CogInstrument: Modeling Cognitive Processes for Bidirectional Human-LLM Alignment in Planning Tasks

TL;DR

CogInstrument is a novel system that externalizes and visualizes human reasoning structures as editable motifs, improving bidirectional alignment and trust in human-LLM planning tasks.

Contribution

It introduces cognitive motifs as a new formalism for representing and editing reasoning processes, enhancing human-LLM collaboration.

Findings

Explicitly surfaces implicit reasoning structures

Facilitates targeted revision and reusability

Enhances user agency and trust

Abstract

Although Large Language Models (LLMs) demonstrate proficiency in knowledge-intensive tasks, current interfaces frequently precipitate cognitive misalignment by failing to externalize users' underlying reasoning structures. Existing tools typically represent intent as "flat lists," thereby disregarding the causal dependencies and revisable assumptions inherent in human decision-making. We introduce CogInstrument, a system that represents user reasoning through cognitive motifs-compositional, revisable units comprising concepts linked by causal dependencies. CogInstrument extracts these motifs from natural language interactions and renders them as editable graphical structures to facilitate bidirectional alignment. This structural externalization enables both the user and the LLM to inspect, negotiate, and reconcile reasoning processes iteratively. A within-subjects study (N=12) demonstrates that CogInstrument explicitly surfaces implicit reasoning structures, facilitating more targeted revision and reusability over conventional LLM-based dialogue interfaces. By enabling users to verify the logical grounding of LLM outputs, CogInstrument significantly enhances user agency, trust, and structural control over the collaboration. This work formalizes cognitive motifs as a fundamental unit for human-LLM alignment, providing a novel framework for achieving structured, reasoning-based human-AI collaboration.