pith. machine review for the scientific record. sign in

Recursive introspection: Teaching language model agents how to self-improve.Advances in Neural Information Processing Systems, 37:55249–55285

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

Confidence-Aware Alignment Makes Reasoning LLMs More Reliable

cs.AI · 2026-05-08 · unverdicted · novelty 6.0

CASPO trains LLMs via iterative direct preference optimization so that token-level confidence tracks step-wise correctness, then applies Confidence-aware Thought pruning at inference to improve both reliability and speed on reasoning benchmarks.

citing papers explorer

Showing 1 of 1 citing paper.

  • Confidence-Aware Alignment Makes Reasoning LLMs More Reliable cs.AI · 2026-05-08 · unverdicted · none · ref 37

    CASPO trains LLMs via iterative direct preference optimization so that token-level confidence tracks step-wise correctness, then applies Confidence-aware Thought pruning at inference to improve both reliability and speed on reasoning benchmarks.