and establishes a knowledge layer that could support future ontology-grounded AI reasoning, a direction this paper motivates but does not evaluate.
Thomas Pallet, Mario Lezoche, Gia Leone et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Scientific reasoning in specialized engineering fields depends on knowledge scattered across the literature, often proprietary and absent from frontier LLM training data. In such domains, frontier models tend to give generic answers. Knowledge graphs (KGs) can ground LLM reasoning. Because a graph is too large to provi...
Background and purpose: Radiotherapy planning agents based on large language models (LLMs) decide when to submit a plan or request review but are evaluated mainly by dose. This study developed OpenGray, a benchmark of planning tasks with known correct decisions. Materials and methods: OpenGray adds tasks with known ans...
Restricting chain-of-thought (CoT) faithfulness evaluation to correctly answered instances changes the population being measured. We study this selection step in a seven-variable structural causal model and derive the exact observed gap $\Delta = \operatorname{Cov}(A, C)/P(C=1)$. The model distinguishes difficulty conf...
Efficient quantum circuit compilation is challenging for quantum computers, where limited qubit connectivity can introduce substantial overhead in the implementation of logical operations. Recent AI-assisted synthesis methods have shown considerable potential for reducing circuit complexity, but their role in uncoverin...
Reinforcement learning with verifiable rewards (RLVR) has shown strong empirical gains in improving the reasoning ability of large language models (LLMs) on tasks such as mathematics and programming. However, recent studies have shown that RLVR rollouts often collapse onto a narrow set of reasoning trajectories, limiti...
Bo Yang, Zishuai Zhang, Weihua Li et al.· 0 citations
Retrieval-augmented generation (RAG) systems ground large language models (LLMs) by retrieving external evidence and conditioning generation on the retrieved context. Although dense retrieval is effective for local semantic matching, independently ranked retrieval can return redundant passages, miss cross-chunk depende...
Z. Sahinoglu, A. Mohammed, Buse Yaren Kazangirler et al.· 0 citations
Large language model (LLM) agents are extending agent-mediated commerce on the Web from shopping for consumers to operating businesses for sellers. In online-to-offline (O2O) commerce, decisions are issued through Web-based platforms but realized through costly physical execution. Evaluating such agents requires going...
Qiming Shi, Yikun Li, Beidi Luan et al.· 0 citations
Proactive Memory (ProactMem), which organizes history into recent events, temporal trajectories, and behavioral regularities, is proposed, which organizes history into recent events, temporal trajectories, and behavioral regularities.
Jin-Yang Li, Zi-Chuan Fu, Xian Wu et al.· 0 citations
