Self-Awareness before Action: Mitigating Logical Inertia via Proactive Cognitive Awareness

TL;DR

This paper introduces SABA, a reasoning framework for large language models that enhances self-awareness of missing premises, leading to improved reasoning stability and accuracy across various benchmarks.

Contribution

SABA is a novel recursive reasoning approach that explicitly models self-awareness of incomplete knowledge to mitigate logical errors in LLM reasoning.

Findings

SABA achieves top performance on all difficulty levels of the Detective Puzzle benchmark.

SABA outperforms existing methods on multiple public reasoning benchmarks.

Explicit self-awareness improves reasoning stability and accuracy.

Abstract

Large language models perform well on many reasoning tasks, yet they often lack awareness of whether their current knowledge or reasoning state is complete. In non-interactive puzzle settings, the narrative is fixed and the underlying structure is hidden; once a model forms an early hypothesis under incomplete premises, it can propagate that error throughout the reasoning process, leading to unstable conclusions. To address this issue, we propose SABA, a reasoning framework that explicitly introduces self-awareness of missing premises before making the final decision. SABA formulates reasoning as a recursive process that alternates between structured state construction and obstacle resolution: it first applies Information Fusion to consolidate the narrative into a verifiable base state, and then uses Query-driven Structured Reasoning to identify and resolve missing or underspecified premises by turning them into queries and progressively completing the reasoning state through hypothesis construction and state refinement. Across multiple evaluation metrics, SABA achieves the best performance on all three difficulty splits of the non-interactive Detective Puzzle benchmark, and it also maintains leading results on multiple public benchmarks.