# Timo: Towards Better Temporal Reasoning for Language Models

arXiv: https://arxiv.org/abs/2406.14192 · HTML: https://mlsanity.com/paper/2406.14192/

## Key facts

- Cited by 21 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 21 of its 70 references that are in the map.
- First posted on arXiv 20 Jun 2024.

## Placed in

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

## Builds on (most cited first, 21 of 21)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct](https://mlsanity.com/paper/2308.09583/) (2023)
- [Zephyr: Direct Distillation of LM Alignment](https://mlsanity.com/paper/2310.16944/) (2023)
- [MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning](https://mlsanity.com/paper/2309.05653/) (2023)
- [Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision](https://mlsanity.com/paper/2312.09390/) (2023)
- [Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies](https://mlsanity.com/paper/2308.03188/) (2023)
- [Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future](https://mlsanity.com/paper/2309.15402/) (2023)
- [Large Language Models Can Learn Temporal Reasoning](https://mlsanity.com/paper/2401.06853/) (2024)
- [Branch-Solve-Merge Improves Large Language Model Evaluation and Generation](https://mlsanity.com/paper/2310.15123/) (2023)
- [The Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation](https://mlsanity.com/paper/2308.07286/) (2023)
- [TRAM: Benchmarking Temporal Reasoning for Large Language Models](https://mlsanity.com/paper/2310.00835/) (2023)
- [Living in the Moment: Can Large Language Models Grasp Co-Temporal Reasoning?](https://mlsanity.com/paper/2406.09072/) (2024)
- [Towards Robust Temporal Reasoning of Large Language Models via a Multi-Hop QA Dataset and Pseudo-Instruction Tuning](https://mlsanity.com/paper/2311.09821/) (2023)
- [Question Answering as Programming for Solving Time-Sensitive Questions](https://mlsanity.com/paper/2305.14221/) (2023)
- [Exploring the Limitations of Large Language Models in Compositional Relation Reasoning](https://mlsanity.com/paper/2403.02615/) (2024)
- [Back to the Future: Towards Explainable Temporal Reasoning with Large Language Models](https://mlsanity.com/paper/2310.01074/) (2023)

## Built on by (most cited first, 21 of 21)

- [OpenThinkIMG: Learning to Think with Images via Visual Tool Reinforcement Learning](https://mlsanity.com/paper/2505.08617/) (2025)
- [LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training](https://mlsanity.com/paper/2406.16554/) (2024)
- [Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning](https://mlsanity.com/paper/2506.04207/) (2025)
- [Alleviating Hallucination in Large Vision-Language Models with Active Retrieval Augmentation](https://mlsanity.com/paper/2408.00555/) (2024)
- [Time-R1: Towards Comprehensive Temporal Reasoning in LLMs](https://mlsanity.com/paper/2505.13508/) (2025)
- [MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization](https://mlsanity.com/paper/2412.06141/) (2024)
- [Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents](https://mlsanity.com/paper/2512.20092/) (2025)
- [From Head to Tail: Towards Balanced Representation in Large Vision-Language Models through Adaptive Data Calibration](https://mlsanity.com/paper/2503.12821/) (2025)
- [DiMA: An LLM-Powered Ride-Hailing Assistant at DiDi](https://mlsanity.com/paper/2503.04768/) (2025)
- [Date Fragments: A Hidden Bottleneck of Tokenization for Temporal Reasoning](https://mlsanity.com/paper/2505.16088/) (2025)
- [Counterfactual-Consistency Prompting for Relative Temporal Understanding in Large Language Models](https://mlsanity.com/paper/2502.11425/) (2025)
- [Large Language Model Powered Intelligent Urban Agents: Concepts, Capabilities, and Applications](https://mlsanity.com/paper/2507.00914/) (2025)
- [Mitigating Multilingual Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2408.00550/) (2024)
- [DateLogicQA: Benchmarking Temporal Biases in Large Language Models](https://mlsanity.com/paper/2412.13377/) (2024)
- [GTR-Bench: Evaluating Geo-Temporal Reasoning in Vision-Language Models](https://mlsanity.com/paper/2510.07791/) (2025)
- [NeSTR: A Neuro-Symbolic Abductive Framework for Temporal Reasoning in Large Language Models](https://mlsanity.com/paper/2512.07218/) (2025)
- [Time to Revist Exact Match](https://mlsanity.com/paper/2509.16720/) (2025)
- [Structured yet Bounded Temporal Understanding in Large Language Models](https://mlsanity.com/paper/2510.16685/) (2025)
- [MIN-Merging: Merge the Important Neurons for Model Merging](https://mlsanity.com/paper/2510.17890/) (2025)
- [On the Cultural Anachronism and Temporal Reasoning in Vision Language Models](https://mlsanity.com/paper/2605.15071/) (2026)
- [PredAct-Bench: Benchmarking Tool-Augmented Dialogue under Controlled Tool Noise](https://mlsanity.com/paper/2608.02372/) (2026)

## Abstract (arXiv)

Reasoning about time is essential for Large Language Models (LLMs) to understand the world. Previous works focus on solving specific tasks, primarily on time-sensitive question answering. While these methods have proven effective, they cannot generalize to a wider spectrum of temporal reasoning tasks. Therefore, we propose a crucial question: Can we build a universal framework to handle a variety of temporal reasoning tasks? To that end, we systematically study 38 temporal reasoning tasks. Based on the observation that 19 tasks are directly related to mathematics, we first leverage the available mathematical dataset to set a solid foundation for temporal reasoning. However, the in-depth study indicates that focusing solely on mathematical enhancement falls short of addressing pure temporal reasoning tasks. To mitigate this limitation, we propose a simple but effective self-critic temporal optimization method to enhance the model's temporal reasoning capabilities without sacrificing general task abilities. Finally, we develop Timo, a model designed to excel in temporal reasoning at the 7B and 13B scales. Notably, Timo outperforms the counterpart LLMs by 10.0 and 7.6 in average accuracy scores and achieves the new state-of-the-art (SOTA) performance of comparable size. Extensive experiments further validate our framework's effectiveness and its generalization across diverse temporal tasks. The code is available at https://github.com/zhaochen0110/Timo.