pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

When Can LLMs Learn to Reason with Weak Supervision?

cs.LG · 2026-04-20 · unverdicted · novelty 6.0

LLM reasoning generalization under weak RL supervision is governed by prolonged reward saturation dynamics and pre-RL reasoning faithfulness, enabled by SFT on explicit reasoning traces plus domain pre-training.

citing papers explorer

Showing 1 of 1 citing paper.

  • When Can LLMs Learn to Reason with Weak Supervision? cs.LG · 2026-04-20 · unverdicted · none · ref 8

    LLM reasoning generalization under weak RL supervision is governed by prolonged reward saturation dynamics and pre-RL reasoning faithfulness, enabled by SFT on explicit reasoning traces plus domain pre-training.