elder-plinius/CL4R1T4S
CL4R1T4S is a project that provides transparency by collecting and sharing the hidden system prompts and guidelines used by major AI models and agents to promote trust and understanding of AI behavior.
Awesome AI Agents › LLM Research Repositories
xhyumiracle/Awesome-AgenticLLM-RL-Papers
This repository is the official companion to the survey paper The Landscape of Agentic Reinforcement Learning for LLMs, published in Transactions on Machine Learning Research with a Survey Certification and available on arXiv and Hugging Face. It provides the BibTeX citation for the survey and turns its sections into browsable reference material, most notably the section on agentic reinforcement learning algorithms. That section is a large comparison table in which each method is described by year, objective type, whether it clips the policy ratio to keep updates stable, whether and how it applies a KL penalty against a reference policy, its key mechanism, the kind of learning signal it consumes, and links to the paper plus any released code, model checkpoints or project website. Methods are grouped into families: the PPO family with PPO, VAPO, PF-PPO, VinePPO and PSGPO; the DPO family with DPO, beta-DPO, SimPO, IPO, KTO, ORPO, Step-DPO and LCPO; and the GRPO family with GRPO, DAPO, LUFFY, GSPO, GMPO, ProRL, Posterior-GRPO, Dr.GRPO, Step-GRPO, SRPO, GRESO and StarPO. Annotations record the distinguishing idea behind each variant, such as adaptive KL penalties with variance control, policy filtration under noisy rewards, unbiased value estimates, process supervision, dynamic KL coefficients, sequence-level clipping, geometric means of token-level rewards, reference policy resets, pre-rollout filtering and multi-turn reasoning-guided actions. The signal column separates plain reward, human preference, process or step-wise reward, group-based reward and mixed on-policy plus off-policy variants. The repository is aimed at researchers and engineers working on reinforcement learning for LLM agents who need a single map of the algorithm space together with pointers to reproducible implementations.
https://github.com/xhyumiracle/Awesome-AgenticLLM-RL-Papers
Also in LLM Research Repositories
WooooDyy/LLM-Agent-Paper-List
A comprehensive repository compiling essential academic papers and a detailed survey on the rise, framework, applications, and societal aspects of Large Language Model based AI agents.
mahseema/awesome-ai-tools
A curated repository listing top Artificial Intelligence tools across various categories including generative AI, chatbots, search engines, and writing assistants.
filipecalegario/awesome-generative-ai
A curated and comprehensive list of Generative AI tools, projects, models, artworks, and educational resources, regularly updated to reflect the latest advancements in the field.
DSXiangLi/DecryptPrompt
DecryptPrompt is a comprehensive resource hub that summarizes prompt and LLM research papers, open-source datasets and models, and AIGC applications, providing in-depth tutorials and analyses for AI researchers and practitioners.
zjunlp/LLMAgentPapers
LLMAgentPapers is a curated repository of essential academic papers on Large Language Model agents, covering topics from agent personality to multi-agent systems and applications.
luo-junyu/Awesome-Agent-Papers
A comprehensive and up-to-date research collection of papers on Large Language Model (LLM) agents, covering methodologies, applications, challenges, and key categories such as construction, collaboration, evolution, tools, security, benchmarks, and real-world applications.
webfuse-com/awesome-autoresearch
Curated index of autonomous improvement loops and research-agent systems descended from karpathy/autoresearch, grouped into general-purpose forks, research systems, platform ports, domain adaptations and benchmarks.