mlsanityData to 7 Oct 2026

TEMPO: A Realistic Multi-Domain Benchmark for Temporal Reasoning-Intensive Retrieval

arXiv 2601.09523 ↗First posted 14 Jan 2026cs.IRcited by 6

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Existing temporal QA benchmarks focus on simple fact-seeking queries from news corpora, while reasoning-intensive retrieval benchmarks lack temporal grounding. However, real-world information needs often require reasoning about temporal evolution and synthesizing evidence across time periods. We introduce TEMPO, the first benchmark combining temporal reasoning with reasoning-intensive retrieval across 13 domains. TEMPO features: (1) 1,730 complex queries requiring deep temporal reasoning such as tracking changes, identifying trends, or comparing cross-period evidence; (2) step-wise retrieval planning with 3,976 decomposed steps and gold documents mapped to each step for multi-hop evaluation; and (3) novel temporal metrics including Temporal Coverage@k and Temporal Precision@k measuring whether results span required time periods. Evaluation of 12 retrieval systems reveals substantial challenges: the best model (DiVeR) achieves only 32.0 NDCG@10 and 71.4% Temporal Coverage@10, demonstrating difficulty in retrieving temporally complete evidence. We believe TEMPO provides a challenging benchmark for improving temporal reasoning in retrieval and RAG systems. Our code and data are available at https://github.com/tempo-bench/Tempo. See also our official website: https://tempo-bench.github.io/.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 20 of its 37 references that are in the map. First posted on arXiv 14 Jan 2026.

Builds on

20 of 37 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025HistoryBankQA: Multilingual Temporal Question Answering on Historical Events16 Sep
  2. 2025DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillation23 Aug
  3. 2025DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval11 Aug
  4. 2025TIME: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenarios19 May
  5. 2025ReasonIR: Training Retrievers for Reasoning Tasks29 Apr
  6. 2024RAR-b: Reasoning as Retrieval Benchmark9 Apr

Other references · 14

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  2. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
  3. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
  4. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  5. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,050
  6. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 705
  7. 2024BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrievalcited by 153
  8. 2021A Dataset for Answering Time-Sensitive Questionscited by 150
  9. 2025A Systematic Literature Review of Retrieval-Augmented Generation: Techniques, Metrics, and Challengescited by 16
  10. 2025TempRetriever: Fusion-based Temporal Dense Passage Retrieval for Time-Sensitive Questionscited by 14
  11. 2025Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generationcited by 13
  12. 2025It's High Time: A Survey of Temporal Question Answeringcited by 12
2 more
  1. 2025A Study into Investigating Temporal Robustness of LLMscited by 10
  2. 2025SustainableQA: A Comprehensive Question Answering Dataset for Corporate Sustainability and EU Taxonomy Reportingcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026Are LLM-Based Retrievers Worth Their Cost? An Empirical Study of Efficiency, Robustness, and Reasoning Overheadcited by 4
  2. 2026The Magnitude Mirage: Rethinking Confidence for Reasoning-Intensive Retrievalcited by 1
  3. 2026MARVEL: Multimodal Adaptive Reasoning-intensiVe Expand-rerank and retrievaLcited by 0
  4. 2026BRIDGE: Multimodal-to-Text Retrieval via Reinforcement-Learned Query Alignmentcited by 0
  5. 2026HIVE: Query, Hypothesize, Verify An LLM Framework for Multimodal Reasoning-Intensive Retrievalcited by 0
  6. 2026BracketRank: Large Language Model Document Ranking via Reasoning-based Competitive Eliminationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Difficulty-Gated Fusion of Reasoning Views for Temporal Retrieval
  2. 2024MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answering
  3. 2025LiveSearchBench: An Automatically Constructed Benchmark for Retrieval and Reasoning over Dynamic Knowledge
  4. 2025MemoTime: Memory-Augmented Temporal Knowledge Graph Enhanced Large Language Model Reasoning
  5. 2026IA-RAG: Interval-Algebra-Driven Temporal Reasoning for Dynamic Knowledge Retrieval
  6. 2024Time Awareness in Large Language Models: Benchmarking Fact Recall Across Time
  7. 2026TS-Haystack: A Multi-Task Retrieval Benchmark for Long-Context Time-Series Reasoning
  8. 2026Measuring Iterative Temporal Reasoning with Time Puzzles