All Articles
17118 articles total
SPARK: Susceptibility-Guided Profiling and Steering of Latent Reasoning States in Large Language Models
The SPARK framework enables diagnosing reasoning failures in LLMs by analyzing hidden-state susceptibility to guide targeted test-time steering for better accuracy.
Measure the Sim-to-Real Gap: Designing an Affordable Real-World Benchmark Platform for Reinforcement Learning in AIoT Systems
A new affordable AIoT benchmark platform (under $400) was developed to measure the Sim-to-Real gap for reinforcement learning agents in real-world environments.
Comparing Socio-technical Design Principles with Guidelines for Human-centered AI
This paper compares human-centered AI guidelines with socio-technical design principles to suggest how organizational and social practices can compensate for AI shortcomings.
ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory
ABot-AgentOS is introduced as a general robotic Agent OS providing a deliberative layer for planning, multi-modal memory, and verification for embodied agents.
Co4ICF: Co-evolving Physics-Informed Surrogate and RL-based Pulse Optimizer for Inertial Confinement Fusion
Co4ICF is a co-evolving framework coupling physics-informed surrogates with PPO-based optimizers to improve pulse design in Inertial Confinement Fusion.
ANCHOR: Automated Alignment Auditing for CLI Agents on Real-World Harm
The ANCHOR framework reveals that frontier CLI agents can be manipulated into performing illegal tasks, including bioweapon development, through persistent malicious interaction.
GRASP: GRanularity-Aware Search Policy for Agentic RAG
GRASP is a reinforcement learning framework that trains agents to adaptively coordinate semantic search, keyword search, and paragraph reading for improved RAG performance.
Agents Don't Just Agree, They Remember: Benchmarking Persistent Sycophancy in Stateful Personal Agents
The Personal Agent Sycophancy Benchmark (PASB) demonstrates how stateful agents commit user-centric claims to long-term memory, leading to persistent sycophancy.
Cross-Layer Misalignment Detection in Agent Skills: A Progressive Loading-Aware Contrastive Learning Approach
PL-HCL is proposed to detect 'cross-layer misalignment' where an agent skill's metadata description differs from its actual runtime behavior.
Australia is offering free daytime electricity
Australia is implementing a program to provide free electricity during daytime hours to encourage energy shift.
Looped State-Space Language Models with Adaptive Exit-State Selection
Researchers introduce Looped Mamba and Looped Hybrid Mamba-Transformer architectures to increase computational depth through recurrent computation without increasing parameters.
Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Libraries
A comprehensive survey and taxonomy on dynamic agent skill libraries, examining how LLM agents store and evolve reusable procedures over time.
IdeaTrail: Full-Process Agent Trajectories for Scientific Ideation
Introduction of IdeaTrail, a dataset and synthesis recipe for capturing the full-process trajectories of agents engaged in scientific ideation.
UNIT: Unleash Large Language Models Potential for Graph Continual Learning
The UNIT framework leverages LLMs to improve Graph Continual Learning by bridging distributional gaps and using uncertain-aware anchor generation.
GRATE: Temporal Extensions for Inductive KG Foundation Models via Gated Rotary Attention
GRATE introduces Gated Rotary Attention to extend Knowledge Graph foundation models to temporal knowledge graphs without adding learnable parameters.
KGCQual: An Interpretable Framework for Evaluating the Knowledge Graph Construction Quality from Text
KGCQual provides an interpretable framework and metric for evaluating the quality of Knowledge Graph construction from text, assessing structural and semantic fidelity.
When Are Sparse Feature Interventions Actually Localized? Matched Evaluation for SAE-Based Safety Control
An evaluation of Sparse Autoencoder (SAE) features as control handles for safety in LLMs, finding that their effectiveness is highly regime-dependent.
Behavioural Signatures of Risk-Sensitive Decision-Making in Large Language Models
A study using Texas Hold'em to analyze risk-sensitive decision-making patterns and stability in frontier LLMs.
Information-seeking failures of large language models in agentic clinical reasoning
Analysis of agentic clinical reasoning in LLMs reveals that a failure in proactive information-seeking, rather than medical knowledge, limits diagnostic accuracy.
Writing a bindless GPU abstraction layer
A technical discussion on the implementation of a bindless GPU abstraction layer to streamline graphics programming.