# Time-R1: Towards Comprehensive Temporal Reasoning in LLMs

arXiv: https://arxiv.org/abs/2505.13508 · HTML: https://mlsanity.com/paper/2505.13508/

## Key facts

- Cited by 25 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 32 of its 47 references that are in the map.
- First posted on arXiv 16 May 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 30 of 32)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [ToolRL: Reward is All Tool Learning Needs](https://mlsanity.com/paper/2504.13958/) (2025)
- [R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.05592/) (2025)
- [Large Language Models for Mathematical Reasoning: Progresses and Challenges](https://mlsanity.com/paper/2402.00157/) (2024)
- [A Survey of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2312.14925/) (2023)
- [Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning](https://mlsanity.com/paper/2502.14768/) (2025)
- [ToRL: Scaling Tool-Integrated RL](https://mlsanity.com/paper/2503.23383/) (2025)
- [Understanding World or Predicting Future? A Comprehensive Survey of World Models](https://mlsanity.com/paper/2411.14499/) (2024)
- [RM-R1: Reward Modeling as Reasoning](https://mlsanity.com/paper/2505.02387/) (2025)
- [LLM Post-Training: A Deep Dive into Reasoning Large Language Models](https://mlsanity.com/paper/2502.21321/) (2025)
- [How well do Large Language Models perform in Arithmetic tasks?](https://mlsanity.com/paper/2304.02015/) (2023)
- [Large Language Models Can Learn Temporal Reasoning](https://mlsanity.com/paper/2401.06853/) (2024)
- [Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs](https://mlsanity.com/paper/2402.14740/) (2024)
- [Acting Less is Reasoning More! Teaching Model to Act Efficiently](https://mlsanity.com/paper/2504.14870/) (2025)
- [Temporal Reasoning on Implicit Events from Distant Supervision](https://mlsanity.com/paper/2010.12753/) (2020)
- [TimeBench: A Comprehensive Evaluation of Temporal Reasoning Abilities in Large Language Models](https://mlsanity.com/paper/2311.17667/) (2023)
- [Temporal Knowledge Graph Forecasting Without Knowledge Using In-Context Learning](https://mlsanity.com/paper/2305.10613/) (2023)
- [Time is Encoded in the Weights of Finetuned Language Models](https://mlsanity.com/paper/2312.13401/) (2023)
- [Set the Clock: Temporal Alignment of Pretrained Language Models](https://mlsanity.com/paper/2402.16797/) (2024)
- [Timo: Towards Better Temporal Reasoning for Language Models](https://mlsanity.com/paper/2406.14192/) (2024)

