Slithering to Autonomy: A Snake Robot Navigates the Real World
Researchers have developed a complete navigation system enabling a snake robot to autonomously follow waypoints and adapt to complex terrains.
Science
Beyond Logic: When AI Gets Reasoning Wrong
New research reveals that while artificial intelligence systems can flawlessly solve formal logic problems, they struggle with reasoning based on real-world knowledge and are surprisingly susceptible to human biases.
Robots That Understand What Things Are For
A new framework, SAGA, empowers robots to perform complex manipulation tasks in real-world environments by grounding semantic understanding in structured affordances.
AI Agents Revive Stalled Open Source Science
A new approach leverages artificial intelligence to overcome development hurdles and breathe life back into critical, yet neglected, scientific software projects.
Beyond Black Boxes: Learning Robot Dynamics with Interpretable Models
![Evaluations demonstrate the trained model’s performance using scene reconstruction on real-world data gathered from a 7-degree-of-freedom WAM robot arm, as detailed in Sousa et al.’s work [sousa2014].](https://arxiv.org/html/2512.11900v1/x4.png)
New research demonstrates that symbolic regression and sparse identification techniques can unlock clear, physically-meaningful insights into how robots move, offering a powerful alternative to complex neural networks.
Choosing the Right AI for Your Code: A Smarter Approach
Researchers now have a new framework to navigate the complex landscape of artificial intelligence models for software engineering tasks.
Seeing Beyond the Sensor: Collaborative Perception with CoRA
A new architecture, CoRA, dramatically improves the efficiency and robustness of vehicle-to-everything (V2X) perception systems by intelligently decoupling performance from communication overhead.
Beyond Recall: Architecting Memory for Intelligent Agents
As AI agents become increasingly sophisticated, their ability to learn and adapt hinges on robust and well-designed memory systems.
Decoding Emotions: AI Helps Children with Autism Express Themselves Through Robotics
A new deep learning framework is improving the accuracy of emotion recognition in autistic children during interactions with social robots, paving the way for more effective support and diagnosis.
AI Agents Speed Up the Hunt for New Materials
A new open-access platform combines the power of artificial intelligence with materials science databases to automate research and accelerate discovery.