[ACL'26 Oral] AgentOCR is a token-efficient framework that compresses multi-turn agent history by rendering it into images and adopting RL-driven self-compression
☆45Mar 1, 2026Updated 5 months ago
Alternatives and similar repositories for AgentOCR
Users that are interested in AgentOCR are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- MemOCR: an OCR-driven visual memory agent.☆33May 17, 2026Updated 3 months ago
- Reproduction code for paper "MineExplorer: Evaluating Open-World Exploration of MLLM Agents in Minecraft"☆20Jun 12, 2026Updated 2 months ago
- ☆15Jan 14, 2026Updated 7 months ago
- RETROAGENT: From Solving to Evolving via Retrospective Dual Intrinsic Feedback☆29Mar 30, 2026Updated 4 months ago
- ☆249Jul 17, 2026Updated last month
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- The official implementation of the paper "Mem-α: Learning Memory Construction via Reinforcement Learning"☆224Dec 25, 2025Updated 8 months ago
- Dr. MAS is an end-to-end RL training framework for multi-agent LLM systems, supporting the co-training of multiple (heterogeneous) LLMs.☆154Jul 27, 2026Updated 3 weeks ago
- Official implementation for Text Generation Beyond Discrete Token Sampling☆26Aug 11, 2025Updated last year
- Official implementation of "Learning To Draft: Adaptive Speculative Decoding with Reinforcement Learning" (ICLR 2026)☆22Mar 1, 2026Updated 5 months ago
- ☆109May 20, 2026Updated 3 months ago
- (ArXiv25) Vision Matters: Simple Visual Perturbations Can Boost Multimodal Math Reasoning☆61Sep 30, 2025Updated 10 months ago
- Official repository for paper Auto-scaling Continuous Memory for GUI Agent☆30Feb 2, 2026Updated 6 months ago
- A collection of long-term memory papers☆36Jan 18, 2026Updated 7 months ago
- Official implementation of Stackelberg PPO for morphology–control co-design.☆17Mar 17, 2026Updated 5 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆117Jul 1, 2026Updated last month
- MemGen: Weaving Generative Latent Memory for Self-Evolving Agents☆409Jun 10, 2026Updated 2 months ago
- [EMNLP Main 2026]VTC-R1: Vision-Text Compression for Efficient Long-Context Reasoning.☆26Jul 20, 2026Updated last month
- NeurIPS 2025☆16Feb 4, 2026Updated 6 months ago
- EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systems (ICLR'26)☆28Nov 3, 2025Updated 9 months ago
- Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting—ICCV'25☆20Mar 6, 2025Updated last year
- ☆25Apr 8, 2026Updated 4 months ago
- [ACM MM 2026] MemGUI-Bench: Benchmarking Memory of Mobile GUI Agents in Dynamic Environments☆48Aug 11, 2026Updated 2 weeks ago
- CANDI: Continuous and Discrete Diffusion☆28Oct 27, 2025Updated 9 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- The data and code of the paper "Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction" (AAA…☆32Nov 26, 2025Updated 8 months ago
- ☆11Oct 2, 2024Updated last year
- The official implementation of paper "Towards Synergistic Path-based Explanations for Knowledge Graph Completion: Exploration and Evaluat…☆15Feb 28, 2025Updated last year
- ☆40May 30, 2025Updated last year
- (ICML 2024) PyTorch implementation of "Self-Attention through Kernel-Eigen Pair Sparse Variational Gaussian Processes"☆16Oct 15, 2024Updated last year
- Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information☆34May 14, 2026Updated 3 months ago
- This codebase is to reproduce the results of the paper "Grounded Test-Time Adaptation for LLM Agents".☆18Mar 4, 2026Updated 5 months ago
- DLLM-Searcher has been accepted by SIGIR 2026! 🥳☆34Jan 23, 2026Updated 7 months ago
- Official repo for "REX-RAG: Reasoning Exploration with Policy Correction in Retrieval-Augmented Generation"☆35Sep 28, 2025Updated 10 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Implementation of SLIM, a framework of dynamics skill lifecycle management for agentic reinforcement learning☆22May 12, 2026Updated 3 months ago
- ☆16Aug 11, 2025Updated last year
- [EMNLP 2025] The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"☆106Apr 21, 2026Updated 4 months ago
- verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in…☆2,251Jun 9, 2026Updated 2 months ago
- [ECCV 2026] VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs☆17Feb 3, 2026Updated 6 months ago
- ☆43Jun 17, 2026Updated 2 months ago
- ☆35Apr 22, 2026Updated 4 months ago