Dolphin: Closed-loop Open-ended Auto-research through Thinking, Practice, and Feedback

• URL: http://arxiv.org/abs/2501.03916v2
• Date: Fri, 10 Jan 2025 13:14:28 GMT
• Title: Dolphin: Closed-loop Open-ended Auto-research through Thinking, Practice, and Feedback
• Authors: Jiakang Yuan, Xiangchao Yan, Botian Shi, Tao Chen, Wanli Ouyang, Bo Zhang, Lei Bai, Yu Qiao, Bowen Zhou,
• Abstract summary: We propose Dolphin, the first closed-loop open-ended auto-research framework. Dolphin can generate research ideas, perform experiments, and get feedback from experimental results to generate higher-quality ideas. We highlight that Dolphin can automatically propose methods that are comparable to the state-of-the-art in some tasks such as 2D image classification and 3D point classification.
• Score: 71.89119648053396
• License:
• Abstract: The scientific research paradigm is undergoing a profound transformation owing to the development of Artificial Intelligence (AI). Recent works demonstrate that various AI-assisted research methods can largely improve research efficiency by improving data analysis, accelerating computation, and fostering novel idea generation. To further move towards the ultimate goal (i.e., automatic scientific research), in this paper, we propose Dolphin, the first closed-loop open-ended auto-research framework to further build the entire process of human scientific research. Dolphin can generate research ideas, perform experiments, and get feedback from experimental results to generate higher-quality ideas. More specifically, Dolphin first generates novel ideas based on relevant papers which are ranked by the topic and task attributes. Then, the codes are automatically generated and debugged with the exception-traceback-guided local code structure. Finally, Dolphin automatically analyzes the results of each idea and feeds the results back to the next round of idea generation. Experiments are conducted on the benchmark datasets of different topics and results show that Dolphin can generate novel ideas continuously and complete the experiment in a loop. We highlight that Dolphin can automatically propose methods that are comparable to the state-of-the-art in some tasks such as 2D image classification and 3D point classification.

Related papers

• DiSciPLE: Learning Interpretable Programs for Scientific Visual Discovery [61.02102713094486]
  Good interpretation is important in scientific reasoning, as it allows for better decision-making. This paper introduces an automatic way of obtaining such interpretable-by-design models, by learning programs that interleave neural networks. We propose DiSciPLE an evolutionary algorithm that leverages common sense and prior knowledge of large language models (LLMs) to create Python programs explaining visual data.
  arXiv  Detail & Related papers  (2025-02-14T10:26:14Z)
• ORS: A novel Olive Ridley Survival inspired Meta-heuristic Optimization Algorithm [2.4343652794054487]
  Olive Ridley Survival (ORS) is proposed which is inspired from survival challenges faced by hatchlings of Olive Ridley sea turtle. ORS has two major phases: hatchlings survival through environmental factors and impact of movement trajectory on its survival. To validate the algorithm, fourteen mathematical benchmark functions from standard CEC test suites are evaluated and statistically tested.
  arXiv  Detail & Related papers  (2024-09-13T21:48:05Z)
• The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery [14.465756130099091]
  This paper presents the first comprehensive framework for fully automatic scientific discovery. We introduce The AI Scientist, which generates novel research ideas, writes code, executes experiments, visualizes results, and describes its findings. In principle, this process can be repeated to iteratively develop ideas in an open-ended fashion, acting like the human scientific community.
  arXiv  Detail & Related papers  (2024-08-12T16:58:11Z)
• DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents [49.74065769505137]
  We introduce DISCOVERYWORLD, the first virtual environment for developing and benchmarking an agent's ability to perform complete cycles of novel scientific discovery. It includes 120 different challenge tasks spanning eight topics each with three levels of difficulty and several parametric variations. We find that strong baseline agents, that perform well in prior published environments, struggle on most DISCOVERYWORLD tasks.
  arXiv  Detail & Related papers  (2024-06-10T20:08:44Z)
• Autonomous LLM-driven research from data to human-verifiable research papers [0.0]
  We build an automation platform that guides interacting through complete stepwise process. In mode provided annotated data alone, datapaper raised hypotheses, designed plans, wrote and interpreted analysis codes, generated and interpreted results. We demonstrate potential for AI-driven acceleration of scientific discovery while enhancing traceability, transparency and verifiability.
  arXiv  Detail & Related papers  (2024-04-24T23:15:49Z)
• Dolphins: Multimodal Language Model for Driving [42.14069594700448]
  We introduce Dolphins, a novel vision-language model architected to imbibe human-like abilities as a conversational driving assistant. Dolphins is adept at processing multimodal inputs comprising video (or image) data, text instructions, and historical control signals.
  arXiv  Detail & Related papers  (2023-12-01T09:10:33Z)
• SciMON: Scientific Inspiration Machines Optimized for Novelty [68.46036589035539]
  We explore and enhance the ability of neural language models to generate novel scientific directions grounded in literature. We take a dramatic departure with a novel setting in which models use as input background contexts. We present SciMON, a modeling framework that uses retrieval of "inspirations" from past scientific papers.
  arXiv  Detail & Related papers  (2023-05-23T17:12:08Z)
• Deep Depth Completion: A Survey [26.09557446012222]
  We provide a comprehensive literature review that helps readers better grasp the research trends and clearly understand the current advances. We investigate the related studies from the design aspects of network architectures, loss functions, benchmark datasets, and learning strategies. We present a quantitative comparison of model performance on two widely used benchmark datasets, including an indoor and an outdoor dataset.
  arXiv  Detail & Related papers  (2022-05-11T08:24:00Z)
• Recovering 3D Human Mesh from Monocular Images: A Survey [49.00136388529404]
  Estimating human pose and shape from monocular images is a long-standing problem in computer vision. This survey focuses on the task of monocular 3D human mesh recovery.
  arXiv  Detail & Related papers  (2022-03-03T18:56:08Z)
• RoboTHOR: An Open Simulation-to-Real Embodied AI Platform [56.50243383294621]
  We introduce RoboTHOR to democratize research in interactive and embodied visual AI. We show there exists a significant gap between the performance of models trained in simulation when they are tested in both simulations and their carefully constructed physical analogs.
  arXiv  Detail & Related papers  (2020-04-14T20:52:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.