{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mirror-cognitive-inner-monologue-between","title":"MIRROR: Cognitive Inner Monologue Between Conversational Turns for Persistent Reflection and Reasoning in Conversational LLMs","arxiv_id":"2506.00430","date":"2025-05-31","proceeding":null,"authors":["Nicole Hsing"],"abstract":"Human intelligence relies on inner monologue to process complex information through simultaneous reflection, memory retrieval, and response formulation. We introduce MIRROR (Modular Internal Reasoning, Reflection, Orchestration, and Response), a cognitive architecture that systematically implements these parallel reasoning capabilities in large language models. MIRROR operates as a unified system with two distinct functional layers: the Thinker and the Talker. The Thinker encompasses: (1) the Inner Monologue Manager, coordinating reasoning threads across cognitive dimensions (Goals, Reasoning, and Memory); and (2) the Cognitive Controller, synthesizing these threads into a coherent internal narrative maintained across conversation turns. The Talker component then leverages this integrated narrative for context-aware responses. Evaluated on the CuRaTe benchmark--testing personalized dialogue with safety-critical constraints, conflicting preferences, and multi-turn consistency--LLMs utilizing the MIRROR architecture achieve up to 156% relative improvement in critical safety scenarios involving three persons with conflicting preferences, maintaining an average accuracy of ~>80% on all scenarios. Across scenario-specific comparisons, GPT-4o, Gemini 1.5 Pro, Claude 3.7 Sonnet, Llama 4 variants, and Mistral 3 variants with the MIRROR architecture outperformed baseline models by 21% on average (15.5 percentage points absolute). MIRROR directly addresses three critical LLM failure modes: sycophancy, attentional deficits to critical information, and inconsistent prioritization of conflicting constraints. This work bridges cognitive science and AI by implementing modular internal reasoning inspired by human cognition, creating a persistent internal model that significantly enhances multi-turn conversation capabilities.","url_abs":"https://arxiv.org/abs/2506.00430v1","url_pdf":"https://arxiv.org/pdf/2506.00430v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mirror-cognitive-inner-monologue-between","repo_url":"https://github.com/nicolehsing/MIRROR","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[{"method_slug":"llama","method_name":"LLaMA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2506.00430","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}