# RASTeR: Robust, Agentic, and Structured Temporal Reasoning

arXiv: https://arxiv.org/abs/2406.19538 · HTML: https://mlsanity.com/paper/2406.19538/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 11 of its 60 references that are in the map.
- First posted on arXiv 27 Jun 2024.

## 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, 11 of 11)

- [Making Retrieval-Augmented Language Models Robust to Irrelevant Context](https://mlsanity.com/paper/2310.01558/) (2023)
- [How Context Affects Language Models' Factual Predictions](https://mlsanity.com/paper/2005.04611/) (2020)
- [Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training](https://mlsanity.com/paper/2405.20978/) (2024)
- [TRAM: Benchmarking Temporal Reasoning for Large Language Models](https://mlsanity.com/paper/2310.00835/) (2023)
- [TimeBench: A Comprehensive Evaluation of Temporal Reasoning Abilities in Large Language Models](https://mlsanity.com/paper/2311.17667/) (2023)
- [Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Models](https://mlsanity.com/paper/2306.08952/) (2023)
- [KnowGPT: Knowledge Graph based Prompting for Large Language Models](https://mlsanity.com/paper/2312.06185/) (2023)
- [Are Large Language Models Temporally Grounded?](https://mlsanity.com/paper/2311.08398/) (2023)
- [Two-stage Generative Question Answering on Temporal Knowledge Graph Using Large Language Models](https://mlsanity.com/paper/2402.16568/) (2024)
- [Desiderata for the Context Use of Question Answering Systems](https://mlsanity.com/paper/2401.18001/) (2024)
- [ComplexTempQA:A 100m Dataset for Complex Temporal Question Answering](https://mlsanity.com/paper/2406.04866/) (2024)

## Built on by (most cited first, 2 of 2)

- [Trustworthiness in Retrieval-Augmented Generation Systems: A Survey](https://mlsanity.com/paper/2409.10102/) (2024)
- [EvoWiki: Incremental State Overwriting and Traceable Question Answering for Cross-Meeting Knowledge Evolution](https://mlsanity.com/paper/2608.23265/) (2026)

## Abstract (arXiv)

Temporal question answering (TQA) remains a challenge for large language models (LLMs), particularly when retrieved content may be irrelevant, outdated, or temporally inconsistent. This is especially critical in applications like clinical event ordering, and policy tracking, which require reliable temporal reasoning even under noisy or outdated information. To address this challenge, we introduce RASTeR: Robust, Agentic, and Structured, Temporal Reasoning, a prompting framework that separates context evaluation from answer generation. RASTeR first assesses the relevance and temporal coherence of the retrieved context, then constructs a temporal knolwedge graph (TKG) to better facilitate reasoning. When inconsistencies are detected, RASTeR selectively corrects or discards context before generating an answer. Across multiple datasets and LLMs, RASTeR consistently improves robustnessfootnote Some TQA work defines robustness as handling diverse temporal phenomena. Here, we define it as the ability to answer correctly despite suboptimal context. We further validate our approach through a ``needle-in-the-haystack'' study, in which relevant context is buried among distractors. With forty distractors, RASTeR achieves 75% accuracy, over 12% ahead of the runner up