Outcome RL gains are mostly finishing and reliability, not reach
On four physics and math sets, newly solved problems add at most 2.1 points, and only 3.5% of 144 unique physics solves held up.
Stories per day · 30 days
3 stories, newest first · one card per story
Stories tagged #pass-at-k
Beyond Repeated Sampling: Learning Search Policies for LLM Reasoning
An RL-trained concept generator lifts a frozen LLM's pass@k on hard math versus repeated sampling.
Difficulty-Adaptive Tree-Structured Policy Optimization for Expanding Reasoning Coverage in RLVR
Researchers propose DATPO, a difficulty-adaptive tree-structured RLVR training method that expands reasoning coverage (pass@k) and improves test-time scaling on math benchmarks.