A curated list of awesome resources about reward construction for AI agents. This repository covers cutting-edge research, and practical guides on defining and collecting rewards to build more intelligent and aligned AI agents.
☆61Sep 1, 2025Updated last year
Alternatives and similar repositories for Awesome-Agent-RL
Users that are interested in Awesome-Agent-RL are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning☆160Aug 21, 2026Updated 3 weeks ago
- In this work, we investigate the compositionality of large language models (LLMs) in mathematical reasoning. Specifically, we construct a…☆59Mar 15, 2025Updated last year
- We introduce 'Thinking with Video', a new paradigm leveraging video generation for multimodal reasoning. Our VideoThinkBench shows that S…☆320Aug 23, 2026Updated 3 weeks ago
- ☆146Aug 31, 2026Updated last week
- We propose Reinforcement Learning from Community Feedback (RLCF), a training paradigm that uses large-scale community signals as supervis…☆432Jul 22, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- A multi-device environment for evaluating intelligent vehicle interaction across connected cockpit systems☆25Sep 16, 2025Updated 11 months ago
- A benchmark for evaluating future-event forecasting from audio and video context in multimodal language models☆29Jan 22, 2026Updated 7 months ago
- A toolkit for normalizing tool-use datasets and preparing, annotating, training, and evaluating tool-using language models☆22Jul 23, 2025Updated last year
- FamilyTool benchmark☆14Sep 10, 2025Updated last year
- 启智平台的 Agent 驾驶舱：Skill + CLI，一条命令直达。Agent cockpit for the Inspire ML platform: one command, every operation, straight from chat.☆218Updated this week
- Enhanced version of original AutoGPTQ (https://github.com/PanQiWei/AutoGPTQ).☆10Nov 2, 2023Updated 2 years ago
- [arxiv: 2604.14142] From P(y|x) to P(y): Investigating Reinforcement Learning in Pre-train Space☆17Apr 16, 2026Updated 4 months ago
- ☆17Apr 10, 2024Updated 2 years ago
- ☆72Feb 4, 2026Updated 7 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.
- ☆14May 21, 2024Updated 2 years ago
- 启智平台任务管理 CLI：资源查询、任务提交、日志查看和 MCP/agent workflow☆130Updated this week
- Where Scientific Computing Meets Artificial Intellegence☆54Apr 30, 2026Updated 4 months ago
- 🏭 AI agent platform with skills for protein engineering, the noob-friendly AI tutorial tool for life science professionals. (ACL Demo202…☆248Jul 28, 2026Updated last month
- Offline implementation of LoMo: Local Modality Substitution for Deeper Vision-Language Fusion.☆25Jun 1, 2026Updated 3 months ago
- A foundation model that generates synchronized video and audio in a single model☆1,111Updated this week
- ☆18Jun 7, 2023Updated 3 years ago
- Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication☆21Mar 21, 2024Updated 2 years ago
- ☆26Jan 29, 2026Updated 7 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- 在随时断连的websocket上实现可靠的tcp隧道☆44Jun 8, 2026Updated 3 months ago
- Modified LLaVA framework for MOSS2, and makes MOSS2 a multimodal model.☆13Sep 19, 2024Updated last year
- [ICLR 2025] Language Imbalance Driven Rewarding for Multilingual Self-improving☆25Apr 6, 2026Updated 5 months ago
- [IEEE TVCG 2025] Self-supervised Learning of Event-guided Video Frame Interpolation for Rolling Shutter Frames☆12Jun 1, 2025Updated last year
- [ICML 2026] Prism: Spectral-Aware Block-Sparse Attention☆27May 22, 2026Updated 3 months ago
- Official repository for the EMNLP 2025 paper “UnifiedVisual: A Framework for Constructing Unified Vision-Language Datasets”.☆16Sep 19, 2025Updated 11 months ago
- [NeurIPS25] RULE: Reinforcement UnLEarning Achieves Forge-retain Pareto Optimality☆21Oct 22, 2025Updated 10 months ago
- [EMNLP Findings'25] Official PyTorch Implementation of Decoupled Proxy Alignment: Mitigating Language Prior Conflict for Multimodal Align…☆16Sep 19, 2025Updated 11 months ago
- Replication package of ELFuzz☆15Feb 8, 2026Updated 7 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.
- [ACL 2025] "World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning." https://arxiv.org/abs/2503.1…☆18Jul 22, 2025Updated last year
- ☆16Mar 31, 2026Updated 5 months ago
- R1V, trained with AI feedback, answers open-ended visual questions.☆14Apr 12, 2025Updated last year
- 方便扩展的Cuda算子理解和优化框架，仅用在学习使用☆18Jun 13, 2024Updated 2 years ago
- ☆13Jan 14, 2025Updated last year
- ☆14Nov 25, 2025Updated 9 months ago
- Performance analysis of predictive (alpha) factors☆28Jul 25, 2025Updated last year