香港入境处智能身份证预约配额监控看板：5分钟级检测+邮件/飞书放号通知（第三方工具，非官方）

Implementation of “Can LLM-as-a-Judge Reliably Verify Rubrics in Agentic Scenarios?”

Hy3 (295B A21B), a leading reasoning and agent model in its size, with great cost efficiency.

Hy3 preview (295B A21B), a leading reasoning and agent model in its size, with great cost efficiency

UniRL is a Framework for Unified Multimodal Model Reinforcement Learning

MiroEval: A benchmark and evaluation framework for deep research agents — 100 tasks (70 text, 30 multimodal) assessed across synthesis quality, factuality, and research process. 13 systems evaluated.

mini-claude-code: A minimal, readable Python re-implementation of Claude Code

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

OpenSeeker: A search agent with open-source data and models

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…

MemOCR: an OCR-driven visual memory agent.

The official repo of "WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents"

Official Code Repository for the paper "Distilling LLM Agent into Small Models with Retrieval and Code Tools"

MLLM, DeepResearch, Agentic AI

Agent-Omit: Training Efficient LLM Agents for Adaptive Thought and Observation Omission via Reinforcement Learning

[CVPR 2026🔥] Enhancing Spatial Understanding in Image Generation via Reward Modeling

[ICLR 2026] VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications

We introduce VISTA-Bench, a systematic benchmark from multimodal perception, reasoning, to unimodal understanding domains. It evaluates visualized text understanding by contrasting pure-text and vi…

RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios

VTC-R1: Vision-Text Compression for Efficient Long-Context Reasoning.

EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control

Contexts Optical Compression

Incentivizing "Thinking with Long Videos" via Native Tool Calling

DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation.

[ICCV 2025] Hybrid Layout Control for Diffusion Transformer: Fewer Annotations, Superior Aesthetics.

EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing [ICLR 2026]