arXiv:2601.19726v1 Announce Type: cross Abstract: The dual offensive and defensive utility of Large Language Models (LLMs) highlights a critical gap in AI security: the lack of unified frameworks for dynamic, iterative adversarial adaptation hardening. To bridge this gap, we propose the Red Team vs. Blue Team (RvB) framework, formulated as a training-free, sequential, imperfect-information game. […]
LabelKAN — Kolmogorov-Arnold Networks for Inter-Label Learning: Avian Community Learning
arXiv:2601.18818v1 Announce Type: new Abstract: Global biodiversity loss is accelerating, prompting international efforts such as the Kunming-Montreal Global Biodiversity Framework (GBF) and the United Nations Sustainable Development Goals to direct resources toward halting species declines. A key challenge in achieving this goal is having access to robust methodologies to understand where species occur and how […]
MATA: A Trainable Hierarchical Automaton System for Multi-Agent Visual Reasoning
arXiv:2601.19204v1 Announce Type: new Abstract: Recent vision-language models have strong perceptual ability but their implicit reasoning is hard to explain and easily generates hallucinations on complex queries. Compositional methods improve interpretability, but most rely on a single agent or hand-crafted pipeline and cannot decide when to collaborate across complementary agents or compete among overlapping ones. […]
Temporal Knowledge-Graph Memory in a Partially Observable Environment
arXiv:2408.05861v3 Announce Type: replace Abstract: Agents in partially observable environments require persistent memory to integrate observations over time. While KGs (knowledge graphs) provide a natural representation for such evolving state, existing benchmarks rarely expose agents to environments where both the world dynamics and the agent’s memory are explicitly graph-shaped. We introduce the Room Environment v3, […]
EnzyPGM: Pocket-conditioned Generative Model for Substrate-specific Enzyme Design
arXiv:2601.19205v1 Announce Type: new Abstract: Designing enzymes with substrate-binding pockets is a critical challenge in protein engineering, as catalytic activity depends on the precise interaction between pockets and substrates. Currently, generative models dominate functional protein design but cannot model pocket-substrate interactions, which limits the generation of enzymes with precise catalytic environments. To address this issue, […]
GOFAI meets Generative AI: Development of Expert Systems by means of Large Language Models
arXiv:2507.13550v2 Announce Type: replace Abstract: The development of large language models (LLMs) has successfully transformed knowledge-based systems such as open domain question nswering, which can automatically produce vast amounts of seemingly coherent information. Yet, those models have several disadvantages like hallucinations or confident generation of incorrect or unverifiable facts. In this paper, we introduce a […]
Beyond In-Domain Detection: SpikeScore for Cross-Domain Hallucination Detection
arXiv:2601.19245v1 Announce Type: new Abstract: Hallucination detection is critical for deploying large language models (LLMs) in real-world applications. Existing hallucination detection methods achieve strong performance when the training and test data come from the same domain, but they suffer from poor cross-domain generalization. In this paper, we study an important yet overlooked problem, termed generalizable […]
LLM-Generated Explanations Do Not Suffice for Ultra-Strong Machine Learning
arXiv:2509.00961v2 Announce Type: replace Abstract: Ultra Strong Machine Learning (USML) refers to symbolic learning systems that not only improve their own performance but can also teach their acquired knowledge to quantifiably improve human performance. We introduce LENS (Logic Programming Explanation via Neural Summarisation), a neuro-symbolic framework that combines symbolic program synthesis with large language models […]
GLOVE: Global Verifier for LLM Memory-Environment Realignment
arXiv:2601.19249v1 Announce Type: new Abstract: Most existing memory-enhanced Large Language Model (LLM) approaches implicitly assume that memory validity can be established either through external evaluators that provide task-specific success signals or through internal model cognition, such as reflection, for editing memory entries. However, these assumptions often break down in practical environments with dynamic drifts. We […]
Plan Then Retrieve: Reinforcement Learning-Guided Complex Reasoning over Knowledge Graphs
arXiv:2510.20691v3 Announce Type: replace Abstract: Knowledge Graph Question Answering aims to answer natural language questions by reasoning over structured knowledge graphs. While large language models have advanced KGQA through their strong reasoning capabilities, existing methods continue to struggle to fully exploit both the rich knowledge encoded in KGs and the reasoning capabilities of LLMs, particularly […]
PCEvo: Path-Consistent Molecular Representation via Virtual Evolutionary
arXiv:2601.19257v1 Announce Type: new Abstract: Molecular representation learning aims to learn vector embeddings that capture molecular structure and geometry, thereby enabling property prediction and downstream scientific applications. In many AI for science tasks, labeled data are expensive to obtain and therefore limited in availability. Under the few-shot setting, models trained with scarce supervision often learn […]
Rethinking the AI Scientist: Interactive Multi-Agent Workflows for Scientific Discovery
arXiv:2601.12542v2 Announce Type: replace Abstract: Artificial intelligence systems for scientific discovery have demonstrated remarkable potential, yet existing approaches remain largely proprietary and operate in batch-processing modes requiring hours per research cycle, precluding real-time researcher guidance. This paper introduces Deep Research, a multi-agent system enabling interactive scientific investigation with turnaround times measured in minutes. The architecture […]