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

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.

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.

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.

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.

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

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.

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.

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

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.

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

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.

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.

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.

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

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

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.

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.

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.

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.

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.

DiscoveryRSI uses multi-agent evolutionary search and recursive learning to generate testable scientific hypotheses, improving quality through self-improvement and outperforming baseline agents on life-science benchmarks.

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.

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

ATAS improves long-form video consistency by compiling screenplays into referenced shot requests, retrieving spatial and temporal evidence from scene and event memories, and conditionally updating memory after generation.

RSI-Anything leverages predictive world models to guide action selection and adaptive learning, enabling recursive self-improvement across coding, interface navigation, laboratory planning, and scientific optimization tasks.

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.

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.

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.

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

Zep, a memory layer service, outperforms MemGPT in the DMR benchmark and LongMemEval by excelling in dynamic knowledge integration and temporal reasoning, critical for enterprise use cases.

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.

Manga2Animate uses paired creator and reviewer agents to build script and storyboard representations from manga panels, yielding more faithful and consistent animations.

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.

Researchers introduce a benchmark, automated data engine, and self-distillation method to improve audio-visual joint reasoning in omni-modal models.

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.

_paperbanana is an agentic framework that automates the creation of publication-ready academic illustrations using advanced vision-language models and image generation techniques.

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.

EvaOmni is an evidence-grounded benchmark that evaluates whether omnimodal language models identify audio-visual evidence and construct reasoning chains for audiovisual questions.

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

ScaleNav learns goal-directed visual dynamics from internet egocentric videos to generate robot actions for language-conditioned local navigation, achieving high success rates in simulation and real-world deployment.

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.

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

UniForge3D unifies 3D reconstruction and generation in a shared anchor-guided space to build complete assets from sparse images while preserving observed geometry and selecting relevant views for detail recovery.

MemSlides presents a hierarchical memory framework for personalized presentation agents that separates long-term user profiles, working memory for session constraints, and tool memory for reusable execution experiences to enable stable personalization and reliable local edits across multi-turn revisions.

InfiniDream is a vision-language model framework that generates open-ended, editable, photorealistic 3D worlds through symbolic procedural asset creation and deterministic scene placement.

Player-1 improves game control by combining supervised fine-tuning on gameplay trajectories with reinforcement learning across synthetic environments, achieving substantial gains over demonstration-only baselines.

Prime Agent is an open-source harness that uses recursive subagents, persistent computation, and agent-to-agent coordination to extend language models' long-horizon capabilities across coding and reasoning tasks.