## Built on by (most cited first, 25 of 25)

- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents](https://mlsanity.com/paper/2512.20092/) (2025)
- [Agentic Forecasting using Sequential Bayesian Updating of Linguistic Beliefs](https://mlsanity.com/paper/2604.18576/) (2026)
- [Your LLM Agents are Temporally Blind: The Misalignment Between Tool Use Decisions and Human Time Perception](https://mlsanity.com/paper/2510.23853/) (2025)
- [Self-Aligned Reward: Towards Effective and Efficient Reasoners](https://mlsanity.com/paper/2509.05489/) (2025)
- [STReasoner: Empowering LLMs for Spatio-Temporal Reasoning in Time Series via Spatial-Aware Reinforcement Learning](https://mlsanity.com/paper/2601.03248/) (2026)
- [FinSTaR: Towards Financial Reasoning with Time Series Reasoning Models](https://mlsanity.com/paper/2605.03460/) (2026)
- [Bridging Modalities, Spanning Time: Structured Memory for Ultra-Long Agentic Video Reasoning](https://mlsanity.com/paper/2605.08271/) (2026)
- [A Modular Multitask Reasoning Framework Integrating Spatio-temporal Models and LLMs](https://mlsanity.com/paper/2506.20073/) (2025)
- [NeMo: Needle in a Montage for Video-Language Understanding](https://mlsanity.com/paper/2509.24563/) (2025)
- [Video-in-the-Loop: Span-Grounded Long Video QA with Interleaved Reasoning](https://mlsanity.com/paper/2510.04022/) (2025)
- [SeeingEye: Agentic Information Flow Unlocks Multimodal Reasoning In Text-only LLMs](https://mlsanity.com/paper/2510.25092/) (2025)
- [Learning to Refuse: Refusal-Aware Reinforcement Fine-Tuning for Hard-Irrelevant Queries in Video Temporal Grounding](https://mlsanity.com/paper/2511.23151/) (2025)
- [Do Language Models Update their Forecasts with New Information?](https://mlsanity.com/paper/2509.23936/) (2025)
- [Towards Interpretable and Trustworthy Time Series Reasoning: A BlueSky Vision](https://mlsanity.com/paper/2510.16980/) (2025)
- [OracleProto: A Reproducible Framework for Benchmarking LLM Forecasting via Knowledge Cutoffs and Temporal Masking](https://mlsanity.com/paper/2605.03762/) (2026)
- [Audio-Visual Intelligence in Large Foundation Models](https://mlsanity.com/paper/2605.04045/) (2026)
- [SynthEHR-Eviction: Enhancing Eviction SDoH Detection with LLM-Augmented Synthetic EHR Data](https://mlsanity.com/paper/2507.07421/) (2025)
- [Evaluating Temporal Consistency in Multi-Turn Language Models](https://mlsanity.com/paper/2604.23051/) (2026)
- [AnomSeer: Reinforcing Multimodal LLMs to Reason for Time-Series Anomaly Detection](https://mlsanity.com/paper/2602.08868/) (2026)
- [Large Language Model-Powered Query-Driven Event Timeline Summarization in Industrial Search](https://mlsanity.com/paper/2605.27066/) (2026)
- [Temporal Preference Concepts and their Functions in a Large Language Model](https://mlsanity.com/paper/2606.05194/) (2026)
- [TimeProVe: Propose, then Verify for Efficient Long Video Temporal Reasoning in Activities of Daily Living](https://mlsanity.com/paper/2606.20561/) (2026)
- [Auto-AEG: Scalable Data Construction for Open-Vocabulary Audio Event Grounding](https://mlsanity.com/paper/2607.04383/) (2026)
- [TimeThink: Eliciting Compositional Reasoning in Timeseries Large Language Models](https://mlsanity.com/paper/2609.13457/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) demonstrate impressive capabilities but lack robust temporal intelligence, struggling to integrate reasoning about the past with predictions and plausible generations of the future. Meanwhile, existing methods typically target isolated temporal skills, such as question answering about past events or basic forecasting, and exhibit poor generalization, particularly when dealing with events beyond their knowledge cutoff or requiring creative foresight. To address these limitations, we introduce textitTime-R1, the first framework to endow a moderate-sized (3B-parameter) LLM with comprehensive temporal abilities: understanding, prediction, and creative generation. Our approach features a novel three-stage development path; the first two constitute a textitreinforcement learning (RL) curriculum driven by a meticulously designed dynamic rule-based reward system. This framework progressively builds (1) foundational temporal understanding and logical event-time mappings from historical data, (2) future event prediction skills for events beyond its knowledge cutoff, and finally (3) enables remarkable generalization to creative future scenario generation without any fine-tuning. Strikingly, experiments demonstrate that Time-R1 outperforms models over 200 times larger, including the state-of-the-art 671B DeepSeek-R1, on highly challenging future event prediction and creative scenario generation benchmarks. This work provides strong evidence that thoughtfully engineered, progressive RL fine-tuning allows smaller, efficient models to achieve superior temporal performance, offering a practical and scalable path towards truly time-aware AI. To foster further research, we also release textitTime-Bench, a large-scale multi-task temporal reasoning dataset derived from 10 years of news data, and our series of textitTime-R1 checkpoints.