A new preprint introduces Skillware, a software abstraction designed to formalize and manage persistent behavioral artifacts—called Skill Artifacts—in AI agent systems. The paper defines Skillware Units as managed software entities with independent identity and lifecycle, operationalized through three necessary conditions: behavioral primacy, independent software identity, and an Agent Host execution relationship. The work is supported by analysis of a large corpus of SKILL.md records and multiple engineering implementations, establishing a recurring artifact structure and lifecycle engineering considerations.
Why it matters: Skillware offers a formal ontology and lifecycle for agent skills, potentially enabling more robust, maintainable, and evolvable software artifacts in AI agent ecosystems.
A recent grey literature review synthesizes 106 sources to define AI-native applications, highlighting two core pillars: the central role of AI as the system's intelligence paradigm and their inherently probabilistic, non-deterministic nature. The review identifies key quality attributes—reliability, usability, performance efficiency, and AI-specific observability—and describes an emerging technology stack including LLM orchestration frameworks, vector databases, and AI-native observability platforms. This work offers a structured synthesis of current conceptual and practical perspectives on AI-native software engineering.
Why it matters: This review provides the first comprehensive engineering definition and architectural blueprint for AI-native applications, addressing a gap in systematic guidance for practitioners.
Researchers introduce a method for representing both human and robot hands as sets of 3D particles, with actions defined as end-effector particle displacement fields, to facilitate cross-embodiment learning. They train a graph-based world model on diverse simulated and real hand data, and show that this model, combined with model-predictive control, enables effective dexterous manipulation on previously unseen robotic hands with different kinematics. The study demonstrates that increasing the diversity of training embodiments improves generalization, and that mixing simulated and real data yields better performance than using either alone.
Why it matters: This work provides a shared geometric representation that could accelerate the development of generalist robots capable of learning manipulation skills across a wide range of hand morphologies.
A new preprint report envisions a future where drones transport goods and medical supplies at a scale comparable to highways and the electric grid, but highlights a significant 'capability gap' between current hardware and the software needed for safe, large-scale operations. The report details twelve technical challenges, including scaling to millions of drones, AI assurance, edge-cloud coordination, and regulatory issues, outlining a roadmap for overcoming these barriers.
Why it matters: Addressing these challenges is crucial for enabling transformative applications of drone technology in logistics, disaster response, and infrastructure inspection.
Researchers have introduced the Open Ant, a physical robot platform modeled after the popular Gymnasium Ant environment, to facilitate reinforcement learning (RL) research beyond simulation. The platform enables learning walking policies from scratch in about one hour using either SARSA(λ) or Soft Actor-Critic algorithms, and supports successful transfer of policies trained in simulation to the real robot. Open-source hardware and software are provided to encourage broader adoption and experimentation in real-world RL.
Why it matters: The Open Ant platform makes it significantly easier for RL researchers to test and validate algorithms on real robots, helping to bridge the gap between simulation and real-world deployment.
A new preprint introduces RoboInspector, a pipeline designed to systematically identify and characterize unreliable behaviors in policy code generated by large language models (LLMs) for robotic manipulation. The study analyzes 216 combinations of tasks, instructions, and LLMs, uncovering four main types of unreliable behaviors that can lead to manipulation failures. The authors also propose a refinement approach, guided by feedback from failed policy code, which improves reliability by up to 35% in both simulated and real-world robotic environments.
Why it matters: This work exposes critical reliability challenges in LLM-driven robotic manipulation and demonstrates a practical method to significantly reduce failures, which is important for real-world deployment.
Researchers introduce a hierarchical framework that employs Signal Temporal Logic (STL) as a shared representation to bridge high-level language understanding and low-level robot execution. The system uses a vision-language model to decompose instructions into subtasks with STL specifications, enabling enforcement of precise spatial, temporal, and logical constraints. Real-world tabletop experiments demonstrate that this approach improves the precision, reliability, and interpretability of language-conditioned robot planning compared to standard vision-language-action models.
