1 link tagged with all of: agents + legal agents + lab + wake sleep
Click any tag below to further narrow down your results
Links
@nikogrupen on X
This post describes applying the wake-sleep learning algorithm to long-horizon legal agents, where the agent works on tasks online and a review model writes reusable lessons offline. Tested on Harvey's Legal Agent Benchmark, the approach raised all-pass rates and cut cost per task by letting the agent retrieve only relevant lessons.
- Wake-sleep lifted the all-pass rate from 2.9% for a vanilla agent to 15.7% across 196 Corporate M&A and Capital Markets tasks, with the biggest gains in early cycles.
- Lessons written offline generalized to new matter types the agent never saw in training, not just familiar ones.
- Retrieving only task-relevant lessons halved cost per task while keeping rubric pass rates roughly the same.