Understanding a Law Firm through Study — Engram
engram.com · 2,924 words · saved by 2 readers
Training agents to combine knowledge in weights, text memory, and search on realistic legal work.
August 17, 2026 Training agents to combine knowledge in weights, text memory, and search on realistic legal work. Written by Engram, in partnership with Harvey The agents of the future will familiarize themselves with their work in many different ways: learning knowledge and skills into weights, writing notes to themselves, and using tools to efficiently navigate the world. We’re excited to share our first results on what this would look like. In our work, we see these different forms of learning and memory as part of one end-to-end system. Integrating parametric knowledge, notes, and…
saved by
related reading
- Training a State-of-the-Art Legal Agent with Harvey | Applied Computeappliedcompute.com
- Neural Cheat Sheets: Learning to Summarize with Reinforcement Learning | Applied Computeappliedcompute.com
- Remember, Refine, Retrieve: A Context Engine for Enterprise Agents | Applied Computeappliedcompute.com
- Training a Specialist Code Search Agent with turbopufferappliedcompute.com
- Machine Studying | Jacob Xiaochen Lijacobxli.com
- Memory in the wild: how we use Context Engine on our own code | Applied Computeappliedcompute.com
- Training an Agentic Router for Optimal Cost-Performance on SWE Tasks | Applied Computeappliedcompute.com
- Continual Learning in Token Space | Lettaletta.com
- The Continual Learning Problemjessylin.com
- Why We Need Continual Learning | Andreessen Horowitza16z.com
- [2005.11401] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasksarxiv.org
- Agent Harness for Learning Thingsyoutube.com