The paper introduces MiraBench, a new benchmark that evaluates the action-conditioned reliability of robotic world models, finding that visual fidelity is insufficient and that optimism bias is a perv…

The paper introduces NaRA, a noise-aware LoRA technique that dynamically adapts fine-tuning parameters based on the noise level during diffusion, significantly improving the performance of Diffusion L…

The paper proposes SCALE, a self-improving web agent framework that uses adversarial roles and graph exploration to autonomously discover agent limitations and enhance adaptability in complex web envi…

The paper introduces ARCA, a novel credit assignment method that measures token salience directly from the adapter's residual hidden state, addressing the degeneracy of standard intrinsic signals when…

The paper demonstrates that supervised fine-tuning significantly outperforms frontier zero-shot large language models for screen-conditioned action prediction on the PiSAR benchmark, highlighting the…

The paper proposes Preference Delta Aggregation (PDA), a framework that aggregates multiple weak preference signals derived from smaller model pairs using LoRA merging to significantly boost the perfo…

This paper investigates the robustness of world models in vision-based quadrotor navigation and identifies factors governing their quality.

The paper introduces CyBiasBench, a comprehensive benchmark that quantifies the inherent, agent-specific bias in LLM agents' attack selection patterns in cybersecurity scenarios.

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex open-world agent deployments.

The paper introduces AgentDoG 1.5, a lightweight and scalable alignment framework that significantly improves AI agent safety and security for complex, open-world agentic scenarios.

The paper formally addresses the challenging question of cross-domain transferability of latent predictive models by proposing a structured framework that quantifies the relationship between source an…

The paper proposes PaW, a co-training framework that uses standard RL rollouts to provide auxiliary world model supervision directly during policy training, significantly improving language agent perf…

SkillAdaptor is a novel, training-free framework that enables stable, step-level adaptation of external skills for LLM agents by precisely attributing failures to specific skills.

The paper introduces Grounded Agentic Interaction Synthesis (GAIS), a framework that generates high-quality, diverse, and complex agentic training data by anchoring tasks to real-world protocols, sign…

The paper introduces Andes, a framework that treats data generation as a plug-and-play agent skill, enabling autonomous alignment of LLMs by providing an intelligent, closed-loop data synthesis interf…

DeMaVLA is a generalizable Vision-Language-Action foundation model designed for deformable object manipulation, achieving strong real-world performance on folding tasks by leveraging large-scale real-…

This study provides a comprehensive benchmark of 10 frontier LLMs on 200 offensive cybersecurity tasks, finding that environment tooling and model selection are the primary performance drivers, with C…