SyncAI.news, a Varaisys broadcasting
Agentic Multi-Turn Reasoning: A Fairness Approach
TT

Thanh-Dat Truong, Sankalp Pandey, Hugh Churchill, Jackson Cothren, Marios Savvides, Khoa Luu

· 1 min read

ResearcharXiv cs.AI

Agentic Multi-Turn Reasoning: A Fairness Approach

arXiv:2609.33323v1 Announce Type: new Abstract: Recent advances in Large Language Models (LLMs) have enabled agentic systems capable of solving complex tasks through multi-turn planning, tool use, verification, and memory updates. However, learning agentic systems remains difficult due to two fundamental challenges, i.e., (1) long-horizon credit assignment, where supervision is available only at the final outcome, and (2) imbalanced data distributions, where dominant data patterns bias optimization and weaken adaptation to rare but informative reasoning behaviors. In this paper, we propose Fair Multi-Level Preference Optimization (Fair-MPO or $\Phi$-MPO), a new preference optimization framework for agentic learning. We first show that Multi-Level Preference Optimization provides a principled and more computationally efficient framework for long-horizon reasoning. Then, we introduce a Fair Multi-Level Objective that addresses imbalance in agentic learning. We provide a comprehensive theoretical analysis demonstrating that our approach addresses both long-horizon reasoning and data imbalance. Our experiments on agentic reasoning benchmarks demonstrate that our approach achieves State-of-the-Art (SOTA) performance.

Original source

This story was published by arXiv cs.AI and written by Thanh-Dat Truong, Sankalp Pandey, Hugh Churchill, Jackson Cothren, Marios Savvides, Khoa Luu. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News