Trending Papers

GenericAgent is a self-evolving large language model agent system that maximizes context information density through hierarchical memory, reusable SOPs, and efficient compression to overcome long-horizon limitations.

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.

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.

LingBot-Map is a feed-forward 3D foundation model that reconstructs scenes from video streams using a geometric context transformer architecture with specialized attention mechanisms for coordinate grounding, dense geometric cues, and long-range drift correction, achieving stable real-time performance at 20 FPS.

OpenGame is an open-source agentic framework for end-to-end web game creation that uses specialized code models and evaluation benchmarks to overcome challenges in interactive application development.

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.

LLaDA2.0-Uni is a unified discrete diffusion language model that integrates multimodal understanding and generation through a semantic discrete tokenizer, MoE-based backbone, and diffusion decoder, achieving performance comparable to specialized vision-language models while enabling efficient inference and high-fidelity image generation.

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

VibeVoice synthesizes long-form multi-speaker speech using next-token diffusion and a highly efficient continuous speech tokenizer, achieving superior performance and fidelity.

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.

PaddleOCR-VL, a vision-language model combining NaViT-style dynamic resolution and ERNIE, achieves state-of-the-art performance in document parsing and element recognition with high efficiency.

We study allowing large language models (LLMs) to process arbitrarily long prompts through the lens of inference-time scaling. We propose Recursive Language Models (RLMs), a general inference strategy that treats long prompts as part of an external environment and allows the LLM to programmatically examine, decompose, and recursively call itself over snippets of the prompt. We find that RLMs successfully handle inputs up to two orders of magnitude beyond model context windows and, even for shorter prompts, dramatically outperform the quality of base LLMs and common long-context scaffolds across four diverse long-context tasks, while having comparable (or cheaper) cost per query.

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.

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.

A large language model adapted for time-series forecasting achieves near-optimal zero-shot performance on diverse datasets across different time scales and granularities.

AutoDev is an AI-driven software development framework that automates complex engineering tasks within a secure Docker environment, achieving high performance in code and test generation.

LightRAG improves Retrieval-Augmented Generation by integrating graph structures for enhanced contextual awareness and efficient information retrieval, achieving better accuracy and response times.

Mixture of Experts models are reviewed for their efficiency and performance in large-scale, multimodal data tasks across various machine learning paradigms and applications in computer vision and natural language processing.

HY-World 2.0 is a multi-modal world model framework that generates high-fidelity 3D Gaussian Splatting scenes from diverse inputs using specialized modules for panorama generation, trajectory planning, world expansion, and composition, along with an enhanced rendering platform for interactive 3D exploration.

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.

DFlash is a speculative decoding framework that uses a lightweight block diffusion model for parallel token drafting, achieving significant speedup over existing autoregressive methods while maintaining high-quality outputs.

The study analyzes Claude Code's architecture, identifying five motivating human values and tracing them through thirteen design principles to specific implementation choices, including a core while-loop architecture and supporting systems for safety, context management, and extensibility.

LeWorldModel presents a stable end-to-end JEPA framework that trains efficiently from raw pixels using minimal loss terms while maintaining competitive performance in control tasks and encoding meaningful physical structures.

LlamaFactory is a unified framework enabling efficient fine-tuning of large language models across various tasks using a web-based user interface.

A hierarchical time series reasoning dataset and model are introduced to improve LLM understanding of temporal data through visualized patterns and numerical tables.

A novel GPT-based model, OmniFlatten, enables real-time natural full-duplex spoken dialogue through a multi-stage post-training technique that integrates speech and text without altering the original model's architecture.

MultiWorld is a unified framework for multi-agent multi-view world modeling that achieves accurate multi-agent control while maintaining multi-view consistency through specialized modules for condition handling and global state encoding.

