# Pathways of Thoughts: Multi-Directional Thinking for Long-form Personalized Question Answering

arXiv: https://arxiv.org/abs/2509.19094 · HTML: https://mlsanity.com/paper/2509.19094/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 4 of its 44 references that are in the map.
- First posted on arXiv 23 Sep 2025.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)

## Builds on (most cited first, 4 of 4)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [OptimalThinkingBench: Evaluating Over and Underthinking in LLMs](https://mlsanity.com/paper/2508.13141/) (2025)
- [Reasoning-Enhanced Self-Training for Long-Form Personalized Text Generation](https://mlsanity.com/paper/2501.04167/) (2025)
- [Learning from Natural Language Feedback for Personalized Question Answering](https://mlsanity.com/paper/2508.10695/) (2025)

## Built on by (most cited first, 5 of 5)

- [Learning Personalized Agents from Human Feedback](https://mlsanity.com/paper/2602.16173/) (2026)
- [Learning to Reason for Multi-Step Retrieval of Personal Context in Personalized Question Answering](https://mlsanity.com/paper/2602.19317/) (2026)
- [Training LLMs with Reinforcement Learning for Intent-Aware Personalized Question Answering](https://mlsanity.com/paper/2605.12645/) (2026)
- [Improving User Privacy in Personalized Generation: Client-Side Retrieval-Augmented Modification of Server-Side Generated Speculations](https://mlsanity.com/paper/2601.17569/) (2026)
- [PersonaMem-v3: Toward Omni-Platform Personal Intelligence for Holistic User Understanding, Recommendation, and Agentic Tasks](https://mlsanity.com/paper/2608.21381/) (2026)

## Abstract (arXiv)

Personalization is well studied in search and recommendation, but personalized question answering remains underexplored due to challenges in inferring preferences from long, noisy, implicit contexts and generating responses that are both accurate and aligned with user expectations. To address this, we propose Pathways of Thoughts (PoT), an inference-stage method that applies to any large language model (LLM) without task-specific fine-tuning. PoT models the thinking as an iterative decision process, where the model dynamically selects among cognitive operations such as reasoning, revision, personalization, and clarification. This enables exploration of multiple reasoning trajectories, producing diverse candidate responses that capture different perspectives. PoT then aggregates and reweights these candidates according to inferred user preferences, yielding a final personalized response that benefits from the complementary strengths of diverse reasoning paths. Experiments on the LaMP-QA benchmark show that PoT consistently outperforms competitive baselines, achieving up to a 10.8% relative improvement. Human evaluation further validates these improvements, with annotators preferring PoT in 66% of cases compared to the best-performing baseline and reporting ties in 15% of cases.