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

Source: [Let the Agent Search: Autonomous Exploration Beats Rigid Workflows in Temporal Question Answering](<https://www.sota2.com/research/paper/69a66c512d603e6de3e3d051>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-27T05:00:12.960Z

Authors: Xufei Lv, Jiahui Yang, Haoyuan Sun, Xialin Su, Zhiliang Tian, Yifu Gao, Linbo Qiao, Houde Liu

Published: 2026-03-02T13:33:39.000Z

## 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

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Temporal Knowledge Graph Question Answering on MultiTQ (test)](<https://www.sota2.com/research/sota/temporal-knowledge-graph-question-answering-on-multitq-test.md>): Temporal Knowledge Graph Question Answering; MultiTQ (test); Hits@1 (Overall): 0.887.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.01853>)

[PDF](<https://arxiv.org/pdf/2603.01853.pdf>)