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

• URL: http://arxiv.org/abs/2601.18296v1
• Date: Mon, 26 Jan 2026 09:23:53 GMT
• Title: Temp-R1: A Unified Autonomous Agent for Complex Temporal KGQA via Reverse Curriculum Reinforcement Learning
• Authors: Zhaoyan Gong, Zhiqiang Liu, Songze Li, Xiaoke Guo, Yuanxiang Liu, Xinle Deng, Zhizhen Liu, Lei Liang, Huajun Chen, Wen Zhang,
• Abstract summary: 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.<n>We propose Temp-R1, the first autonomous end-to-end agent for TKGQA trained through reinforcement learning.<n>Our 8B- parameter Temp-R1 achieves state-of-the-art performance on MultiTQ and TimelineKGQA, improving 19.8% over strong baselines on complex questions.
• Score: 51.79753403262177
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Let the Agent Search: Autonomous Exploration Beats Rigid Workflows in Temporal Question Answering [12.204337131764852]
  Temporal Knowledge Graph Question Answering (TKGQA) demands multi-hop reasoning under temporal constraints.<n>We show that granting an off-the-shelf autonomy, that is, letting it decide what to do next, already yields substantial gains.<n>We propose AT2QA, an autonomous, training-free agent for temporal question answering.
  arXiv  Detail & Related papers  (2026-03-02T13:33:39Z)
• TKG-Thinker: Towards Dynamic Reasoning over Temporal Knowledge Graphs via Agentic Reinforcement Learning [22.089705008812217]
  Temporal knowledge graph question answering (TKGQA) aims to answer time-sensitive questions by leveraging temporal knowledge bases.<n>Current prompting strategies constrain their efficacy in two primary ways.<n>We propose textbfTKG-Thinker, a novel agent equipped with autonomous planning and adaptive retrieval capabilities.
  arXiv  Detail & Related papers  (2026-02-05T16:08:36Z)
• KnowCoder-A1: Incentivizing Agentic Reasoning Capability with Outcome Supervision for KBQA [55.26634094204971]
  Knowledge Base Question Answering (KBQA) aims to answer natural-language questions over a structured Knowledge Base (KB)<n>Recent work improves KBQA by adopting an agentic reasoning paradigm, in which Large Language Models (LLMs) iteratively decompose a question, generate its corresponding logical queries, and interact with the KB to derive the answer.<n>We propose KnowCoder-A1, an LLM that can autonomously perform agentic reasoning on KBs to obtain answers.
  arXiv  Detail & Related papers  (2025-10-29T02:12:18Z)
• RTQA : Recursive Thinking for Complex Temporal Knowledge Graph Question Answering with Large Language Models [46.789791710884835]
  RTQA is a novel framework for enhancing reasoning over TKGs without requiring training.<n>It decomposes questions into sub-problems, solves them bottom-up using LLMs and TKG knowledge, and employs multi-path answer aggregation to improve fault tolerance.<n>Experiments on MultiTQ and TimelineKGQA benchmarks demonstrate significant Hits@1 improvements in "Multiple" and "Complex" categories, outperforming state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-09-04T08:25:01Z)
• Living in the Moment: Can Large Language Models Grasp Co-Temporal Reasoning? [70.19200858203388]
  Temporal reasoning is fundamental for large language models to comprehend the world. CoTempQA is a benchmark containing four co-temporal scenarios. Our experiments reveal a significant gap between the performance of current LLMs and human-level reasoning.
  arXiv  Detail & Related papers  (2024-06-13T12:56:21Z)
• Self-Improvement Programming for Temporal Knowledge Graph Question Answering [31.33908040172437]
  Temporal Knowledge Graph Question Answering (TKGQA) aims to answer questions with temporal intent over Temporal Knowledge Graphs (TKGs) Existing end-to-end methods implicitly model the time constraints by learning time-aware embeddings of questions and candidate answers. We introduce a novel self-improvement Programming method for TKGQA (Prog-TQA)
  arXiv  Detail & Related papers  (2024-04-02T08:14:27Z)
• ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent [50.508669199496474]
  We develop a ReAct-style LLM agent with the ability to reason and act upon external knowledge. We refine the agent through a ReST-like method that iteratively trains on previous trajectories. Starting from a prompted large model and after just two iterations of the algorithm, we can produce a fine-tuned small model.
  arXiv  Detail & Related papers  (2023-12-15T18:20:15Z)
• Towards Robust Temporal Reasoning of Large Language Models via a Multi-Hop QA Dataset and Pseudo-Instruction Tuning [73.51314109184197]
  It is crucial for large language models (LLMs) to understand the concept of temporal knowledge. We propose a complex temporal question-answering dataset Complex-TR that focuses on multi-answer and multi-hop temporal reasoning.
  arXiv  Detail & Related papers  (2023-11-16T11:49:29Z)
• AutoSTL: Automated Spatio-Temporal Multi-Task Learning [17.498339023562835]
  We propose a scalable architecture consisting of advanced-temporal operations to exploit the dependency between tasks. Our model automatically allocates operations the intrinsic fusion weight. As we can know AutoSTL is the first automated-temporal multi-task- learning method.
  arXiv  Detail & Related papers  (2023-04-16T10:03:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.