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
Figures & tables
Figure 2: Performance comparison on the MultiTQ benchmark. In a zero-shot setting, the autonomous LLM agent surpasses existing baselines, highlighting the efficacy of unlocking the model’s inherent decision-making capabilities.
Figure 3: Pass@k analysis of our method. In a zero-shot setting, our method achieves >84% Pass@1 accuracy. For difficult queries that initially fail, repeated sampling ( k=10 ) successfully retrieves the correct answer, suggesting the reasoning capability is present but dormant.
Figure 4: The overview of our proposed framework AT2QA. Top: At inference, an LLM agent repeatedly queries a Search tool to interact with the TKG environment until sufficient evidence is collected. Inputs include a system prompt, the question, and few-shot demonstrations. Bottom: The few-shot library is selected from candidate trajectories via training-free GRPO-style rule editing with rule-based rewards.
Method
TimelineKGQA-CronQuestion
TimelineKGQA-ICEWS-Actor
Overall
Simple
Medium
Complex
Overall
Simple
Medium
Complex
RAG Baseline
0.235
0.704
0.092
0.009
0.265
0.660
0.128
0.011
LLaMA2-7B
0.169
0.049
0.143
0.282
0.111
0.035
0.066
0.322
GPT-4o
0.206
0.069
0.130
0.376
0.113
0.051
0.035
0.353
RTQA
0.298
0.608
0.218
0.135
–
–
–
–
PoK
0.651
0.737
0.539
0.683
0.602
0.744
0.456
0.578
Table 1: Performance comparison on TimelineKGQA-CronQuestion and TimelineKGQA-ICEWS-Actor datasets. Bold indicates the best performance, and underline indicates the second best.
Method
Overall
Question Type
Answer Type
multiple
single
entity
time
TKG Embedding-based Methods
EmbedKGQA
0.206
0.134
0.235
0.290
0.001
CronKGQA
0.279
0.134
0.337
0.328
0.156
MultiQA
0.293
0.159
0.347
0.349
0.157
LLM-based Static Workflows
Table 2: Performance comparison on the MultiTQ test set. Bold indicates the best performance, and underline indicates the second best.
Figure 5: Effect of the maximum interaction rounds Tmax on MultiTQ. AT2QA reaches most of its gain with a moderate interaction budget, rather than relying on very deep search.
Paradigm
Configuration
Hits@1
LLM only
DeepSeek V3.2 without search tool
0.100
Rigid workflow (RTQA)
+ Base tool (semantic relevance)
0.762
+ Advanced tool (all components)
0.767
Autonomous agent (zero-shot)
+ Base tool (semantic relevance)
0.791
+ Base tool + time limit
0.817
+ Base tool + time-aware sorting
0.814
Table 3: Ablation of the main performance drivers. For the autonomous-agent rows, the four single-component settings are variants built on top of the base tool, while “Advanced tool” combines all tool components.
Retrieval Depth
Hits@1
Top-10
0.898
Top-15
0.898
Top-20
0.904
Top-25
0.904
Top-30
0.906
Table 4: Effect of retrieval depth.
Backbone LLM (Zero-shot)
Hits@1
Qwen3-Max
0.793
DeepSeek-R1
0.842
Kimi-2.5
0.789
DeepSeek V3.2
0.844
Table 5: Zero-shot performance across different LLMs.
Appendix figures & tables9 assets
Supplementary material from the paper’s appendix.
Appendix
Category
Train
Dev
Test
Single
Equal
135,890
18,983
17,311
Before/After
75,340
11,655
11,073
First/Last
72,252
11,097
10,480
Multiple
Equal Multi
16,893
3,213
3,207
After First
43,305
6,499
6,266
Before Last
43,107
6,532
6,247
Appendix
Table 6: Statistics of question categories in MultiTQ.
Category
Train
Dev
Test
Simple
7,200
2,400
2,400
Medium
8,252
2,751
2,751
Complex
9,580
3,193
3,193
Total
25,032
8,344
8,344
Appendix
Table 7: Statistics of question categories in Timeline-CronQuestion.
Category
Train
Dev
Test
Simple
17,982
5,994
5,994
Medium
15,990
5,330
5,330
Complex
19,652
6,550
6,550
Total
53,624
17,874
17,874
Appendix
Table 8: Statistics of question categories in Timeline-ICEWS-Actor.
Figure 6: Cumulative Density of First Gold-Fact Position for complex multiple-target queries. The distribution provides quantitative proof of the agent’s self-validation (left) and self-correction (right) capabilities.
Backbone Embedding Model (Zero-shot)
Hits@1
text-embedding-3-large
0.883
text-embedding-3-small
0.892
gemini-embedding-001
0.889
Baidu-Embedding-V1
0.877
Appendix
Table 9: Performance across different embedding.
QLevel
Reason
Example
AT2QA Answer Relevant Facts
Simple
insufficient gold (91.4%)
Question: “Burnley F.C. is member of sports team by who from 1960-01-01 to 1968-01-01?” Gold: Willie Morgan AT2QA: Andy Lochhead
Search fact: 301957|Andy Lochhead|member of sports team|Burnley F.C.|1960-01-01|1968-01-01
Medium
insufficient gold (23%)
Question: “Cell 211 nominated for which object after Romeo Menti member of sports team A.C. Milan?” Gold: Goya Award for Best Film AT2QA: Goya Award for Best Producer
Search fact: 120994|Cell 211|nominated for|Goya Award for Best Producer|2010-01-01|2010-01-01 289197|Romeo Menti|member of sports team|A.C. Milan|1944-01-01|1944-01-01
Appendix
Table 10: Representative examples of answer undercounting in Timeline-CronQuestion.
Figure 7: Case Study for Equal Multi Questions.
Figure 8: Case Study for Before Last Questions with Consistency Checking.
Figure 9: Case Study for After First Questions with Self-Correction.
School of Internet of Things, Nanjing University of Posts and Telecommunications · Faculty of Medicine & Health, University of New South Wales, Sydney, Australia · Beijing Information Science and Technology University +2
Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China · School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China