# Temp-R1: A Unified Autonomous Agent for Complex Temporal KGQA via Reverse Curriculum Reinforcement Learning Source: [Temp-R1: A Unified Autonomous Agent for Complex Temporal KGQA via Reverse Curriculum Reinforcement Learning]() Collection index: [llms.txt]() Data updated: 2026-04-23T05:00:05.534Z Authors: Zhaoyan Gong, Zhiqiang Liu, Songze Li, Xiaoke Guo, Yuanxiang Liu, Xinle Deng, Zhizhen Liu, Lei Liang, Huajun Chen, Wen Zhang Published: 2026-01-26T09:23:53.000Z ## Abstract Temporal Knowledge Graph Question Answering (TKGQA) is inherently challenging, as it requires sophisticated reasoning over dynamic facts with multi-hop dependencies and complex temporal constraints. Existing methods rely on fixed workflows and expensive closed-source APIs, limiting flexibility and scalability. We propose Temp-R1, the first autonomous end-to-end agent for TKGQA trained through reinforcement learning. To address cognitive overload in single-action reasoning, we expand the action space with specialized internal actions alongside external action. To prevent shortcut learning on simple questions, we introduce reverse curriculum learning that trains on difficult questions first, forcing the development of sophisticated reasoning before transferring to easier cases. Our 8B-parameter Temp-R1 achieves state-of-the-art performance on MultiTQ and TimelineKGQA, improving 19.8% over strong baselines on complex questions. Our work establishes a new paradigm for autonomous temporal reasoning agents. The code is available at https://github.com/zjukg/Temp-R1. ## 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 Timeline-ICEWS (test)](): Temporal Knowledge Graph Question Answering; Timeline-ICEWS (test); Overall Accuracy: 64.2. - [Temporal Knowledge Graph Question Answering on CronQuestion KG In Domain TIMELINEKGQA (test)](): Temporal Knowledge Graph Question Answering; CronQuestion KG In Domain TIMELINEKGQA (test); Hits@1 (Overall): 0.705. - [Temporal Knowledge Graph Question Answering on MultiTQ](): Temporal Knowledge Graph Question Answering; MultiTQ; Hits@1 (Overall): 78. ## Original sources and implementation [Original paper]() [PDF]()