Agentic coding tools receive goals written in natural language as input, break them down into specific tasks, and write or execute the actual code with minimal human intervention. Central to this process are agent context files ("READMEs for agents") that provide persistent, project-level instructions. In this paper, we conduct the first large-scale empirical study of 2,303 agent context files from 1,925 repositories to characterize their structure, maintenance, and content. We find that these files are not static documentation but complex, difficult-to-read artifacts that evolve like configuration code, maintained through frequent, small additions. Our content analysis of 16 instruction types shows that developers prioritize functional context, such as build and run commands (62.3%), implementation details (69.9%), and architecture (67.7%). We also identify a significant gap: non-functional requirements like security (14.5%) and performance (14.5%) are rarely specified. These findings indicate that while developers use context files to make agents functional, they provide few guardrails to ensure that agent-written code is secure or performant, highlighting the need for improved tooling and practices.

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.

GEPA, a prompt optimizer using natural language reflection, outperforms RL methods like GRPO and MIPROv2 with fewer rollouts by learning high-level rules from trial and error.

MemOS, a memory operating system for Large Language Models, addresses memory management challenges by unifying plaintext, activation-based, and parameter-level memories, enabling efficient storage, retrieval, and continual learning.

ClawGUI presents an open-source framework that addresses key challenges in GUI agent development through unified reinforcement learning, standardized evaluation, and cross-platform deployment capabilities.

DeepSeek-V3 is a parameter-efficient Mixture-of-Experts language model using MLA and DeepSeekMoE architectures, achieving high performance with efficient training and minimal computational cost.

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.

GigaWorld-Policy introduces an action-centered World-Action Model that improves robotic policy learning by decoupling visual and motion representations, enabling faster inference and better task performance through dual supervision from action prediction and video generation.

SkillClaw enables collective skill evolution in multi-user LLM agent systems by aggregating user interactions to autonomously update and improve reusable skills across the ecosystem.

A retrieval-augmented LLM framework improves financial sentiment analysis by tuning LLMs for sentiment prediction and augmenting them with external context, outperforming traditional models and other LLMs.

Despite growing interest in Quranic data research, existing Quran datasets remain limited in both scale and diversity. To address this gap, we present Tadabur, a large-scale Quran audio dataset. Tadabur comprises more than 1400+ hours of recitation audio from over 600 distinct reciters, providing substantial variation in recitation styles, vocal characteristics, and recording conditions. This diversity makes Tadabur a comprehensive and representative resource for Quranic speech research and analysis. By significantly expanding both the total duration and variability of available Quran data, Tadabur aims to support future research and facilitate the development of standardized Quranic speech benchmarks.

RF-DETR, a light-weight detection transformer, uses weight-sharing NAS to optimize accuracy and latency for real-time detection across diverse datasets.

EasyVideoR1 presents an efficient reinforcement learning framework for video understanding that improves training throughput, supports diverse video tasks, and enables joint image-video training with comprehensive evaluation across multiple benchmarks.

Vista4D presents a video reshooting framework that uses 4D point cloud representation to synthesize scenes from new viewpoints while maintaining 4D consistency and camera control.

AI-Trader presents the first fully automated live benchmark for evaluating large language models in financial decision-making across multiple markets with autonomous information processing.

AutoFigure-Edit is an end-to-end system that generates editable scientific illustrations from text descriptions and reference images, supporting flexible style adaptation and efficient refinement.

A self-distillation framework converts implicit 3D knowledge from video diffusion models into an explicit 3D Gaussian Splatting representation, enabling 3D scene generation from text or images.

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.

Bitnet.cpp enhances edge inference for ternary LLMs using a novel mixed-precision matrix multiplication library, achieving significant speed improvements over baselines.

mmGRPO, a multi-module extension of GRPO, enhances accuracy in modular AI systems by optimizing LM calls and prompts across various tasks.

A self-supervised framework optimizes prompts for both closed and open-ended tasks by evaluating LLM outputs without external references, reducing costs and required data.

The Qwen3-TTS series presents advanced multilingual text-to-speech models with voice cloning and controllable speech generation capabilities, utilizing dual-track LM architecture and specialized speech tokenizers for efficient streaming synthesis.