pith. sign in

Green card is immediately playable

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

Don't Make the LLM Read the Graph: Make the Graph Think

cs.AI · 2026-04-24 · unverdicted · novelty 5.0

Belief graphs improve LLM 2nd-order theory-of-mind performance in Hanabi when they gate action selection (100% vs 20%) but are mostly decorative as prompt context for strong models, with model-family-specific planner defiance and diminishing returns from deeper graphs.

citing papers explorer

Showing 1 of 1 citing paper.

  • Don't Make the LLM Read the Graph: Make the Graph Think cs.AI · 2026-04-24 · unverdicted · none · ref 8

    Belief graphs improve LLM 2nd-order theory-of-mind performance in Hanabi when they gate action selection (100% vs 20%) but are mostly decorative as prompt context for strong models, with model-family-specific planner defiance and diminishing returns from deeper graphs.