Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
TPAMI 2026 | This repository collects awesome survey, resource, and paper for lifelong learning LLM agents
| Date | Stars |
|---|---|
| 2026-07-31 | 321 |
| 2026-08-06 | 321 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# TPAMI 2026 | Lifelong Learning of Large Language Model based Agents: A Roadmap [](https://arxiv.org/pdf/2501.07278) Welcome to the repository accompanying our survey paper on **Lifelong Learning of Large Language Model based Agents: A Roadmap**. This repository collects awesome paper for lifelong learning (also known as, continual learning and incremental learning) of LLM agent. We identify three key modules-Perception, Memory, and Action-that are integral to agent's ability to perform lifelong learning. Please refer to [this survey](https://arxiv.org/pdf/2501.07278) for detailed introduction. Additionally, for other papers, surveys, and resources on lifelong learning (continual learning, incremental learning) of LLMs, you can refer to [this repository](https://github.com/zzz47zzz/awesome-lifelong-learning-methods-for-llm). A chinese version of this README is provided in [this file](./README_chinese.md). ## 📢 News - **2026.01**: Our [survey paper](https://arxiv.org/pdf/2501.07278) has been accepted for publication in IEEE TPAMI. An updated version, which includes additional experimental results and more references, will be released soon. - **2025.06**: We are excited to release the first benchmark [LifelongAgentBench](https://caixd-220529.github.io/LifelongAgentBench/) for lifelong learning of LLM Agents. The paper, source code, datasets are all available! - **2025.01**: The interpretation of this survey is available on [PaperWeekly](https://mp.weixin.qq.com/s/svub9VZGXkbFWH2A7p91SQ) and [知乎](https://zhuanlan.zhihu.com/p/20703148682)! - **2025.01**: We released a survey paper "[Lifelong Learning of Large Language Model based Agents: A Roadmap](https://arxiv.org/pdf/2501.07278)". Feel free to cite or open pull requests.   ## 📒 Table of Contents ## Perception Module ### Single-Modal Perception |Title|Venue|Date| |:---|:---|:---| |[AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agent](https://arxiv.org/pdf/2410.13825?)|arXiv|2024-10| |[GPT-4V(ision) is a Generalist Web Agent, if Grounded](https://arxiv.org/pdf/2401.01614.pdf)|ICLR|2024-01| |[Webarena: A realistic web environment for building autonomous agents](https://arxiv.org/pdf/2307.13854)|ICLR|2023-07| |[Synapse: Trajectory-asexemplar prompting with memory for computer control](https://openreview.net/pdf?id=Pc8AU1aF5e)|ICLR|2023-06| |[Multimodal web navigation with instruction-finetuned foundation models](https://arxiv.org/pdf/2305.11854)|ICLR|2023-05| ### Multi-Modal Perception |Title|Venue|Date| |:---|:---|:---| |[Llms can evolve continually on modality for x-modal reasoning](https://arxiv.org/pdf/2410.20178)|NeurIPS|2024-10| |[Modaverse: Efficiently transforming modalities with llms](https://openaccess.thecvf.com/content/CVPR2024/papers/Wang_ModaVerse_Efficiently_Transforming_Modalities_with_LLMs_CVPR_2024_paper.pdf)|CVPR|2024-01| |[Omnivore: A single model for many visual modalities](https://arxiv.org/PDF/2201.08377)|CVPR|2022-01| |[Perceiver: General perception with iterative attention](http://proceedings.mlr.press/v139/jaegle21a/jaegle21a.pdf)|ICML|2021-07| |[Vatt: Transformers for multimodal self-supervised learning from raw video, audio and text](https://proceedings.neurips.cc/paper_files/paper/2021/file/cb3213ada48302953cb0f166464ab356-Paper.pdf)|NeurIPS|2021-04| ## Memory Module ### Working Memory |Title|Venue|Date| |:---|:---|:---| |[Character-llm: A trainable agent for role-playing](https://arxiv.org/pdf/2310.10158)|EMNLP|2023-10| |[Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers](https://arxiv.org/pdf/2309.08532)|ICLR|2023-09| |[Adapting Language Models to Compress Contexts](https://arxiv.org/pdf/2305.14788)|ACL|2023-05| |[Critic: Large language models can self-correct with tool-interactive critiquing}](https://arxiv.org/pdf/2305.
Excerpt of 13,802 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:22fb9452702eb08e, topic:llm