MEMENTO: Leveraging Web as a Learning Signal for Low-Data Domains

• URL: http://arxiv.org/abs/2605.29795v1
• Date: Thu, 28 May 2026 11:44:32 GMT
• Title: MEMENTO: Leveraging Web as a Learning Signal for Low-Data Domains
• Abstract summary: Real-world tasks often lack large labeled datasets, motivating extensive work on learning in low-data regimes.<n>We propose MEMENTO, a framework that treats the web as a learning signal rather than a stateless retrieval interface.<n>We evaluate MEMENTO on two low-data professional domains: sales automation and legal research.
• Score: 3.572758120834609
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Real-world tasks often lack large labeled datasets, motivating extensive work on learning in low-data regimes. However, existing approaches such as few-shot prompting, instruction tuning, and synthetic data generation, continue to treat labeled or pseudo-labeled data as the primary learning signal. In contrast, human practitioners acquire expertise through repeated, self-directed interaction with the open web, progressively refining both domain knowledge and search strategies. We propose MEMENTO, a framework that treats the web as a learning signal rather than a stateless retrieval interface. MEMENTO operates at two levels: within each session, it conducts iterative web exploration via an Adaptive Exploration Tree (AET) that decomposes tasks into evolving questions and reflects on intermediate findings; across sessions, it accumulates experience through dual-channel memory, separating declarative knowledge (facts) from procedural knowledge (search strategies). This design enables agents to learn reusable research strategies and domain expertise from trajectories of web interaction without additional model training. We evaluate MEMENTO on two low-data professional domains: sales automation and legal research. Our empirical results show consistent improvements in performance over ReAct based baselines (+25.6% on sales automation and 36.5% on legal research), demonstrating that the web can serve as a scalable learning source for acquiring task-specific expertise in data-scarce settings.

Related papers

• Scaling Web Agent Training through Automatic Data Generation and Fine-grained Evaluation [54.945281159783896]
  We present a scalable pipeline for automatically generating high-quality training data for web agents.<n>We introduce a novel constraint-based evaluation framework that provides fine-grained assessment of progress towards task completion.
  arXiv  Detail & Related papers  (2026-02-13T02:52:18Z)
• Synthesizing Agentic Data for Web Agents with Progressive Difficulty Enhancement Mechanisms [81.90219895125178]
  Web-based 'deep research' agents aim to solve complex question - answering tasks through long-horizon interactions with online tools.<n>These tasks remain challenging, as the underlying language models are often not optimized for long-horizon reasoning.<n>We introduce a two-pronged data synthesis pipeline that generates question - answer pairs by progressively increasing complexity.
  arXiv  Detail & Related papers  (2025-10-15T06:34:46Z)
• WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents [72.28593628378991]
  WebResearcher is an iterative deep-research paradigm that reformulates deep research as a Markov Decision Process.<n>WebResearcher achieves state-of-the-art performance, even surpassing frontier proprietary systems.
  arXiv  Detail & Related papers  (2025-09-16T17:57:17Z)
• WebDS: An End-to-End Benchmark for Web-based Data Science [59.270670758607494]
  WebDS is the first end-to-end web-based data science benchmark.<n>It comprises 870 web-based data science tasks across 29 diverse websites.<n>WebDS sets the stage for significant advances in the development of practically useful LLM-based data science.
  arXiv  Detail & Related papers  (2025-08-02T06:39:59Z)
• SiameseDuo++: Active Learning from Data Streams with Dual Augmented Siamese Networks [8.762175520727611]
  This work proposes the SiameseDuo++ method, which uses active learning to automatically select instances for a human expert to label according to a budget.<n>Specifically, it incrementally trains two siamese neural networks which operate in synergy, augmented by generated examples.<n> Simulation experiments show that the proposed method outperforms strong baselines and state-of-the-art methods in terms of learning speed and/or performance.
  arXiv  Detail & Related papers  (2025-04-06T20:45:25Z)
• DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments [20.498100965239818]
  We introduce DeepResearcher, the first comprehensive framework for end-to-end training of LLM-based deep research agents.<n>Unlike RAG-based approaches that assume all necessary information exists within a fixed corpus, our method trains agents to navigate the noisy, unstructured, and dynamic nature of the open web.<n>Extensive experiments on open-domain research tasks demonstrate that DeepResearcher achieves substantial improvements of up to 28.9 points over prompt engineering-based baselines.
  arXiv  Detail & Related papers  (2025-04-04T04:41:28Z)
• RECALL+: Adversarial Web-based Replay for Continual Learning in Semantic Segmentation [27.308426315113707]
  We extend our previous approach (RECALL) and tackle forgetting by exploiting unsupervised web-crawled data. Experimental results show that this enhanced approach achieves remarkable results, particularly when the incremental scenario spans multiple steps.
  arXiv  Detail & Related papers  (2023-09-19T09:50:30Z)
• Reinforcement Learning Based Multi-modal Feature Fusion Network for Novel Class Discovery [47.28191501836041]
  In this paper, we employ a Reinforcement Learning framework to simulate the cognitive processes of humans. We also deploy a Member-to-Leader Multi-Agent framework to extract and fuse features from multi-modal information. We demonstrate the performance of our approach in both the 3D and 2D domains by employing the OS-MN40, OS-MN40-Miss, and Cifar10 datasets.
  arXiv  Detail & Related papers  (2023-08-26T07:55:32Z)
• Self-Supervised Graph Neural Network for Multi-Source Domain Adaptation [51.21190751266442]
  Domain adaptation (DA) tries to tackle the scenarios when the test data does not fully follow the same distribution of the training data. By learning from large-scale unlabeled samples, self-supervised learning has now become a new trend in deep learning. We propose a novel textbfSelf-textbfSupervised textbfGraph Neural Network (SSG) to enable more effective inter-task information exchange and knowledge sharing.
  arXiv  Detail & Related papers  (2022-04-08T03:37:56Z)
• Unsupervised Domain Adaptive Learning via Synthetic Data for Person Re-identification [101.1886788396803]
  Person re-identification (re-ID) has gained more and more attention due to its widespread applications in video surveillance. Unfortunately, the mainstream deep learning methods still need a large quantity of labeled data to train models. In this paper, we develop a data collector to automatically generate synthetic re-ID samples in a computer game, and construct a data labeler to simultaneously annotate them.
  arXiv  Detail & Related papers  (2021-09-12T15:51:41Z)

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.