# Personal-Agent Mediated Recommendation with Cross-Platform User History

arXiv: https://arxiv.org/abs/2610.07588 · HTML: https://mlsanity.com/paper/2610.07588/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agentic recommender systems, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 43 references that are in the map.
- First posted on arXiv 6 Oct 2026.

## Placed in

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

## Builds on (most cited first, 16 of 16)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [LlamaRec: Two-Stage Recommendation using Large Language Models for Ranking](https://mlsanity.com/paper/2311.02089/) (2023)
- [OneRec-Think: In-Text Reasoning for Generative Recommendation](https://mlsanity.com/paper/2510.11639/) (2025)
- [Towards Agentic Recommender Systems in the Era of Multimodal Large Language Models](https://mlsanity.com/paper/2503.16734/) (2025)
- [Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directions](https://mlsanity.com/paper/2602.22680/) (2026)
- [The Next Paradigm Is User-Centric Agent, Not Platform-Centric Service](https://mlsanity.com/paper/2602.15682/) (2026)
- [RecThinker: An Agentic Framework for Tool-Augmented Reasoning in Recommendation](https://mlsanity.com/paper/2603.09843/) (2026)
- [Agentic Recommender System with Hierarchical Belief-State Memory](https://mlsanity.com/paper/2605.14401/) (2026)
- [SAGER: Self-Evolving User Policy Skills for Recommendation Agent](https://mlsanity.com/paper/2604.14972/) (2026)
- [Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems](https://mlsanity.com/paper/2607.04433/) (2026)
- [From Hidden Profiles to Governable Personalization: Recommender Systems in the Age of LLM Agents](https://mlsanity.com/paper/2604.20065/) (2026)
- [τ-Rec: A Verifiable Benchmark for Agentic Recommender Systems](https://mlsanity.com/paper/2606.10156/) (2026)
- [LLM Agents Enable User-Governed Personalization Beyond Platform Boundaries](https://mlsanity.com/paper/2605.09794/) (2026)
- [ClawRec: A Claw-Native Recommender System](https://mlsanity.com/paper/2607.23779/) (2026)
- [A Position Paper on Recommender Systems in the Era of Autonomous Agents](https://mlsanity.com/paper/2607.24822/) (2026)

## Abstract (arXiv)

Modern recommendation is shifting from platform-centric personalization toward user-governed personalization, where a personal LLM agent can act on the user's behalf across services. We formalize this emerging paradigm as Personal-Agent Mediated Recommendation: a platform recommender ranks a candidate set using platform-local information, and a personal agent uses user-authorized cross-platform history to mediate the resulting ranking and produce the final top-K slate. Such mediation is nontrivial: the platform ranking can encode strong population evidence that the personal agent cannot observe, so effective mediation must therefore balance beneficial rescues against harmful overrides. To study this trade-off, we introduce MediateRec, a benchmark that includes scalable proxy cross-platform environments and a real cross-platform test under a controlled platform-agent information boundary. To train the agent to use cross-platform history effectively, we further propose Personal Attribution Mediation Optimization (PAMO), which counterfactually masks that history to estimate personal mediation support and reallocates rank-aware advantage mass under a platform-relative value floor. We theoretically prove that PAMO preserves cutoff-level advantage mass and is locally optimal among first-order reallocations that preserve this mass without lowering average platform-relative value. Experiments on MediateRec show that personal-agent mediation enables meaningful platform corrections, yet even strong proprietary LLMs introduce non-negligible harmful overrides. PAMO consistently improves over matched outcome-only RL across seen and unseen target platforms and on the real cross-platform test, while achieving a better rescue-harm balance.