arXiv:2601.18924v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly relied upon for complex workflows, yet their ability to maintain flow of instructions remains underexplored. Existing benchmarks conflate task complexity with structural ordering, making it difficult to isolate the impact of prompt topology on performance. We introduce RIFT, Reordered Instruction Following Testbed, to assess […]
Cross-Domain Offshore Wind Power Forecasting: Transfer Learning Through Meteorological Clusters
arXiv:2601.19674v1 Announce Type: cross Abstract: Ambitious decarbonisation targets are catalysing growth in orders of new offshore wind farms. For these newly commissioned plants to run, accurate power forecasts are needed from the onset. These allow grid stability, good reserve management and efficient energy trading. Despite machine learning models having strong performances, they tend to require […]
Explainable Uncertainty Quantification for Wastewater Treatment Energy Prediction via Interval Type-2 Neuro-Fuzzy System
arXiv:2601.18897v1 Announce Type: new Abstract: Wastewater treatment plants consume 1-3% of global electricity, making accurate energy forecasting critical for operational optimization and sustainability. While machine learning models provide point predictions, they lack explainable uncertainty quantification essential for risk-aware decision-making in safety-critical infrastructure. This study develops an Interval Type-2 Adaptive Neuro-Fuzzy Inference System (IT2-ANFIS) that generates […]
AgenticSCR: An Autonomous Agentic Secure Code Review for Immature Vulnerabilities Detection
arXiv:2601.19138v1 Announce Type: cross Abstract: Secure code review is critical at the pre-commit stage, where vulnerabilities must be caught early under tight latency and limited-context constraints. Existing SAST-based checks are noisy and often miss immature, context-dependent vulnerabilities, while standalone Large Language Models (LLMs) are constrained by context windows and lack explicit tool use. Agentic AI, […]
LLM Driven Design of Continuous Optimization Problems with Controllable High-level Properties
arXiv:2601.18846v1 Announce Type: new Abstract: Benchmarking in continuous black-box optimisation is hindered by the limited structural diversity of existing test suites such as BBOB. We explore whether large language models embedded in an evolutionary loop can be used to design optimisation problems with clearly defined high-level landscape characteristics. Using the LLaMEA framework, we guide an […]
Agentic Business Process Management Systems
arXiv:2601.18833v1 Announce Type: new Abstract: Since the early 90s, the evolution of the Business Process Management (BPM) discipline has been punctuated by successive waves of automation technologies. Some of these technologies enable the automation of individual tasks, while others focus on orchestrating the execution of end-to-end processes. The rise of Generative and Agentic Artificial Intelligence […]
“Not in My Backyard”: LLMs Uncover Online and Offline Social Biases Against Homelessnes
arXiv:2508.13187v2 Announce Type: replace-cross Abstract: Homelessness is a persistent social challenge, impacting millions worldwide. Over 876,000 people experienced homelessness (PEH) in the U.S. in 2025. Social bias is a significant barrier to alleviation, shaping public perception and influencing policymaking. Given that online textual media and offline city council discourse reflect and influence part of public […]
Smooth embeddings in contracting recurrent networks driven by regular dynamics: A synthesis for neural representation
arXiv:2601.19019v1 Announce Type: new Abstract: Recurrent neural networks trained for time-series prediction often develop latent trajectories that preserve qualitative structure of the dynamical systems generating their inputs. Recent empirical work has documented topology-preserving latent organization in trained recurrent models, and recent theoretical results in reservoir computing establish conditions under which the synchronization map is an […]
One Token Is Enough: Improving Diffusion Language Models with a Sink Token
arXiv:2601.19657v1 Announce Type: cross Abstract: Diffusion Language Models (DLMs) have emerged as a compelling alternative to autoregressive approaches, enabling parallel text generation with competitive performance. Despite these advantages, there is a critical instability in DLMs: the moving sink phenomenon. Our analysis indicates that sink tokens exhibit low-norm representations in the Transformer’s value space, and that […]
Hyperbolic Additive Margin Softmax with Hierarchical Information for Speaker Verification
arXiv:2601.19709v1 Announce Type: cross Abstract: Speaker embedding learning based on Euclidean space has achieved significant progress, but it is still insufficient in modeling hierarchical information within speaker features. Hyperbolic space, with its negative curvature geometric properties, can efficiently represent hierarchical information within a finite volume, making it more suitable for the feature distribution of speaker […]
1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning
arXiv:2508.07667v2 Announce Type: replace Abstract: Addressing contextual privacy concerns remains challenging in interactive settings where large language models (LLMs) process information from multiple sources (e.g., summarizing meetings with private and public information). We introduce a multi-agent framework that decomposes privacy reasoning into specialized subtasks (extraction, classification), reducing the information load on any single agent while […]
Exploring Weaknesses in Function Call Models via Reinforcement Learning: An Adversarial Data Augmentation Approach
arXiv:2601.19122v1 Announce Type: new Abstract: Function call capabilities have become crucial for Large Language Models (LLMs), enabling them to interact more effectively with external tools and APIs. Existing methods for improving the function call capabilities of LLMs rely on data obtained either through manual annotation or automated generation by models, and use this data to […]