pith. machine review for the scientific record. sign in

Reflexion: language agents with verbal reinforcement learning

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

2 Pith papers citing it

fields

cs.AI 2

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

Counterfactual Trace Auditing of LLM Agent Skills

cs.AI · 2026-05-12 · unverdicted · novelty 7.0

CTA framework detects 522 skill influence patterns in LLM agent traces across 49 tasks where average pass rate shifts only +0.3%, exposing evaluation gaps in behavioral effects like template copying and excess planning.

citing papers explorer

Showing 2 of 2 citing papers.