karl.pdf

N/A

KARL: Knowledge Agents via Reinforcement Learning Databricks AI Research∗ ∗ Please see Contributions for Full List We present a system for training enterprise search agents via reinforcement learning that achieves state-of-the-art performance across a diverse suite of hard-to-verify agentic search tasks. Our work makes four core contributions. First, we introduce KARLBench, a multi-capability evaluation suite spanning six distinct search regimes, including…

saved by

• Katherine Driscoll

related reading

• [2505.17373] Value-Guided Search for Efficient Chain-of-Thought Reasoningarxiv.org
• [2602.19362] LLMs Can Learn to Reason Via Off-Policy RLarxiv.org
• [2005.11401] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasksarxiv.org
• State of RL for reasoning LLMs | A. Weersaweers.de
• [2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org
• Kevin-32B: Multi-Turn RL for Writing CUDA Kernels | Cognitioncognition.ai
• [2507.19457] GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learningarxiv.org
• [2603.21972] Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipearxiv.org
• [2412.14135] Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspectivearxiv.org
• [2506.06266] Cartridges: Lightweight and general-purpose long context representations via self-studyarxiv.org
• A Taxonomy of RL Environments for LLM Agentsleehanchung.github.io
• Language Models can Solve Computer Tasksarxiv.org