pith. sign in

What can you do when you have zero rewards during rl?

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

2 Pith papers citing it

citation-role summary

method 1

citation-polarity summary

fields

cs.LG 2

years

2026 2

verdicts

UNVERDICTED 2

roles

method 1

polarities

use method 1

representative citing papers

Learning, Fast and Slow: Towards LLMs That Adapt Continually

cs.LG · 2026-05-12 · unverdicted · novelty 7.0 · 2 refs

Fast-Slow Training uses context optimization as fast weights alongside parameter updates as slow weights to achieve up to 3x better sample efficiency, higher performance, and less catastrophic forgetting than standard RL in continual LLM learning.

Scaling Self-Play with Self-Guidance

cs.LG · 2026-04-22 · unverdicted · novelty 6.0

SGS adds self-guidance to LLM self-play for Lean4 theorem proving, surpassing RL baselines and enabling a 7B model to outperform a 671B model after 200 rounds.

citing papers explorer

Showing 2 of 2 citing papers.

  • Learning, Fast and Slow: Towards LLMs That Adapt Continually cs.LG · 2026-05-12 · unverdicted · none · ref 43 · 2 links

    Fast-Slow Training uses context optimization as fast weights alongside parameter updates as slow weights to achieve up to 3x better sample efficiency, higher performance, and less catastrophic forgetting than standard RL in continual LLM learning.

  • Scaling Self-Play with Self-Guidance cs.LG · 2026-04-22 · unverdicted · none · ref 25

    SGS adds self-guidance to LLM self-play for Lean4 theorem proving, surpassing RL baselines and enabling a 7B model to outperform a 671B model after 200 rounds.