arXiv:2602.00104v2 Announce Type: replace-cross Abstract: Vision-centric retrieval for VQA requires retrieving images to supply missing visual cues and integrating them into the reasoning process. However, selecting the right images and integrating them effectively into the model’s reasoning remains challenging.To address this challenge, we propose R3G, a modular Reasoning-Retrieval-Reranking framework.It first produces a brief reasoning plan […]
From Large Language Model Predicates to Logic Tensor Networks: Neurosymbolic Offer Validation in Regulated Procurement
arXiv:2604.05539v1 Announce Type: new Abstract: We present a neurosymbolic approach, i.e., combining symbolic and subsymbolic artificial intelligence, to validating offer documents in regulated public institutions. We employ a language model to extract information and then aggregate with an LTN (Logic Tensor Network) to make an auditable decision. In regulated public institutions, decisions must be made […]
Label Effects: Shared Heuristic Reliance in Trust Assessment by Humans and LLM-as-a-Judge
arXiv:2604.05593v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as automated evaluators (LLM-as-a-Judge). This work challenges its reliability by showing that trust judgments by LLMs are biased by disclosed source labels. Using a counterfactual design, we find that both humans and LLM judges assign higher trust to information labeled as human-authored than […]
Inventory of the 12 007 Low-Dimensional Pseudo-Boolean Landscapes Invariant to Rank, Translation, and Rotation
arXiv:2604.05530v1 Announce Type: new Abstract: Many randomized optimization algorithms are rank-invariant, relying solely on the relative ordering of solutions rather than absolute fitness values. We introduce a stronger notion of rank landscape invariance: two problems are equivalent if their ranking, but also their neighborhood structure and symmetries (translation and rotation), induce identical landscapes. This motivates […]
Cross-Domain Few-Shot Learning for Hyperspectral Image Classification Based on Mixup Foundation Model
arXiv:2601.22581v2 Announce Type: replace-cross Abstract: Although cross-domain few-shot learning (CDFSL) for hyper-spectral image (HSI) classification has attracted significant research interest, existing works often rely on an unrealistic data augmentation procedure in the form of external noise to enlarge the sample size, thus greatly simplifying the issue of data scarcity. They involve a large number of […]
LUDOBENCH: Evaluating LLM Behavioural Decision-Making Through Spot-Based Board Game Scenarios in Ludo
arXiv:2604.05681v1 Announce Type: new Abstract: We introduce LudoBench, a benchmark for evaluating LLM strategic reasoning in Ludo, a stochastic multi-agent board game whose dice mechanics, piece capture, safe-square navigation, and home-path progression introduce meaningful planning complexity. LudoBench comprises 480 handcrafted spot scenarios across 12 behaviorally distinct decision categories, each isolating a specific strategic choice. We […]
GenomeQA: Benchmarking General Large Language Models for Genome Sequence Understanding
arXiv:2604.05774v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly adopted as conversational assistants in genomics, where they are mainly used to reason over biological knowledge, annotations, and analysis outputs through natural language interfaces. However, existing benchmarks either focus on specialized DNA models trained for sequence prediction or evaluate biological knowledge using text-only questions, […]
SignalClaw: LLM-Guided Evolutionary Synthesis of Interpretable Traffic Signal Control Skills
arXiv:2604.05535v1 Announce Type: new Abstract: Traffic signal control TSC requires strategies that are both effective and interpretable for deployment, yet reinforcement learning produces opaque neural policies while program synthesis depends on restrictive domain-specific languages. We present SIGNALCLAW, a framework that uses large language models LLMs as evolutionary skill generators to synthesize and refine interpretable control […]
Marangoni-Driven Redistribution and Activity of Piezo1 Molecules in Epithelial and Cancer Cells
arXiv:2604.05556v1 Announce Type: new Abstract: The activity and distribution of Piezo1 molecules, along with the maturity and strength of focal adhesions (FAs), serve as critical factors influencing cell mechanosensing. Notably, migrating epithelial cells and mesenchymal-like cancer cells exhibit significantly different behaviors regarding these elements. In cancer cells, Piezo1 molecules are distributed uniformly, while in epithelial […]
PECKER: A Precisely Efficient Critical Knowledge Erasure Recipe For Machine Unlearning in Diffusion Models
arXiv:2604.05634v1 Announce Type: new Abstract: Machine unlearning (MU) has become a critical technique for GenAI models’ safe and compliant operation. While existing MU methods are effective, most impose prohibitive training time and computational overhead. Our analysis suggests the root cause lies in poorly directed gradient updates, which reduce training efficiency and destabilize convergence. To mitigate […]
Can Large Language Models Reinvent Foundational Algorithms?
arXiv:2604.05716v1 Announce Type: new Abstract: LLMs have shown strong potential to advance scientific discovery. Whether they possess the capacity for foundational innovation, however, remains an open question. In this work, we focus on a prerequisite for foundational innovation: can LLMs reinvent foundational algorithms in computer science? Our textitUnlearn-and-Reinvent pipeline applies LLM unlearning to remove a […]
Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents
arXiv:2604.05808v1 Announce Type: new Abstract: Large language model (LLM) agents have demonstrated strong capabilities in complex interactive decision-making tasks. However, existing LLM agents typically rely on increasingly long interaction histories, resulting in high computational cost and limited scalability. In this paper, we propose STEP-HRL, a hierarchical reinforcement learning (HRL) framework that enables step-level learning by […]