PACT: From Credit Assignment to Critic Alignment
PACT realigns actor-critic training and beats GRPO and PPO on math reasoning and SWE-bench Verified.
2 stories, newest first · one card per story
PACT realigns actor-critic training and beats GRPO and PPO on math reasoning and SWE-bench Verified.
PACT benchmark tests LLM agents' rule compliance under pressure across 12 enterprise domains; top models violate rules on 6-10% of items.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views