A cycle of solver, adversarial flawed-chain challenger, and feedback agent optimizes CoT prompts to raise accuracy and cut run-to-run answer variability within two to three cycles.
Your language model may think too rigidly: Achieving reasoning consistency with symmetry-enhanced training
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
CAP-CoT improves LLM reasoning accuracy and stability by iteratively refining solver prompts via contrast with adversarially generated flawed reasoning chains.
citing papers explorer
-
CAP-CoT: Cycle Adversarial Prompt for Improving Chain of Thoughts in LLM Reasoning
A cycle of solver, adversarial flawed-chain challenger, and feedback agent optimizes CoT prompts to raise accuracy and cut run-to-run answer variability within two to three cycles.
-
Partial exploiters sustain cooperation: the hump-shaped strategy stably coexists with unconditional cooperators
CAP-CoT improves LLM reasoning accuracy and stability by iteratively refining solver prompts via contrast with adversarially generated flawed reasoning chains.