AI Dataset2026
A synthetic, verifiable-first agentic training corpus with 19,072 training traces and 2,135 held-out evaluation rows. Provides per-turn visible reasoning, real sandboxed tool executions, 13 verifiable task families, and NeMo Gym / RL-ready reward contracts for SFT and RL workflows.
AI Agent Papers2026
Trains a foundation GUI agent using a closed-loop, environment-grounded data stack plus in-context multimodal demonstrations to automate long-horizon desktop workflows. Combines scalable task generation/verification, subtask-level demo guidance, and a 100-task OSWorkerBench benchmark to improve strict success and task progress.
Presents a unified black-box reinforcement learning framework to train and optimize agents running inside complex execution harnesses. Uses sandbox-parallel rollouts, a serving proxy that captures model calls and reconstructs multi-turn trajectories as prefix trees, and adapted GRPO/PPO optimizers to achieve stable, scalable RL across heterogeneous harnesses.
AI Agent Papers2026
Enables closed-loop execution for embodied agents by evolving code-based runtime critics and recovery skills online while keeping the base policy frozen. Combines three timescale loops with Z-Infra rollout infrastructure; reports 90.8% on LIBERO-Pro, 93.6% on RoboCasa and an 11.1× inference speedup.
Uses cooperative multi-agent RL where multiple decoupled models provide peer-derived pseudo-rewards to each other, enabling unsupervised improvements in reasoning; increases cohort diversity to reduce correlated errors and avoid training collapse, showing consistent gains across text and multimodal benchmarks.
Embodied AI2026
Turns embodied navigation into 2D visual prompting where a vision-language model selects image pixels that are projected to 3D actions; adds selective chain-of-thought, compressed anchor-trajectory memory, and a two-level alignment objective to improve sample and runtime efficiency.
Fine-tunes long-horizon LLM agents with evolution strategies so full-model updates run at inference-level GPU memory. Emphasizes trajectory-level credit via black-box rewards, online prompt–parameter co-evolution, and a cosine decay for perturbation scale to balance exploration and adaptation; suited for limited-GPU settings.
AI Dataset2026
Contains ~2 million human pairwise preference judgments comparing images generated from text prompts; each example pairs two images with a preferred/tie label and is formatted for preference learning, reward-model training, and evaluation.
AI Agent Papers2026
Wraps static, hand-built environments with a programmable plug-in harness that reshapes environment behavior without changing underlying logic. EnvRigger automates diagnosis and synthesis of harness components from agent failure trajectories, validating edits via fresh rollouts to improve agent success and efficiency.
AI Video Papers2026
Yunheng Li, Guohong Mu +5VCIP, School of Computer Science, Nankai University, Brain and Artificial Intelligence Lab, Northwestern Polytechnical University +2
Treats human annotations as oracle rollouts and separates them from on-policy baselines to improve reinforcement learning for video multimodal LLMs. Key features include a decoupled advantage estimator, sign-balanced pruning, and scalable gains across model sizes and data budgets.
AI Model2026
A 4B-parameter on-device general-purpose LLM for chat, writing, translation, coding and agentic workflows with native 1,000,000-token context. Uses a hybrid attention design to enable long-context efficiency, pretrained on ~20T tokens, and compatible with vLLM, llama.cpp, Ollama and LM Studio.
AI Dataset2026
Evaluates whether tool-using LLM agents reliably complete stateful business workflows via 507 executable agent–tool–user tasks across retail, travel, auto insurance, neobank, and IT/HR consulting. Provides browsable Parquet tables for tasks, scenarios, and agent instructions; v1.0 is intended for evaluation-only.