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 (2569)

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 (118943)

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 (30061)

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 (127)

OpenDevin: An Open Platform for AI Software Developers as GeneralistAgents

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.

https://arxiv.org/abs/2407.16741

https://hjfy.top/arxiv/2407.16741

https://github.com/opendevin/opendevin (92355)

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 (85)

Xiaomi-OCR-0 Technical Report

Xiaomi-OCR-0 is a compact vision-language model that unifies document parsing and OCR understanding through automated data synthesis, progressive training with text anchoring and reinforcement learning, and achieves state-of-the-art results on multiple benchmarks.

https://arxiv.org/abs/2609.36136

https://hjfy.top/arxiv/2609.36136

https://github.com/SeerRay-Lab/Xiaomi-OCR-0 (369)

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 (69924)

HairDeck: Animation-Ready Stylized Hair Cards from a Single Image

HairDeck generates stylized hair cards and spring-bone animations as unordered token sets using a diffusion transformer, improving accuracy and speed over prior methods.

https://arxiv.org/abs/2610.40599

https://hjfy.top/arxiv/2610.40599

https://github.com/hyz317/HairDeck (188)