pith. sign in

InftyThink+ : Effective and efficient infinite-horizon reasoning via reinforcement learning

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

1 Pith paper citing it

fields

cs.AI 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

MEMENTO: Teaching LLMs to Manage Their Own Context

cs.AI · 2026-04-10 · unverdicted · novelty 6.0

MEMENTO trains LLMs to segment reasoning into blocks, generate mementos as dense summaries, and reason forward using only mementos and KV states, cutting peak KV cache by ~2.5x while preserving benchmark accuracy.

citing papers explorer

Showing 1 of 1 citing paper.

  • MEMENTO: Teaching LLMs to Manage Their Own Context cs.AI · 2026-04-10 · unverdicted · none · ref 32 · internal anchor

    MEMENTO trains LLMs to segment reasoning into blocks, generate mementos as dense summaries, and reason forward using only mementos and KV states, cutting peak KV cache by ~2.5x while preserving benchmark accuracy.