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

arXiv: https://arxiv.org/abs/2603.01853 · HTML: https://mlsanity.com/paper/2603.01853/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 20 of its 39 references that are in the map.
- First posted on arXiv 2 Mar 2026.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)
- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 20 of 20)

- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?](https://mlsanity.com/paper/2504.13837/) (2025)
- [Knowledge Graphs](https://mlsanity.com/paper/2003.02320/) (2020)
- [Learning Sequence Encoders for Temporal Knowledge Graph Completion](https://mlsanity.com/paper/1809.03202/) (2018)
- [Question Answering Over Temporal Knowledge Graphs](https://mlsanity.com/paper/2106.01515/) (2021)
- [Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs](https://mlsanity.com/paper/2410.23875/) (2024)
- [Complex Temporal Question Answering on Knowledge Graphs](https://mlsanity.com/paper/2109.08935/) (2021)
- [Temporal Knowledge Graph Completion: A Survey](https://mlsanity.com/paper/2201.08236/) (2022)
- [Training-Free Group Relative Policy Optimization](https://mlsanity.com/paper/2510.08191/) (2025)
- [TEQUILA: Temporal Question Answering over Knowledge Bases](https://mlsanity.com/paper/1908.03650/) (2019)
- [Temporal Knowledge Question Answering via Abstract Reasoning Induction](https://mlsanity.com/paper/2311.09149/) (2023)
- [MemoTime: Memory-Augmented Temporal Knowledge Graph Enhanced Large Language Model Reasoning](https://mlsanity.com/paper/2510.13614/) (2025)
- [Rewarding Graph Reasoning Process makes LLMs more Generalized Reasoners](https://mlsanity.com/paper/2503.00845/) (2025)
- [Improving Embedded Knowledge Graph Multi-hop Question Answering by introducing Relational Chain Reasoning](https://mlsanity.com/paper/2110.12679/) (2021)
- [Self-Improvement Programming for Temporal Knowledge Graph Question Answering](https://mlsanity.com/paper/2404.01720/) (2024)
- [TimelineKGQA: A Comprehensive Question-Answer Pair Generator for Temporal Knowledge Graphs](https://mlsanity.com/paper/2501.04343/) (2025)
- [Temp-R1: A Unified Autonomous Agent for Complex Temporal KGQA via Reverse Curriculum Reinforcement Learning](https://mlsanity.com/paper/2601.18296/) (2026)
- [Plan of Knowledge: Retrieval-Augmented Large Language Models for Temporal Knowledge Graph Question Answering](https://mlsanity.com/paper/2511.04072/) (2025)
- [TKG-Thinker: Towards Dynamic Reasoning over Temporal Knowledge Graphs via Agentic Reinforcement Learning](https://mlsanity.com/paper/2602.05818/) (2026)

## Abstract (arXiv)

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