arXiv:2603.17244v1 Announce Type: new Abstract: While individual components for AI agent memory exist in prior systems, their architectural synthesis and formal grounding remain underexplored. We present Kumiho, a graph-native cognitive memory architecture grounded in formal belief revision semantics. The structural primitives required for cognitive memory — immutable revisions, mutable tag pointers, typed dependency edges, URI-based […]
Efficient LLM Safety Evaluation through Multi-Agent Debate
arXiv:2511.06396v3 Announce Type: replace Abstract: Safety evaluation of large language models (LLMs) increasingly relies on LLM-as-a-judge pipelines, but strong judges can still be expensive to use at scale. We study whether structured multi-agent debate can improve judge reliability while keeping backbone size and cost modest. To do so, we introduce HAJailBench, a human-annotated jailbreak benchmark […]
Integrative modelling of protein-glycan interactions with HADDOCK3
arXiv:2603.17251v1 Announce Type: new Abstract: Glycans are structurally diverse and flexible biomolecules that play key roles in many biological processes. Their conformational variability makes the modeling of their interactions with proteins particularly challenging. This chapter presents a step-by-step protocol for modeling protein-glycan interactions using HADDOCK3, an integrative modeling platform that supports the inclusion of experimental […]
TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas
arXiv:2603.16448v2 Announce Type: replace Abstract: Text-to-SQL parsing has achieved remarkable progress under the Full Schema Assumption. However, this premise fails in real-world enterprise environments where databases contain hundreds of tables with massive noisy metadata. Rather than injecting the full schema upfront, an agent must actively identify and verify only the relevant subset, giving rise to […]
Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations
arXiv:2603.17305v1 Announce Type: new Abstract: We propose CRAFT, a red-teaming alignment framework that leverages model reasoning capabilities and hidden representations to improve robustness against jailbreak attacks. Unlike prior defenses that operate primarily at the output level, CRAFT aligns large reasoning models to generate safety-aware reasoning traces by explicitly optimizing objectives defined over the hidden state […]
CMADiff: Cross-Modal Aligned Diffusion for Controllable Protein Generation
arXiv:2503.21450v2 Announce Type: replace-cross Abstract: AI-assisted protein design has emerged as a critical tool for advancing biotechnology, as deep generative models have demonstrated their reliability in this domain. However, most existing models primarily utilize protein sequence or structural data for training, neglecting the physicochemical properties of proteins.Moreover, they are deficient to control the generation of […]
LLM NL2SQL Robustness: Surface Noise vs. Linguistic Variation in Traditional and Agentic Settings
arXiv:2603.17017v1 Announce Type: cross Abstract: Robustness evaluation for Natural Language to SQL (NL2SQL) systems is essential because real-world database environments are dynamic, noisy, and continuously evolving, whereas conventional benchmark evaluations typically assume static schemas and well-formed user inputs. In this work, we introduce a robustness evaluation benchmark containing approximately ten types of perturbations and conduct […]
Knowledge Localization in Mixture-of-Experts LLMs Using Cross-Lingual Inconsistency
arXiv:2603.17102v1 Announce Type: cross Abstract: Modern LLMs continue to exhibit significant variance in behavior across languages, such as being able to recall factual information in some languages but not others. While typically studied as a problem to be mitigated, in this work, we propose leveraging this cross-lingual inconsistency as a tool for interpretability in mixture-of-experts […]
InfoDensity: Rewarding Information-Dense Traces for Efficient Reasoning
arXiv:2603.17310v1 Announce Type: new Abstract: Large Language Models (LLMs) with extended reasoning capabilities often generate verbose and redundant reasoning traces, incurring unnecessary computational cost. While existing reinforcement learning approaches address this by optimizing final response length, they neglect the quality of intermediate reasoning steps, leaving models vulnerable to reward hacking. We argue that verbosity is […]
On the Degrees of Freedom of Gridded Control Points in Learning-Based Medical Image Registration
arXiv:2603.16940v1 Announce Type: cross Abstract: Many registration problems are ill-posed in homogeneous or noisy regions, and dense voxel-wise decoders can be unnecessarily high-dimensional. A sparse control-point parameterisation provides a compact, smooth deformation representation while reducing memory and improving stability. This work investigates the required control points for learning-based registration network development. We present GridReg, a […]
Fast weight programming and linear transformers: from machine learning to neurobiology
arXiv:2508.08435v5 Announce Type: replace-cross Abstract: Recent advances in artificial neural networks for machine learning, and language modeling in particular, have established a family of recurrent neural network (RNN) architectures that, unlike conventional RNNs with vector-form hidden states, use two-dimensional (2D) matrix-form hidden states. Such 2D-state RNNs, known as Fast Weight Programmers (FWPs), can be interpreted […]
AdapTS: Lightweight Teacher-Student Approach for Multi-Class and Continual Visual Anomaly Detection
arXiv:2603.17530v1 Announce Type: cross Abstract: Visual Anomaly Detection (VAD) is crucial for industrial inspection, yet most existing methods are limited to single-category scenarios, failing to address the multi-class and continual learning demands of real-world environments. While Teacher-Student (TS) architectures are efficient, they remain unexplored for the Continual Setting. To bridge this gap, we propose AdapTS, […]