February 2026

arXiv:2602.18450v1 Announce Type: new Abstract: Multi-agent language systems can exhibit a failure mode where a shared dominant context progressively absorbs individual semantics, yielding near-uniform behavior across agents. We study this effect under the name Asymptotic Semantic Collapse in Hierarchical Optimization. In a closed linguistic setting with a Dominant Anchor Node whose semantic state has effectively infinite inertia, we show that repeated interactions with Peripheral Agent Nodes drive an asymptotic alignment that minimizes a global loss. We model semantic […]

Ver mais

arXiv:2602.18449v1 Announce Type: new Abstract: We propose a diffusion-based framework for prompt optimization that leverages Diffusion Language Models (DLMs) to iteratively refine system prompts through masked denoising. By conditioning on interaction traces, including user queries, model responses, and optional feedback, our method enables flexible, span-level prompt updates without requiring gradient access or modifying the downstream language model. Across diverse benchmarks (e.g., $tau$-bench, SST-2, SST-5), DLM-optimized prompts consistently improve the performance of a frozen target LLM (e.g., GPT-4o-mini). We […]

Ver mais

arXiv:2602.18448v1 Announce Type: new Abstract: Administrative phone tasks drain roughly 1 trillion USD annually from U.S. healthcare, with over 500 million insurance-benefit verification calls manually handled in 2024. We introduce INSURE-Dial, to our knowledge the first public benchmark for developing and assessing compliance-aware voice agents for phase-aware call auditing with span-based compliance verification. The corpus includes 50 de-identified, AI-initiated calls with live insurance representatives (mean 71 turns/call) and 1,000 synthetically generated calls that mirror the same workflow. All […]

Ver mais

arXiv:2602.18447v1 Announce Type: new Abstract: Chain-of-Thought reasoning significantly improves the performance of large language models on complex tasks, but incurs high inference latency due to long generation traces. Step-level speculative reasoning aims to mitigate this cost, yet existing approaches face a long-standing trade-off among accuracy, inference speed, and resource efficiency. We propose ConfSpec, a confidence-gated cascaded verification framework that resolves this trade-off. Our key insight is an asymmetry between generation and verification: while generating a correct reasoning step […]

Ver mais

arXiv:2602.18446v1 Announce Type: new Abstract: Users increasingly rely on Large Language Models (LLMs) for Deep Research, using them to synthesize diverse sources into structured reports that support understanding and action. In this context, the practical reliability of such reports hinges on logical quality: whether the report’s claims and arguments are explicitly supported and can be trusted as a basis for downstream use, rather than merely appearing fluent or informative. However, current evaluation frameworks largely overlook this requirement. To […]

Ver mais

arXiv:2602.18445v1 Announce Type: new Abstract: The advancement of artificial intelligence has transformed user interface design by enabling adaptive and personalized systems. Alongside these benefits, AI driven interfaces have also enabled the emergence of dark patterns, which are manipulative design strategies that influence user behavior for financial or business gain. As AI systems learn from data that already contains deceptive practices, they can replicate and optimize these patterns in increasingly subtle and personalized ways. This paper examines AI generated […]

Ver mais

arXiv:2602.18444v1 Announce Type: new Abstract: Conversational AI has significant potential in the healthcare sector, but many existing systems fall short in emotional intelligence, fairness, and politeness, which are essential for building patient trust. This gap reduces the effectiveness of digital health solutions and can increase user anxiety. This study addresses the challenge of integrating ethical communication principles by designing and evaluating LunaAI, a healthcare chatbot prototype. Using a user-centered design approach informed by a structured literature review, we […]

Ver mais

arXiv:2602.18443v1 Announce Type: new Abstract: Psychosocial online counselling frequently encounters generic subject lines that impede efficient case prioritisation. This study evaluates eleven large language models generating six-word subject lines for German counselling emails through hierarchical assessment – first categorising outputs, then ranking within categories to enable manageable evaluation. Nine assessors (counselling professionals and AI systems) enable analysis via Krippendorff’s $alpha$, Spearman’s $rho$, Pearson’s $r$ and Kendall’s $tau$. Results reveal performance trade-offs between proprietary services and privacy-preserving open-source alternatives, […]

Ver mais

arXiv:2602.18439v1 Announce Type: new Abstract: Vision-language models like CLIP have demonstrated remarkable zero-shot capabilities, yet their adaptation to federated learning scenarios presents significant challenges, particularly regarding generalization to unseen classes. The original FedTPG paper cite{Qiu2024} addresses this limitation by introducing a text driven prompt generation network that dynamically creates prompts conditioned on class names, enabling better cross-class generalization in federated settings. In this work, we present a faithful replication study of FedTPG, evaluating the pre-trained model on six […]

Ver mais

arXiv:2602.18438v1 Announce Type: new Abstract: Efficient resource (re-)allocation is a critical challenge in optimizing productivity and sustainability within multi-party supply networks. In this work, we introduce the textsc{Red-Blue Reinforcement} (R-BR) problem, where a service provider under budgetary constraints must minimize client reallocations to reduce the required number of servers they should maintain by a specified amount. We conduct a systematic algorithmic study, providing three exact algorithms that scale well as the input grows (FPT), which could prove useful […]

Ver mais