AI Agent Papers2026
Drives long‑horizon desktop agents by reading and manipulating program state (files, DOM, backends) instead of relying on screenshots. The main agent uses code for actions and structural verification while a lightweight GUI subagent handles rare screenshot-click steps, improving success rates and lowering per-task cost versus screenshot-only approaches.
Enables tactile-aware robot manipulation by pretraining a vision–tactile–language–action foundation model and improving offline policies with ALTER. Combines large-scale NeoData visuo-tactile pretraining, a latent tactile pathway for predictive touch signals, and advantage‑conditioned offline RL for contact-rich tasks.
AI Agent Papers2026
Lets canvas-native agents plan, generate, edit, and organize long-horizon multimodal creative projects by representing artifacts, versions, and actions as typed canvas nodes and links. Uses a three-layer design (canvas state, protocol bridge, agent runtime) so agents act within an inspectable, editable project state.
Presents a 2.8T-parameter Mixture-of-Experts multimodal model with a 1-million-token context window and 104 billion activated parameters, targeting long-horizon agentic RL, coding, reasoning, and vision. Key innovations include Kimi Delta Attention, Attention Residuals, Stable LatentMoE (16 of 896 experts active per token), ~2.5× scaling efficiency over Kimi K2, and a public weight release.
AI Model2026
A 2.6B causal LLM post-trained for agentic workloads and long-context on-device text generation. Key features: 128K context window and vocabulary, function-calling/tool use support, agentic RL/post-training pipeline, and optimized CPU/Apple inference and multiple deployment formats; suited for agents, RAG and long-context extraction.
AI Dataset2026
Captures synchronized multimodal embodied-human data in real homes — egocentric and multi-view video, metric body/hand/object motion, audio, and tactile signals. Released under a gated non-commercial research license with identifiable participants and strict non-redistribution/privacy constraints.
Presents Metis, a prototype memory foundation model that embeds a persistent native memory state into the backbone so historical experience is compressed and accessed via memory attention. Key features: forward-only, gradient-free online memory updates; memory-specific mid-training objectives; and a dual text/code memory design.
AI Model2026
Provides a 750-billion-parameter multilingual Mixture-of-Experts (MoE) foundation language model optimized for long-context understanding, agentic workflows, and instruction following. Key features include a 262,144-token context window, speculative decoding (MTP/DSpark), 37B active parameters, 10-language support, and an Apache-2.0 license.
Evaluates whether vision-language models can make actionable decisions for a physical body by decoupling decision-making from low-level motor execution. Introduces HumanCLAW-Bench with 1,218 long-horizon egocentric episodes across 41 indoor scenes and diagnoses a lack of embodied self-awareness in current VLMs.
Autonomously proposes, modifies, executes, and evaluates ML experiments to study recursive self-improvement in machine learning engineering. Implements an open stack (OpenMLE-Gym, -RL, -Evo) and post-trains Frontis-MA1 (35B) around four evolution operators (Draft, Improve, Debug, Crossover); releases model weights and the full codebase.
AI Agent Papers2026
Designs and evaluates a foundation GUI agent that performs cross-platform GUI and CLI actions on real devices to complete long-horizon workflows. Emphasizes a unified action space, a large-scale real-device mobile runtime, an AutoResearch-style data flywheel, and online RL training across 10,000+ concurrent environments.
Regularizes latent world models by replacing the Epps–Pulley Gaussianization objective with a quantile–quantile matching loss that aligns projected latent samples to rank-matched Gaussian quantiles, improving tail correction and planning success via cross-batch ranking.