6 papers
Reinforcement Learning
Training agents end-to-end with rewards, from GRPO to deployment loops.
- Papers
- 6
- Read time
- 1.7h
- Avg length
- 17m
Agent Learning via Early Experience
Let an agent take its own (wrong) actions, watch what the environment does back, and turn those consequences into free training data — no human labels for the alternatives, no reward function required.
- Read
- 16 min
- Source
- arXiv:2510.08558
Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning
Agent-R1 reframes a tool-using LLM agent as a multi-turn Markov Decision Process and gives you a framework for training that agent end-to-end with reinforcement learning — so the model learns *when and how* to call tools from reward, instead of being prompt-engineered into it.
- Read
- 16 min
Escaping the Verifier: Learning to Reason via Demonstrations
Instead of needing a "right-answer checker" to train a reasoning model, RARO pits the model against a *critic* (its own twin) that tries to tell the model's answers apart from expert answers — and the model learns to reason just by trying to fool that critic.
- Read
- 16 min
- Source
- arXiv:2511.21667
Iterative Deployment Improves Planning Skills in LLMs
If you keep deploying an LLM, filter for the outputs that actually worked, and train the next version on them, the model bootstraps itself into a far better planner — and the authors prove this accidental "deploy → curate → retrain" loop is mathematically the same thing as reinforcement learning with a hidden reward function.
- Read
- 16 min
- Source
- arXiv:2512.24940
KARL: Knowledge Agents via Reinforcement Learning
Databricks trained a mid-size open model to beat the best frontier models at enterprise search-and-reason tasks — at a fraction of the cost — by generating its own training data with agents and post-training it with a stable, cheap off-policy RL recipe.
- Read
- 18 min
- Source
- arXiv:2508.06600
Let It Flow: Agentic Crafting on Rock and Roll — Building the ROME Model within an Open Agentic Learning Ecosystem
A full-stack open-source toolchain (training framework + sandbox + agent CLI) plus a new RL algorithm that assigns credit over "interaction chunks" instead of tokens, used to train a 30B agent model that matches 100B+ models on terminal and coding tasks.
- Read
- 22 min
- Source
- arXiv:2512.24873