Why it matters: This work demonstrates that integrating formal specifications like STL can address key limitations of vision-language-action models, enabling more reliable and interpretable robot planning from natural language instructions.
Researchers introduce FARO, a nested kino-dynamic framework designed for rapid feasibility checking and trajectory generation in humanoid loco-manipulation tasks. The system combines a feasibility-guided tree search with a large language model (LLM)-based contact plan sampling strategy to improve search efficiency. Generated trajectories are shown to be trackable by a reinforcement learning (RL)-based controller, enabling execution in real-world scenarios.
Why it matters: This work demonstrates a novel integration of LLM-based sampling, feasibility checking, and RL control to advance fast and practical planning for humanoid robots in previously unseen environments.
Fly0 introduces a framework that separates semantic reasoning from geometric planning for aerial vision-language navigation (VLN). It uses a multimodal large language model (MLLM) to interpret instructions into 2D coordinates, then leverages depth data for 3D localization and generates collision-free trajectories. Experiments show Fly0 improves success rate by over 20% and reduces navigation error by about 50% compared to state-of-the-art baselines in unstructured environments.
Why it matters: Fly0 enables more robust and efficient zero-shot aerial navigation by reducing reliance on continuous MLLM inference, which lowers latency and enhances stability for real-world drone operations.
Researchers introduce PostEDA-Bench, a hierarchical benchmark comprising 145 tasks to evaluate large language model (LLM) agents on advanced circuit design challenges, specifically fixing Design Rule Check (DRC) violations and converging Power-Performance-Area (PPA) targets. The study finds that while agents perform adequately on basic tasks, their success rates drop to 36.66% on practical DRC reasoning and 20% on multi-objective PPA tasks, indicating substantial limitations. The benchmark also shows that vision augmentation can improve DRC-related performance.
Why it matters: This work highlights critical gaps in current LLM agents' ability to handle complex, real-world electronic design automation tasks, especially in multi-objective optimization and practical reasoning.
Researchers introduce Agentic Real2Sim, a framework that leverages vision-language agents to automate the conversion of real-world recordings of object-robot interactions into simulatable digital twins. The system is demonstrated on tasks involving rigid objects, deformable objects, and humanoid motions, domains typically requiring separate pipelines. Agentic Real2Sim achieves conversion success rates comparable to leading models but at a lower computational cost, supporting downstream robotics tasks such as policy learning and evaluation.
Why it matters: This framework could streamline and scale the creation of realistic physics simulations from real-world robot interactions, potentially accelerating robotics research and development.
Researchers introduce Doctorina MedBench, a framework for evaluating agent-based medical AI through simulated physician-patient dialogues. The benchmark uses the D.O.T.S. metric (Diagnosis, Observations/Investigations, Treatment, Step Count) to assess both clinical correctness and dialogue efficiency. The dataset features over 1,000 clinical cases spanning more than 750 diagnoses, and includes support for safety-oriented trap cases and regression testing.
Why it matters: By simulating multi-step clinical dialogues, this benchmark enables a more realistic and comprehensive assessment of clinical competence for medical AI systems than traditional test-based evaluations.
Researchers introduce ImplicitRDP, an end-to-end diffusion policy that unifies visual planning and reactive force control for contact-rich robotic manipulation. The approach leverages Structural Slow-Fast Learning to process asynchronous visual and force signals, and Virtual-target-based Representation Regularization to improve modality integration. Experiments show that ImplicitRDP outperforms vision-only and hierarchical baselines in terms of reactivity and success rates on challenging manipulation tasks.
Why it matters: This work demonstrates a significant advance in integrating visual and force modalities for robust, reactive robotic manipulation in contact-rich environments.
Researchers propose Masked Visual Actions, a pixel-space control interface that represents robotic actions as partially revealed trajectories in video. A single model, finetuned on 15 hours of real and simulated data, demonstrates strong visual fidelity and controllability across various scenes and robot embodiments. The approach enables forward dynamics prediction, model-based planning, and inverse modeling within a unified framework.
