pith. sign in

Learning when to think: Shaping adaptive reasoning in r1-style models via multi-stage RL

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

2 Pith papers citing it

citation-role summary

baseline 1

citation-polarity summary

fields

cs.CL 1 cs.LG 1

years

2026 2

verdicts

UNVERDICTED 2

roles

baseline 1

polarities

baseline 1

representative citing papers

CODA: Difficulty-Aware Compute Allocation for Adaptive Reasoning

cs.CL · 2026-03-09 · unverdicted · novelty 6.0

CODA uses rollout-based difficulty signals to drive two gates that penalize verbosity on easy instances and promote deliberation on hard ones, cutting token use over 60% on simple tasks while maintaining accuracy.

citing papers explorer

Showing 2 of 2 citing papers.