Agents & RL Sep 2025 · #21 most cited · 182 citations

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

Guibin Zhang et al.

arXiv:2509.02547

In short

This survey argues agentic RL is a real shift from RL-tuning LLMs: the model acts over many steps in a partially observed world instead of producing one reply. It organises over 500 works by capability (planning, tools, memory, reasoning, self-improvement) and application, and catalogues environments and frameworks.

Why it matters

The map to read first if you want to understand how agents are trained, not just prompted.

Read first

The 4 Field Guide ideas this paper leans on.

Starting from scratch? The full route 26 ideas · basics first
  1. Machine Learning ✓ understood

    Building systems that learn patterns from data instead of following hand-written rules, getting better at a task as they see more examples.

  2. Reinforcement Learning · read first ✓ understood

    Learning through interaction with an environment, receiving rewards or penalties to learn optimal behavior policies.

  3. Reward ✓ understood

    The single number an environment sends back after each action, telling a reinforcement learning agent how good that step was; the agent learns to maximize its long-run total.

  4. Agent ✓ understood

    In reinforcement learning, the learner and decision-maker that observes an environment, takes actions and adjusts its behaviour to maximize cumulative reward.

  5. Environment ✓ understood

    In RL, the world the agent interacts with, providing states, accepting actions, and returning rewards.

  6. Markov Decision Process · read first ✓ understood

    A mathematical framework for modeling sequential decision-making with states, actions, rewards, and transition probabilities.

  7. Natural Language Processing ✓ understood

    The field of AI that lets computers read, interpret, translate and generate human language, from spam filters and search to chatbots.

  8. Token ✓ understood

    The unit of text a language model reads and writes: a word, part of a word, or a character, drawn from the model's fixed vocabulary.

  9. Tokenization ✓ understood

    Splitting text into tokens, usually subword pieces, and mapping each to an integer ID so a language model can process it.

  10. Language Modeling ✓ understood

    Assigning probabilities to sequences of text, in practice by predicting each next token from the ones before it; the objective behind large language models.

  11. Dataset ✓ understood

    A collection of data examples used for training, validating, or testing machine learning models.

  12. Training ✓ understood

    The process of fitting a model to data by repeatedly measuring how wrong its outputs are and adjusting its parameters to reduce that error.

  13. Unsupervised Learning ✓ understood

    Learning from unlabeled data to discover hidden patterns, structures, or relationships without explicit target outputs.

  14. Self-Supervised Learning ✓ understood

    Training on unlabeled data by making the data supply its own answers: hide or alter part of an input and have the model predict or match it.

  15. Pre-training ✓ understood

    Training a model on a large dataset (often self-supervised) before fine-tuning on specific tasks, enabling transfer learning.

  16. Feature ✓ understood

    A single measurable property of an example, such as a house's floor area or how many links an email contains, used as an input to a model.

  17. Neural Network ✓ understood

    A model built from layers of simple units, each taking a weighted sum of its inputs and applying a nonlinearity; training adjusts the weights so the whole stack maps inputs to useful outputs.

  18. Deep Learning ✓ understood

    A subset of machine learning that uses neural networks with multiple layers (deep neural networks) to learn hierarchical representations of data.

  19. Representation Learning ✓ understood

    Letting a model learn its own internal description of the data, such as embeddings or layered visual features, instead of relying on features designed by hand.

  20. Embedding ✓ understood

    A list of numbers (a vector) that represents a word, sentence, image or other item, learned so that similar items end up close together.

  21. Attention Mechanism ✓ understood

    A technique that lets a neural network weigh every part of its input when producing each output, focusing on the parts most relevant at that step.

  22. Transformer ✓ understood

    A neural network architecture, introduced in 2017, built from stacked self-attention and feed-forward layers; the basis of nearly every modern large language model.

  23. Large Language Model · read first ✓ understood

    A neural network, almost always a transformer, trained on vast amounts of text to predict the next token, which lets it write, answer, summarize and follow instructions.

  24. Context Window ✓ understood

    The maximum number of tokens a language model can take into account at once, counting both the input it reads and the output it writes. Also called context length.

  25. Tool Use ✓ understood

    A language model asking the application around it to run a function, such as search, a calculator or an API, then using the result in its answer.

  26. AI Agent · read first ✓ understood

    A system where a large language model decides its own next steps in a loop: calling tools, reading the results, and continuing until the task is done.

In the frontier

Rank
#21 of 100
Citations
182
as of Aug 9, 2026
Published
Sep 2025

Topics: RL for reasoning , Agent training and self-evolution , Agent benchmarks and computer use

Selection: 1kpapers.com by Together AI, most-cited as of Aug 9, 2026

Nearby papers

Summary in our own words; read the paper for the details. ← All papers