AI Dataset2026
Provides a curated benchmark of 170 real-world, multilingual code-refactoring instances to evaluate AI coding agents on large-scale, behavior-preserving, cross-file refactors. Each task includes rewritten issue descriptions and manually reviewed test suites to avoid over- and under-constraining evaluations.
A research report proposing a continual-learning agent workflow that pairs recursive self-improvement with a Mixture-of-LoRA design: freeze a foundation model, compose specialist LoRA adapters routed per user turn, and support them with long-context RL and post-training infrastructure.
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.
AI Video Papers2026
Chuyue Li, Jinpeng Yu +8Affiliation: Qwen Business Unit of Alibaba, Affiliation: ShanghaiTech University +3
Encodes videos into a Film Knowledge Graph and reconstructs them to learn agent-native, editable video representations for agentic reasoning and manipulation. Uses agentic auto-encoding with dual-loop textual-gradient optimization, reports large reconstruction gains, and releases a benchmark and dataset.
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 Video Papers2026
Externalizes persistent scene state into a camera-indexed world bank and designs a long-horizon teacher whose sparse-attention supervision is distilled into a three-step student, enabling responsive, low-latency interactive long-horizon video generation with bounded denoiser context.
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 Dataset2026
Provides 617.5 hours of high-precision optical motion-capture with synchronized object trajectories and standardized 55-joint BVH for whole-body and human–object interaction research. Frame‑LU indexed and paired with natural-language descriptions; designed for humanoid learning, motion priors, and interaction-aware benchmarks.
AI Video Papers2026
Systematically evaluates AI-generated video detectors and generators for real-world crisis scenarios using RA-Bench (17,886 clips: 1,830 real anchors, 16,056 generated). Shows detector families fail to generalize across generation conditions, and that human-misleading videos and social dissemination further degrade detection.
AI Agent Papers2026
Yansong Ning, Jingwen Ye +6Affiliation: AI Thrust, HKUST(GZ), TEG AIPD, Tencentyning092connect.hkust-gz.edu.cn, [email protected]{jingwenye,wadewdzhang}@tencent.com
Evaluates and trains multimodal agents to construct interactive 3D open worlds from user queries — provides a large benchmark of assets, seed worlds, and reverse-synthesized queries plus a sandbox RL gym for tool-driven editing and rubric-based verification. Reports that frontier MLLMs perform under 60% and that RL fine-tuning improves precise 3D editing.
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.
AI Dataset2026
Provides 12 million verified source/edited image pairs with per-sample edit instructions and VQA-style quality checks for large-scale training and evaluation of instruction-based image editing models. Features a 1,000+ fine-grained edit taxonomy and multi-concept dense-supervision bundles; data is distributed as TAR shards for scalable extraction.