# Semantic Commit: Helping Users Update Intent Specifications for AI Memory at Scale

arXiv: https://arxiv.org/abs/2504.09283 · HTML: https://mlsanity.com/paper/2504.09283/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 123 references that are in the map.
- First posted on arXiv 12 Apr 2025.

## Builds on (most cited first, 30 of 39)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [Co-Writing Screenplays and Theatre Scripts with Language Models: An Evaluation by Industry Professionals](https://mlsanity.com/paper/2209.14958/) (2022)
- [Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences](https://mlsanity.com/paper/2404.12272/) (2024)
- [To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-making](https://mlsanity.com/paper/2102.09692/) (2021)
- [ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing](https://mlsanity.com/paper/2309.09128/) (2023)
- [The Metacognitive Demands and Opportunities of Generative AI](https://mlsanity.com/paper/2312.10893/) (2023)
- [Concept Induction: Analyzing Unstructured Text with High-Level Concepts Using LLooM](https://mlsanity.com/paper/2404.12259/) (2024)
- [Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration](https://mlsanity.com/paper/2412.15701/) (2024)
- [Grounding Gaps in Language Model Generations](https://mlsanity.com/paper/2311.09144/) (2023)
- [VISAR: A Human-AI Argumentative Writing Assistant with Visual Programming and Rapid Draft Prototyping](https://mlsanity.com/paper/2304.07810/) (2023)
- [Need Help? Designing Proactive AI Assistants for Programming](https://mlsanity.com/paper/2410.04596/) (2024)
- [Advancing Requirements Engineering through Generative AI: Assessing the Role of LLMs](https://mlsanity.com/paper/2310.13976/) (2023)
- [Cocoa: Co-Planning and Co-Execution with AI Agents](https://mlsanity.com/paper/2412.10999/) (2024)
- [Beyond the Chat: Executable and Verifiable Text-Editing with LLMs](https://mlsanity.com/paper/2309.15337/) (2023)
- [Aligning Language Models with Demonstrated Feedback](https://mlsanity.com/paper/2406.00888/) (2024)
- [Assistance or Disruption? Exploring and Evaluating the Design and Trade-offs of Proactive AI Programming Support](https://mlsanity.com/paper/2502.18658/) (2025)
- [Investigating Reasons for Disagreement in Natural Language Inference](https://mlsanity.com/paper/2209.03392/) (2022)
- ["My agent understands me better": Integrating Dynamic Human-like Memory Recall and Consolidation in LLM-Based Agents](https://mlsanity.com/paper/2404.00573/) (2024)
- [Improving Steering and Verification in AI-Assisted Data Analysis with Interactive Task Decomposition](https://mlsanity.com/paper/2407.02651/) (2024)
- [Navigating Rifts in Human-LLM Grounding: Study and Benchmark](https://mlsanity.com/paper/2503.13975/) (2025)
- [What Should We Engineer in Prompts? Training Humans in Requirement-Driven LLM Use](https://mlsanity.com/paper/2409.08775/) (2024)
- [RELIC: Investigating Large Language Model Responses using Self-Consistency](https://mlsanity.com/paper/2311.16842/) (2023)
- [The Future of AI-Driven Software Engineering](https://mlsanity.com/paper/2406.07737/) (2024)
- [Rambler: Supporting Writing With Speech via LLM-Assisted Gist Manipulation](https://mlsanity.com/paper/2401.10838/) (2024)
- [Exploring the Design Space of Cognitive Engagement Techniques with AI-Generated Code for Enhanced Learning](https://mlsanity.com/paper/2410.08922/) (2024)
- [Leveraging LLMs for the Quality Assurance of Software Requirements](https://mlsanity.com/paper/2408.10886/) (2024)
- [Beyond Code Generation: LLM-supported Exploration of the Program Design Space](https://mlsanity.com/paper/2503.06911/) (2025)
- [Lessons from the Use of Natural Language Inference (NLI) in Requirements Engineering Tasks](https://mlsanity.com/paper/2405.05135/) (2024)

## Built on by (most cited first, 3 of 3)

- [LLM-Augmented Semantic Steering of Text Embedding Projection Spaces](https://mlsanity.com/paper/2605.01957/) (2026)
- [CogInstrument: Modeling Cognitive Processes for Bidirectional Human-LLM Alignment in Planning Tasks](https://mlsanity.com/paper/2604.10587/) (2026)
- [Intent Graph: Navigating the Analytical Reasoning Space for Exploratory Data Analysis](https://mlsanity.com/paper/2610.11025/) (2026)

## Abstract (arXiv)

How do we update AI memory of user intent as intent changes? We consider how an AI interface may assist the integration of new information into a repository of natural language data. Inspired by software engineering concepts like impact analysis, we develop methods and a UI for managing semantic changes with non-local effects, which we call "semantic conflict resolution." The user commits new intent to a project -- makes a "semantic commit" -- and the AI helps the user detect and resolve semantic conflicts within a store of existing information representing their intent (an "intent specification"). We develop an interface, SemanticCommit, to better understand how users resolve conflicts when updating intent specifications such as Cursor Rules and game design documents. A knowledge graph-based RAG pipeline drives conflict detection, while LLMs assist in suggesting resolutions. We evaluate our technique on an initial benchmark. Then, we report a 12 user within-subjects study of SemanticCommit for two task domains -- game design documents, and AI agent memory in the style of ChatGPT memories -- where users integrated new information into an existing list. Half of our participants adopted a workflow of impact analysis, where they would first flag conflicts without AI revisions then resolve conflicts locally, despite having access to a global revision feature. We argue that AI agent interfaces, such as software IDEs like Cursor and Windsurf, should provide affordances for impact analysis and help users validate AI retrieval independently from generation. Our work speaks to how AI agent designers should think about updating memory as a process that involves human feedback and decision-making.