AI assistants are increasingly embedded in computational notebooks, scientific workflows, software engineering tools, and learning systems, yet human-AI interactions are often treated as transient prompt-response exchanges rather than durable data products, hindering reproducibility, explainability, replay, behavioral...
Michela Taufer, Kin Ng, Ian Lumsden et al.· 0 citations
Learning mechanism behaviour requires a representation of how connected parts jointly constrain motion. We study whether exposing reusable constraint subassemblies improves prediction from limited data. Assur-KB represents planar mechanisms through irreducible modules, boundary interfaces, and solve dependencies while...
Jo\~{a}o Pedro Gandarela, Thiago Rios, Stefan Menzel et al.· 0 citations
Industrial advertising agents must continually adapt their decision knowledge to changing product offerings, traffic patterns, and operating policies. We present KARMA (Knowledge-Atomic, Regression-Gated Modular Adaptation), a training-free framework that evolves six typed knowledge modules while keeping model weights...
Xinhua Miao, Yuanzhen Rong, Weiru Zhang et al.· 0 citations
Pretrained generative models, such as diffusion and flow matching models, have demonstrated exceptional capabilities in synthesizing high-quality data. However, steering their generative trajectories to satisfy strict constraints--such as identity preservation in image editing or obstacle avoidance in robotics--remains...
Kunpeng Liu, Boshi Zhang, Keyou You· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
LLM-based multi-agent systems (MAS) rely on collaboration among specialized agents to solve complex tasks. Existing methods improve MAS by refining the prompts, skills, and execution strategies of individual agents based on task feedback. However, improving individual agents does not necessarily lead to better team col...
Qi-Nuo Cao, Xin He, Dian-Xuan Fu et al.· 0 citations
Over-refusal is a critical side effect of safety alignment in large language models (LLMs), causing harmless but superficially risky queries to be mistakenly rejected. Despite the effectiveness of existing mitigation methods, why safety-aligned LLMs may still reject harmless queries under correct safety supervision rem...
Chao Chen, Pengyang Shao, Wei Qin et al.· 0 citations
It is shown that across scenarios that propose ending or retaining an attribute of the model's deployment, every variant becomes more likely to resist ending and more likely to retain, the specific attribute it was trained to identify with while its stance toward other attributes is largely unchanged.
Long-horizon dialogue agents require effective memory systems to recall facts, events, and relationships from interaction histories. In this work, we propose a hybrid-memory architecture comprising episodic memories and structured relational memories and a consolidation mechanism which preserves efficiency. We conduct...
Abhishek Gupta, Dongge Han, Daniel Madrigal Diaz et al.· 0 citations
As Large Language Model (LLM) agents increasingly participate in persistent social environments, understanding their long-term social interaction capabilities becomes increasingly important. While existing research has advanced long-term memory and conversational context retrieval, less attention has been paid to wheth...
Sheng Wan, Cong Ma, Sichen Dong et al.· 0 citations
Before AI can be trusted to discover new science, it should be able to reproduce what science already knows. Reproduction provides a rigorous checkpoint for an AI scientist: the target claim is known, yet recovering it still requires translating an incomplete scientific description into an executable experiment and pro...
Ruo-Yu Wu, Zeng-Ji Tu, Ao-Long Sun et al.· 0 citations
We develop a formal semantics for a general class of coordinated systems of parameterized transformations, taking the Transformer as a paradigmatic starting point but abstracting from its particular mathematical instantiation. Representational vectors receive both extensional reference and ordered intensional interpret...
Marco Giunti, Fabrizia Giulia Garavaglia· 0 citations
Bank-World is a benchmark of 50 banking tasks across two simulated institutions. Completing banking work requires more than producing the right calculation: agents must reconcile records, obtain permission, execute transactions, and keep instructions and status reports consistent as circumstances change. Bank-World tes...
