AI Dataset2026
Provides a year-scale multimodal benchmark and evaluation framework for on-device long-term memory in personal assistants, built from real mobile user trajectories. Tests memory construction, retrieval, updating, temporal reasoning, and implicit preference inference, and includes a knowledge-grounded synthesis pipeline to form coherent long-horizon trajectories.
Builds an editable, persistent 3D world state to drive iterative previsualization for film, games, and design — enabling local edits and recombinations instead of one-shot video regeneration. Uses separate stages for state construction, state evolution, and state access, with render-feedback camera refinement.
AI Agent Papers2026
Uses a stronger 'builder' model at inference time to construct executable harnesses that boost weaker target models without parameter updates, mainly by turning unstable reasoning into deterministic code, routing, and strict answer-format enforcement.
AI Agent2026
Runs persistent, self-hosted AI teammates that retain conversation, memory, routines and a sandboxed browser/shell. Supports bring-your-own models, local or remote sandbox providers, voice, team computers and integrations for auditable, controllable agent workflows.
MCP Server2026
Turns natural-language instructions into end-to-end Android automation that drives real devices and captures Logcat and screenshots. Uses a multimodal “Dynamic‑First, Coordinate‑Fallback” locator and a native MCP server for IDE integration, supporting fast Flash (3–5s/step) and verifiable Pro workflows.
AI Agent Papers2026
Yiwei Li, Wanli Yang +11Affiliation: Meituan, Affiliation: University of Chinese Academy of [email protected]
Systematically evaluates LLM-driven autonomous agents on long-horizon AI research tasks using rule-based within-run metrics (Solution Framing, Execution, Feedback Control). Focuses on experience reuse and harness effects across 36 tasks and seven frontier models, finding agents act more like engineering optimizers than autonomous researchers.
AI Agent Papers2026
Bobo Li, Hao Fei +31National University of Singapore 2University of Oxford, Project page: https://omni-scientist.github.io +1
Conducts end-to-end multidisciplinary research directly from heterogeneous raw evidence using lifecycle-wide perception and three autonomous agents (Ideation, Experiment, Writeup). Integrates perceptual analysis, execution provenance, and code-enforced checks to produce executable analyses, validated results, and compiled manuscripts across many modalities.
AI Agent Papers2026
Defines "agentic transactions" and an ACID-style reliability framework for LLM agents that manage long-horizon tasks over persistent environments. Implements an ACID-compliant data agent using exploration–execution–validation cycles, confidence-divergence checks, semantic isolation, and append-only durable workspaces.
AI Agent2026
Shows what fills a DeepSeek Harness agent's context and how it changes per request. Browse prompts, tools and messages, trace compaction, and inspect token usage, estimated costs and parent/subagent relationships.
AI Agent Papers2026
Trains compact conversational agents to adapt at runtime to changing 'Harness' configurations (Skills, Hooks, prompts, tools) using Harness-Aware Training (HAT): Harness-State Augmentation, on-policy distillation, and RL to preserve generality while meeting low-latency deployment constraints.
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.