Pith. sign in

Enhancing multi-step reasoning abilities of language models through direct q-function optimization.arXiv preprint arXiv:2410.09302

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.LG 2

years

2026 2

representative citing papers

rePIRL: Learn PRM with Inverse RL for LLM Reasoning

cs.LG · 2026-02-08 · conditional · novelty 4.0

rePIRL learns token-level process rewards for LLM reasoning via a guided-cost-learning-style IRL objective, and shows these rewards improve reasoning policies on math/coding benchmarks.

citing papers explorer

Showing 2 of 2 citing papers.