Researchers propose POEF, an automated red-teaming framework to bridge the intent-behavior gap in LLM-based robot jailbreaks, demonstrating an 80% behavior jailbreak success rate.

Researchers investigated the performance of embodied LLMs in a physical robotic setup with varying levels of observation fidelity. They found that LLMs performed best under raw RGB input and worst under perfect ground-truth observations. This suggests that measured performance may not reflect robust problem-solving abilities, but rather the interaction between perceptual errors and reasoning failures.

The authors propose Divide-and-Remember (D&R), a recursive memory method for Vision-Language-Action (VLA) models that learns to remember relevant information from a long history of observations. This method is efficient, scalable, and achieves state-of-the-art results on a benchmark of long-horizon manipulation tasks.

A research paper proposing a design pattern called 'bounded-fidelity sim-as-demo-stage' to improve audit-chain reproducibility in governance benchmarking of LLM-driven robots. The pattern suppresses contact physics within explicitly bracketed handoff envelopes while preserving full dynamics elsewhere.

This paper proposes a method to improve spatial understanding in LLM-driven agents by combining geometrical tools with LLMs. The approach involves vector-quantizing geodesic trajectories and associating natural language descriptions with them. This allows the LLM to choose the most appropriate tool for a given state and goal, effectively separating learning into two levels: tool discovery and reasoning.

A new framework, FailBank, is introduced to improve policy learning for vision-language-action models by using runtime feedback for persistent policy improvement.

Researchers propose URAI (Universal Robot-Agent Interface), a new approach to robot control that couples a programming agent with an execution agent. The programming agent writes reusable tools, while the execution agent selects and parameterizes them. This design retains model-level decision-making and improves performance on various robot tasks.

A research paper introduces ENCORE, a system that enables coding agents to discover manipulation strategies using a few demonstrations. ENCORE improves upon prior agentic systems, achieving higher success rates in various tasks, including cube handover and cup inversion.

Researchers propose Spotter, a system where an embodied model leads and executes continuously, while a vision-language model (VLM) monitors and intervenes only when an error is detected, reflects on and corrects it, and returns control. This approach improves performance in embodied model tasks, such as robotics and navigation, by leveraging the strengths of both models.