Let the Agent Search: Autonomous Exploration Beats Rigid Workflows in Temporal Question Answering

TL;DR

This paper introduces AT2QA, a training-free autonomous agent that enables large language models to perform complex temporal question answering through iterative exploration and self-correction, achieving state-of-the-art results.

Contribution

The paper presents AT2QA, a novel training-free, autonomous reasoning agent that improves temporal question answering by enabling LLMs to interact with knowledge graphs dynamically.

Findings

AT2QA surpasses previous baselines by up to 11.2 points on benchmark datasets.

The approach enables zero-shot reasoning with dynamic self-correction.

It provides a transparent audit trail for reasoning processes.

Abstract

Temporal Knowledge Graph Question Answering (TKGQA) is challenging because it requires multi-hop reasoning under complex temporal constraints. Recent LLM-based approaches have improved semantic modeling for this task, but many still rely on fixed reasoning workflows or costly post-training, which can limit adaptability and make error recovery difficult. We show that enabling an off-the-shelf Large Language Model (LLM) to determine its next action is already effective in a zero-shot setting. Based on this insight, we propose AT2QA, an Autonomous and Training-free Agent for TKG Question Answering. AT2QA empowers the LLM to iteratively interact with the TKG via a generic search tool, inherently enabling autonomous exploration and dynamic self-correction during reasoning. To further elicit the LLM's potential for complex temporal reasoning, we introduce a training-free experience mining mechanism that distills a compact few-shot demonstration library from successful self-generated trajectories. AT2QA also yields a transparent audit trail for every prediction. Experiments on three challenging benchmarks -- MultiTQ, Timeline-CronQuestion, and Timeline-ICEWS-Actor -- show that AT2QA achieves new state-of-the-art performance, surpassing the strongest baselines by 10.7, 4.9, and 11.2 absolute points, respectively. Our code is available at https://github.com/AT2QA-Official-Code/AT2QA-Official-Code