FOR-Prompting: From Objection to Revision via an Asymmetric Prompting Protocol

HE ZHANG, Anzhou Zhang, Jian Dai

Keywords: multi-agent prompting, external questioning, LLM, reasoning, prompting protocol

TL;DR: We propose FOR-Prompting, an asymmetric prompting method where an Objectioner asks question-style objections to elicit the Defender’s self-revision.

Abstract: Reasoning protocols such as Chain of Thought (CoT) and Tree of Thought (ToT) organize internal deliberation but lack an explicit mechanism for external questioning that elicits self-revision. We present FOR-Prompting (From Objection to Revision Prompting), an asymmetric protocol where a Defender proposes an answer, an Debater (Questioner) raises question-style objections with no direct fixes, and a Host optionally synthesizes the final output. Across GSM8K, FOR-Prompting matches the accuracy of CoT and consistently improves over single-prompting when evaluated under identical model backbones. On small-scale open-source models (e.g., LLaMA-3.2-1B), FOR-Prompting yields substantial gains over direct prompting and performs comparably to lightweight reasoning baselines, highlighting its promise for low-resource and on-device settings. Cross-model role-swapping further shows that performance is primarily determined by the Defender, enabling small models to act effectively as Questioners. Beyond structured math tasks, FOR-Prompting supports refinement in open-ended and multi-stage tasks: qualitative analysis shows improved exploration, coverage, and specificity, and a blind human preference study found that participants preferred FOR-Prompting outputs over strong LLM baselines in an itinerary-planning scenario. The protocol is model-agnostic and operates purely through role-structured prompting, requiring no training, access to model internals, or symmetrically strong agents. FOR-Prompting therefore enables scalable study of objection-driven reasoning and offers a practical mechanism for automated iterative refinement across both hosted and local LLMs.

Primary Area: neurosymbolic & hybrid AI systems (physics-informed, logic & formal reasoning, etc.)

Submission Number: 23659