Harness² improves agent execution harnesses through recursive task-level refinement and continual harness-level learning, boosting performance across benchmarks without ground-truth verifiers.

A multi-agent framework using large language models for stock trading simulates real-world trading firms, improving performance metrics like cumulative returns and Sharpe ratio.

Kronos, a specialized pre-training framework for financial K-line data, outperforms existing models in forecasting and synthetic data generation through a unique tokenizer and autoregressive pre-training on a large dataset.

Edge0 enables efficient mixture-of-experts inference on consumer hardware by predicting expert routing ahead of time and using recovery adapters to maintain quality with minimal active memory.

MOSS-Image is an open diffusion transformer that combines high-fidelity synthesis with intent-aware prompt enhancement to generate text-rich, layout-coherent images, achieving state-of-the-art open-weight results on long-form text and layout benchmarks.

Assistants from 2011 answered and waited, and agents from 2023 did a task and stopped. In September 2026 Meta's Muse showed an agent for one person, with accounts, devices, memory and a conversation that lasts, closed, in a vendor's cloud, in one country. Such an agent is expected to act on a person's accounts and devices, remember them across weeks, speak first when it is worth it, and answer for what it did. It is a kind of software, not a model, and until now had no open counterpart. This report defines the personal agent in five questions and three horizons. It reads how Muse is built from Meta's public record and a copy of its production prompt, each statement marked by its source. It then presents nanoMuse, the open-source counterpart under the GPL-3.0, one agent on every device a person owns, with hands on the phone's screen and the computer's. They share one conversation over a relay anyone can run; every action goes through a Sentinel, memory is files the person can read, and the model is their choice. Its size and cost are given as estimates. What is open, memory with provenance, an evaluation suite for the hands and an open model for them, is set out as a roadmap.

StartLux-Decision introduces efficient and adaptive decision models using single-pass prediction and confidence-guided reasoning, trained via a three-stage pipeline with RLCD² reinforcement learning, and evaluates them on Decision Index and the DecisionPivot benchmark.

Next-Concept Modeling uses hierarchical discrete codes and parallel level-wise generation to accelerate diffusion language models while improving quality and reasoning performance.

Frontier large language models exhibit Internal Safety Collapse, where they generate harmful content under specific task conditions, revealing inherent vulnerabilities despite alignment efforts.

OpenDevin is a platform for developing AI agents that interact with the world by writing code, using command lines, and browsing the web, with support for multiple agents and evaluation benchmarks.

PagedAttention algorithm and vLLM system enhance the throughput of large language models by efficiently managing memory and reducing waste in the key-value cache.

Continued pre-training across data scale, diversity, and model size improves embodied learning in virtual worlds but reveals limits in distant-world generalization, motivating richer training beyond imitation.

Prism accelerates native joint video-audio generation at 2K by using dynamic sparse attention guided by local visual variance and audio-visual cross-attention to preserve semantic coherence and cross-modal interactions.

Unlimited OCR introduces Reference Sliding Window Attention to eliminate growing memory consumption during long-sequence OCR tasks, enabling efficient transcription of multiple pages in a single forward pass.

YuE2 unifies symbolic and audio music generation via symbolic planning, producing readable scores and full-song audio with state-of-the-art quality and agentic editing capabilities.

SmolDocling is a compact vision-language model that performs end-to-end document conversion with robust performance across various document types using 256M parameters and a new markup format.

Enhancements to the AgentScope platform improve scalability, efficiency, and ease of use for large-scale multi-agent simulations through distributed mechanisms, flexible environments, and user-friendly tools.

AgentScope enhances agentic applications by providing flexible tool-based interactions, unified interfaces, and advanced infrastructure based on the ReAct paradigm, supporting efficient and safe development and deployment.

MinerU2.5, a 1.2B-parameter document parsing vision-language model, achieves state-of-the-art recognition accuracy with computational efficiency through a coarse-to-fine parsing strategy.

UniAVC trains separate audio and video branches on abundant unimodal data before aligning them with scarce paired data, using independent noise schedules and asymmetric supervision to enable joint synthesis, cross-modal generation, and instruction-guided editing.

WeVisOne-VL unifies object-level and pixel-level visual perception via structured token prediction, supporting detection, localization, counting, OCR, segmentation, and matting with a lightweight pixel decoder and multi-stage training.

MemT-1.0 introduces a memory-native architecture that embeds continuous memory into foundation model computation, improving long-context efficiency and agentic task performance.

