The underlying mechanism of self-reflection in reasoning LLMs is not yet well understood

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• what is the underlying mechanism of self-reflection in reasoning LLMs?question0.964
  Open question motivating the entire paper; identified as not yet well understood
• Reasoning LLMs trigger reflection when their internal uncertainty is highhypothesis0.853
  Core hypothesis linking internal uncertainty to self-reflection behavior, tested via probing experiments
• A linear reflection direction exists in reasoning LLMs' latent representation space that governs self-reflection behaviorclaim0.845
  Core claim of ReflCtrl that a single direction captures and controls reflection
• Self-reflection consumes 25-30% of total reasoning tokens in reasoning LLMsclaim0.834
  Empirical observation motivating the need to control reflection for inference efficiency
• Reflection in LLMsconcept0.823
  The core phenomenon studied: the ability of LLMs to evaluate and revise their own reasoning.
• When LLMs produce experience claims under self-reference, is this sophisticated simulation or genuine self-representation, and how would we tell the difference?question0.801
  The core interpretive question the paper narrows but cannot definitively answer
• The paper does not claim that the LLM itself is the source of meaning and value, only that meaning can be discerned in its output.claim0.782
  Clarification to avoid misinterpretation.
• Standardized LLM self-assessments reflect learned communication postures rather than genuine capabilities (Jackson et al. 2025)claim0.781
  Skeptical prior work motivating validation framework