Why it matters: This method offers a new way to connect video models and robotic control without explicit action tokens, potentially simplifying and unifying world modeling for manipulation tasks.
A new policy architecture called LANav, based on linear attention, has been proposed for open-vocabulary object goal navigation. LANav achieves a 36.4% success rate on the HM3D-OVON benchmark, outperforming Transformer-based baselines by 6.3 percentage points. The method also demonstrates an 82% success rate in real-world tests on a Unitree Go2 robot, indicating strong sim-to-real transfer and practical feasibility.
Why it matters: This work demonstrates that structured linear attention mechanisms can surpass Transformer architectures for navigation tasks, potentially leading to more efficient and effective robotic navigation systems.
Researchers introduce FinRAG-12B, a 12-billion parameter language model designed for grounded question answering in the banking sector, trained on just 143 million tokens. The model surpasses GPT-4.1 in citation grounding, achieves a calibrated 12% refusal rate, and is deployed at over 40 financial institutions, where it improves query resolution by 7.1 percentage points. The system also delivers responses 3-5 times faster and at 20-50 times lower cost compared to GPT-4.1.
Why it matters: This work demonstrates a practical, data-efficient approach for building domain-specific LLMs that satisfy the accuracy, grounding, and compliance needs of regulated industries such as banking.
Researchers present SR-Agent, an agentic framework designed to automate the refinement of post-ranking strategies in industrial e-commerce recommender systems. The system integrates three specialized LLM agents to identify user-perceived issues, diagnose recurring problems, and implement constrained strategy updates. In a one-month A/B test on the Kuaishou platform, SR-Agent improved order volume by 0.71%, browsing depth by 0.34%, and category diversity by 0.48%, while reducing operational costs.
Why it matters: This work demonstrates a practical, deployed LLM agent system that autonomously enhances e-commerce recommendation quality, delivering measurable business impact and reducing manual intervention.
AgentJet is a distributed swarm training framework designed for reinforcement learning with large language model (LLM) agents. It features a decoupled multi-node architecture that enables heterogeneous multi-model RL, mixed-task training, fault-tolerant execution, and live code iteration. The framework demonstrates a 6.25x reduction in actor-update time on AppWorld and supports automated, long-horizon RL studies with minimal human intervention.
Why it matters: AgentJet offers a scalable and flexible solution for training LLM agents in complex, multi-turn environments, potentially accelerating research and development in agentic AI systems.
A new dual-process planning framework for autonomous driving leverages a structured chain-of-thought (S-CoT) schema to represent scene knowledge. The system uses a lightweight Arbiter to route routine scenes to fast meta-action prediction and complex scenes to slower, structured reasoning, with a rule-based validator ensuring consistency between reasoning and actions. On the NAVSIM benchmark, the approach achieves 80.14% planning accuracy, 97.20% logical consistency, and reduces latency by 17.39% compared to always using slow reasoning. The framework also demonstrates strong annotation quality and identifies scenarios where performance may degrade.
Why it matters: This work demonstrates a practical advance in autonomous driving planning by enabling adaptive, verifiable reasoning with reduced manual annotation and improved efficiency.
Researchers introduce RAPT, a lightweight, self-supervised deployment monitor operating at 50Hz that learns nominal execution from simulation and detects out-of-distribution (OOD) states in real-time during sim-to-real transfer for humanoid robots. In simulation, RAPT improves true positive rate by 37% over the strongest baseline at a 0.5% false positive rate, and on hardware, it achieves 89% TPR with 75% semantic failure diagnosis accuracy across 21 categories. The system also provides interpretable, per-dimension predictive deviation signals and post-hoc semantic failure diagnosis using LLM-based reasoning.
Why it matters: This work advances safety and reliability in deploying learned control policies on humanoid robots by enabling high-frequency, accurate OOD detection and interpretable failure diagnosis during real-world operation.