Temp-R1: A Unified Autonomous Agent for Complex Temporal KGQA via Reverse Curriculum Reinforcement Learning

2026-01-26

AI Summary

This work addresses the dynamic reasoning challenges in temporal knowledge graph question answering, particularly those arising from multi-hop dependencies and complex temporal constraints. To this end, the authors propose Temp-R1, the first end-to-end autonomous agent for temporal reasoning. Built upon an 8B-parameter large language model, Temp-R1 introduces a reverse-curriculum reinforcement learning mechanism—training from hard to easy examples to suppress shortcut learning—and designs an expanded action space that integrates internal reasoning with external tool invocation. This framework establishes a novel paradigm for autonomous temporal reasoning. Evaluated on the MultiTQ and TimelineKGQA benchmarks, Temp-R1 achieves state-of-the-art performance, improving accuracy on complex questions by 19.8% over strong baselines.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Planning, Routing, and Scheduling: Temporal Planning
• Multiagent Systems: Multiagent Learning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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. Our code will be publicly available soon at https://github.com/zjukg/Temp-R1.

Problem

• Temporal Knowledge Graph Question Answering
• multi-hop reasoning
• temporal constraints
• autonomous agent
• complex question answering

Innovation

• Temporal Knowledge Graph Question Answering
• Autonomous Agent
• Reverse Curriculum Reinforcement Learning
• Internal Action Space
• End-to-End Reasoning