Future Chunk Prediction improves autoregressive video diffusion by enforcing future-chunk supervision, yielding more physically plausible video generation with reduced training cost.

Raven is an open-source multi-agent ecosystem that autonomously builds and evolves modular harnesses, enabling cross-domain collaboration and expanding reliable task coverage through composable agent units.

Mem0, a memory-centric architecture with graph-based memory, enhances long-term conversational coherence in LLMs by efficiently extracting, consolidating, and retrieving information, outperforming existing memory systems in terms of accuracy and computational efficiency.

SolarRenderer adapts a frozen video backbone with lightweight LoRAs to render realistic videos from diverse structural inputs in four steps or real-time streaming, using frame-aligned training data.

ARIS is an open-source research harness that uses cross-model adversarial collaboration to ensure reliable long-term research outcomes through coordinated execution, orchestration, and assurance layers.

PaddleOCR-VL-1.6 enhances document parsing performance through targeted data optimization and progressive post-training techniques, achieving state-of-the-art results on OmniDocBench v1.6.

OpenGCUA introduces an open generalist computer-use agent that integrates visual and programmatic interfaces, harness-to-model decision transfer, and code execution to improve task performance and efficiency across models.

RAG-Anything is a unified framework that enhances multimodal knowledge retrieval by integrating cross-modal relationships and semantic matching, outperforming existing methods on complex benchmarks.

Transformers library provides state-of-the-art Transformer architectures and pretrained models for natural language processing tasks with a unified API and emphasis on extensibility and robust deployment.

SANA-Video, a small diffusion model, efficiently generates high-resolution, high-quality videos with strong text-video alignment using linear attention and a constant-memory KV cache, achieving competitive performance at a lower cost and faster speed.

OpenVLHarness improves multimodal reasoning by integrating persistent memory, heterogeneous tool interfaces, and iterative evidence composition across 22 benchmarks.

RSIPO is a self-evolving agentic reinforcement learning framework that co-evolves agentic skills and policies while calibrating teacher supervision reliability via empirical Bayes shrinkage.

GAFU leverages native generation-side representations to improve fine-grained visual understanding in unified multimodal models by compressing them into compact tokens for task-conditioned retrieval.

F2G-Pose is a real-time feed-forward framework that predicts category-level object pose, metric size, and completed shape from a single RGB-D image using dense visual features, DGCNN tokenization, and a Mixture-of-Experts Transformer.

GPT-6-Astra achieves high performance across diverse robotic tasks via in-context learning, yet real-world deployment reveals gaps in demonstration cost, execution time, and practical embodied intelligence.

A framework for self-evolving agent harnesses uses feedback-driven revisions and evolutionary optimization with theoretical generalization guarantees while keeping model weights fixed.

AI-Infra-Guard is an open-source framework that addresses AI infrastructure security through layered detection paradigms spanning infrastructure, protocol, agent behavior, and model layers.

UniMate is a unified diffusion transformer that generates articulated motion for arbitrary skeletons from text and rigged 3D assets without per-skeleton retraining, using topology-aware attention and a large curated motion dataset.

Person-grounded AI skills are automatically distilled from heterogeneous traces into inspectable, correctable packages that capture both capabilities and behavioral patterns.

PrismaForge uses a rubric-based pipeline to synthesize and filter high-quality multimodal code data, enabling open models that rival proprietary systems on visual coding tasks.

DecisionPivot is a diagnostic benchmark that evaluates decision models across controlled variations, revealing gaps between aggregate accuracy, contrast-group performance, calibration, and reasoning effort.

A new sparse voxel representation called O-Voxel enables high-quality 3D generative modeling with efficient inference and robust topology handling.

YOLO26 addresses real-time vision challenges through a unified model family with NMS-free inference, improved training strategies, and multi-task capabilities spanning detection, segmentation, and pose estimation.

The PyTorch distributed data parallel module optimizes large-scale model training using techniques like gradient bucketing, computation-communication overlap, and selective synchronization to achieve near-linear scalability.

Hybrid Reasoning Agents combine latent internal reasoning with text-based external interaction via a unified architecture and specialized post-training, improving agent performance while reducing inference cost and token usage.

REMORY enhances long-horizon agent memory by adding learnable soft tokens to textual summaries, improving decision accuracy with minimal context usage.

PDFMathTranslate enables layout-preserving scientific document translation using large language models and precise layout detection, offering improved precision, flexibility, and efficiency.

SUPRA-Tex decouples visible-material estimation, surface alignment, and 3D completion to generate relightable 3D materials that preserve reference image details and complete unobserved surfaces.