TradingAgents: Multi-Agents LLM Financial Trading Framework

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.

https://arxiv.org/abs/2412.20138

https://hjfy.top/arxiv/2412.20138

https://github.com/tauricresearch/tradingagents (118601)

Unlimited OCR Works

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.

https://arxiv.org/abs/2606.23050

https://hjfy.top/arxiv/2606.23050

https://github.com/baidu/Unlimited-OCR (29876)

TokenEconomizer: Experience-Driven Black-Box Cost Control for Coding Agents

TokenEconomizer reduces recurring token costs of coding agents across sequential real-world tasks by pruning irrelevant tools, injecting micro-skills, and interrupting failure loops.

https://arxiv.org/abs/2610.22732

https://hjfy.top/arxiv/2610.22732

https://github.com/microsoft/TokenEconomizer (1134)

Investor's Last Exam: Can AI Agents Do Equity Investment Without Seeing the Future?

Investor's Last Exam evaluates financial agents on end-to-end equity research using frozen evidence, expert criteria, and dependency graphs, revealing that top models excel at research but fail at forecasting and investment judgments.

https://arxiv.org/abs/2610.38342

https://hjfy.top/arxiv/2610.38342

https://github.com/Prophetlab/Investor-Last-Exam (86)

Intrinsic Distribution Matching

Intrinsic Distribution Matching improves few-step text-to-image generation by adding explicit moment constraints to distribution matching distillation, achieving state-of-the-art long-text rendering with minimal network evaluations.

https://arxiv.org/abs/2610.39633

https://hjfy.top/arxiv/2610.39633

https://github.com/inclusionAI/IDM (49)

Hy-Nomas: Towards Free-form Interactive World Generation

Hy-Nomas is a video world model that uses causal attention and structured conditioning to generate interactive, multi-turn video segments with text and camera control.

https://arxiv.org/abs/2610.36729

https://hjfy.top/arxiv/2610.36729

https://github.com/Tencent-Hunyuan/Hy-Nomas (408)

MinerU2.5: A Decoupled Vision-Language Model for EfficientHigh-Resolution Document Parsing

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.

https://arxiv.org/abs/2509.22186

https://hjfy.top/arxiv/2509.22186

https://github.com/opendatalab/MinerU (82816)

SmolDocling: An ultra-compact vision-language model for end-to-endmulti-modal document conversion

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.

https://arxiv.org/abs/2503.11576

https://hjfy.top/arxiv/2503.11576

https://github.com/docling-project/docling (69878)

Next-Concept Modeling: Fast, Parallel Coarse-to-Fine Text Generation

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

https://arxiv.org/abs/2610.14162

https://hjfy.top/arxiv/2610.14162

https://github.com/HazyResearch/ncm (1289)