AMATA: Adaptive Multi-Agent Trajectory Alignment for Knowledge-Intensive Question Answering

TL;DR

AMATA is a multi-agent framework that dynamically integrates external knowledge to enhance factual accuracy and interpretability in knowledge-intensive question answering.

Contribution

It introduces a novel multi-agent trajectory alignment approach with intra-trajectory and inter-agent preference learning for improved QA performance.

Findings

AMATA outperforms baseline and existing frameworks on five QA benchmarks.

The method reduces token consumption in responses.

It effectively captures cross-agent dependencies for better reasoning.

Abstract

Despite substantial advances in large language models (LLMs), generating factually consistent responses for knowledge-intensive question answering remains challenging. These difficulties are primarily due to hallucinations and the limitations of LLMs in bridging long-tail knowledge gaps. To address this, we propose AMATA, an Adaptive Multi-Agent Trajectory Alignment framework that dynamically integrates external knowledge to improve response interpretability and factual grounding. Our architecture leverages six specialized agents that collaboratively perform structured actions for complex question reasoning. We formalize multi-agent collaboration with external tools as a trajectory preference alignment problem, incorporating question-aware agent customization and inter-agent preference harmonization. AMATA introduces two principal innovations: (1) Intra-Trajectory Preference Learning, which learns objective-oriented preferences to prioritize critical agents, and (2) Inter-Agent Dependency Learning, which captures cross-agent tool dependencies through a novel dependency-aware direct preference optimization technique. Empirical results show that AMATA consistently outperforms baseline approaches, knowledge-augmented frameworks, and LLM-based trajectory systems on five established knowledge-intensive QA benchmarks. Further analysis demonstrates the efficiency of our method in reducing token consumption.