# Large Language Models, and LLM-Based Agents, Should Be Used to Enhance the Digital Public Sphere

arXiv: https://arxiv.org/abs/2410.12123 · HTML: https://mlsanity.com/paper/2410.12123/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agentic recommender systems, one of 16 directions in LLM agents and tool use.
- Builds on 35 of its 97 references that are in the map.
- First posted on arXiv 15 Oct 2024.

## Placed in

- LLM agents and tool use / [Agentic recommender systems](https://mlsanity.com/agents/agentic-recommender-systems/)

## Builds on (most cited first, 30 of 35)

- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [GPT-4V(ision) is a Generalist Web Agent, if Grounded](https://mlsanity.com/paper/2401.01614/) (2024)
- [InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents](https://mlsanity.com/paper/2403.02691/) (2024)
- [On the Planning Abilities of Large Language Models : A Critical Investigation](https://mlsanity.com/paper/2305.15771/) (2023)
- [Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System](https://mlsanity.com/paper/2303.14524/) (2023)
- [Recommender Systems in the Era of Large Language Models (LLMs)](https://mlsanity.com/paper/2307.02046/) (2023)
- [A Roadmap to Pluralistic Alignment](https://mlsanity.com/paper/2402.05070/) (2024)
- [How Can Recommender Systems Benefit from Large Language Models: A Survey](https://mlsanity.com/paper/2306.05817/) (2023)
- [Eliciting Human Preferences with Language Models](https://mlsanity.com/paper/2310.11589/) (2023)
- [Training Socially Aligned Language Models on Simulated Social Interactions](https://mlsanity.com/paper/2305.16960/) (2023)
- [Leveraging Large Language Models in Conversational Recommender Systems](https://mlsanity.com/paper/2305.07961/) (2023)
- [Dynamic Planning with a LLM](https://mlsanity.com/paper/2308.06391/) (2023)
- [A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)](https://mlsanity.com/paper/2404.00579/) (2024)
- [CLOVA: A Closed-Loop Visual Assistant with Tool Usage and Update](https://mlsanity.com/paper/2312.10908/) (2023)
- [Using Counterfactual Tasks to Evaluate the Generality of Analogical Reasoning in Large Language Models](https://mlsanity.com/paper/2402.08955/) (2024)
- [Algorithmic progress in language models](https://mlsanity.com/paper/2403.05812/) (2024)
- [Engagement, User Satisfaction, and the Amplification of Divisive Content on Social Media](https://mlsanity.com/paper/2305.16941/) (2023)
- [Embedding Democratic Values into Social Media AIs via Societal Objective Functions](https://mlsanity.com/paper/2307.13912/) (2023)
- [On Natural Language User Profiles for Transparent and Scrutable Recommendation](https://mlsanity.com/paper/2205.09403/) (2022)
- [From Optimizing Engagement to Measuring Value](https://mlsanity.com/paper/2008.12623/) (2020)
- [Enhancing Recommendation Diversity by Re-ranking with Large Language Models](https://mlsanity.com/paper/2401.11506/) (2024)
- [Language-Based User Profiles for Recommendation](https://mlsanity.com/paper/2402.15623/) (2024)
- [Bridging Systems: Open Problems for Countering Destructive Divisiveness across Ranking, Recommenders, and Governance](https://mlsanity.com/paper/2301.09976/) (2023)
- [ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up?](https://mlsanity.com/paper/2311.16989/) (2023)
- [Recommendation with Generative Models](https://mlsanity.com/paper/2409.15173/) (2024)
- [Exploring the Impact of Large Language Models on Recommender Systems: An Extensive Review](https://mlsanity.com/paper/2402.18590/) (2024)
- [What We Know About Using Non-Engagement Signals in Content Ranking](https://mlsanity.com/paper/2402.06831/) (2024)

## Built on by (most cited first, 1 of 1)

- [Infrastructure for AI Agents](https://mlsanity.com/paper/2501.10114/) (2025)

## Abstract (arXiv)

This paper argues that large language model-based recommenders can displace today's attention-allocation machinery. LLM-based recommenders would ingest open-web content, infer a user's natural-language goals, and present information that matches their reflective preferences. Properly designed, they could deliver personalization without industrial-scale data hoarding, return control to individuals, optimize for genuine ends rather than click-through proxies, and support autonomous attention management. Synthesizing evidence of current systems' harms with recent work on LLM-driven pipelines, we identify four key research hurdles: generating candidates without centralized data, maintaining computational efficiency, modeling preferences robustly, and defending against prompt-injection. None looks prohibitive; surmounting them would steer the digital public sphere toward democratic, human-centered values.