FIELD NOTES TOPIC
dense supervision
2 notes, newest first.
QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents
A research paper introduces QVal, a tool for evaluating dense supervision signals in long-horizon tasks for LLM agents without the need for training. The tool measures how well a method's score aligns with Q-values of…
QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents
The paper introduces QVal, a training-free testbed for evaluating dense supervision signals in long-horizon reinforcement learning tasks. QVal measures the alignment of a method's score with the Q-values of a strong…
