Enterprise AI agents that share a memory store face two unaddressed risks: sensitive data can leak through legitimately computed results the requester could not derive, and departm...
When a large language model handles a multi-turn task and a user proposes a change but ultimately rejects it, the model should continue as if nothing changed. We find a surprising ...
``What are the irreducible conditions that are sufficient to produce an outcome?'' is one of the most common questions that recur across computation and science. Its answers, the m...
Action-conditioned robot world models must respond precisely to robot trajectories while preserving realistic visual dynamics, yet learning both from heterogeneous robot videos rem...
Whole-body tracking has become the interface through which operators drive humanoid robots, yet the references it consumes are recorded on level ground and carrying nothing, so the...
Memory has become integral to the LLM agent ecosystem, supporting information retention and reuse across interactions. However, most existing agent memory systems construct memory ...
Reinforcement learning (RL) has greatly advanced the capabilities of large language models (LLMs), but its memory demands remain a barrier to broader adoption. We introduce LoGRA, ...
Memory self-evolution uses task feedback to iteratively improve executable memory programs that store and retrieve information from past interactions. Existing approaches typically...
Tabular foundation models perform in-context learning (ICL) by conditioning predictions on labeled training examples provided as context. Unlike traditional models that separate tr...
Test-time training (TTT) lets a model store information in its weights during inference. When the model learns from its own output, however, each update also changes the model that...
Search agents repeatedly make short decisions about relevance, evidence sufficiency, and search actions. Using generative language models for these decisions introduces latency and...
Most vision-language-action models represent future motion as fixed-rate action chunks, tying temporal resolution and prediction horizon to a fixed output budget. This pointwise re...
Generating a high-quality gaming world from a natural-language game intent requires joint reasoning about scene structure, spatial layout, gameplay objectives, interactive entities...
Long-term memory enables LLM-based agents to retain and reuse information across tasks and sessions, supporting personalization and long-horizon interactions. However, persistent m...
We present Kandinsky 6.0 Video, a family of foundation diffusion models for synchronized text-to-audio-video generation, comprising Kandinsky 6.0 Video Lite (3B parameters) and Kan...
Open-ended discovery requires learning from repeated attempts while continuing to explore directions whose value is not yet apparent. Search with a frozen large language model (LLM...
As agents rapidly evolve, existing benchmarks can become saturated, limiting their ability to distinguish capabilities and reveal remaining failure modes. Particularly in scientifi...
Continual skill evolution enables LLM agents to accumulate and refine reusable procedural knowledge from interaction experience without updating model parameters. Its effectiveness...
Scaling robot data and model capacity has improved Vision-Language-Action (VLA) policies, but further progress is constrained by the high cost of robotic data. Verifier-guided test...
Recent GPU kernel optimization agents retain what they learn in knowledge bases or as distilled skills. Kernel benchmarks score each attempt's implementation for correctness and sp...
Large language models (LLMs) are increasingly used as interactive agents and simulators, yet it remains unclear whether they can recover latent sequential structure beyond surface ...
Tool-using AI agents are increasingly deployed across enterprise software systems, yet widely used benchmarks primarily evaluate nominal task completion, conflating baseline planni...
Large language models (LLMs) progressively revise their predictions across Transformer layers, yet we typically observe only the final output, discarding the trajectory through whi...
Robot agents must connect their intended actions to observed outcomes while retaining the context needed to revise their choices over repeated attempts. Existing interfaces often l...