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

2026-04-22

AI Summary

This work addresses the susceptibility of large language models to logical inertia in non-interactive reasoning, where premature and incomplete assumptions often lead to unstable conclusions. To mitigate this issue, the authors propose the SABA framework, which uniquely integrates an active self-awareness mechanism into the reasoning process. SABA constructs a verifiable foundational state through information fusion and employs query-driven, structured reasoning that recursively alternates between hypothesis completion, state refinement, and resolution of reasoning obstacles. Evaluated on a non-interactive detective puzzle benchmark spanning all difficulty levels, SABA achieves state-of-the-art performance and demonstrates consistent superiority across multiple established reasoning benchmarks, effectively alleviating the problem of logical inertia.

Technology Category

• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• self-awareness
• logical inertia
• reasoning completeness
• premise awareness
• large language models

Innovation

• self-awareness
• logical inertia
• structured reasoning
• information fusion
• query-driven reasoning