Institution profile

Arcarae

Industry research
Research library1linked papers
Opportunities0open roles
Selected work

Representative Papers

MIRROR: Cognitive Inner Monologue Between Conversational Turns for Persistent Reflection and Reasoning in Conversational LLMs

May 31, 2025

This work addresses three critical failure modes of large language models (LLMs) in dialogue: acquiescence bias, neglect of salient information, and inconsistent constraint prioritization. To mitigate these issues, we propose MIRROR, a cognitive architecture comprising two synergistic modules—Thinker (featuring an introspective inner-monologue manager and a cognitive controller) and Talker—that jointly enable cross-turn reflective reasoning, memory integration, and goal-directed inference. MIRROR introduces a human-inspired parallel introspection mechanism, orchestrating modular internal reasoning, persistent cross-turn cognitive state maintenance, and tri-dimensional coordination among goals, reasoning, and memory to drive cognition-informed response generation. Evaluated on the CuRaTe safety benchmark, MIRROR achieves a 156% relative performance improvement over baselines; when integrated across multiple models, it attains a stable overall accuracy exceeding 80%, representing an average gain of 21 percentage points.

0 citationsRead paper
Recent publications

Latest Papers

MIRROR: Cognitive Inner Monologue Between Conversational Turns for Persistent Reflection and Reasoning in Conversational LLMs

May 31, 2025

This work addresses three critical failure modes of large language models (LLMs) in dialogue: acquiescence bias, neglect of salient information, and inconsistent constraint prioritization. To mitigate these issues, we propose MIRROR, a cognitive architecture comprising two synergistic modules—Thinker (featuring an introspective inner-monologue manager and a cognitive controller) and Talker—that jointly enable cross-turn reflective reasoning, memory integration, and goal-directed inference. MIRROR introduces a human-inspired parallel introspection mechanism, orchestrating modular internal reasoning, persistent cross-turn cognitive state maintenance, and tri-dimensional coordination among goals, reasoning, and memory to drive cognition-informed response generation. Evaluated on the CuRaTe safety benchmark, MIRROR achieves a 156% relative performance improvement over baselines; when integrated across multiple models, it attains a stable overall accuracy exceeding 80%, representing an average gain of 21 percentage points.

0 citationsRead paper