Related papers: Learning to Adapt: Self-Improving Web Agent via Cognitive-Aware Exploration

Learning to Adapt: Self-Improving Web Agent via Cognitive-Aware Exploration

URL: http://arxiv.org/abs/2605.31365v1
Date: Fri, 29 May 2026 14:37:27 GMT
Title: Learning to Adapt: Self-Improving Web Agent via Cognitive-Aware Exploration
Abstract summary: We propose a framework for building truly autonomous and adaptive web agents.<n>We use three adversarial roles, Selector, Predictor, and Judger, to discover the agent's limitations and expand its cognitive boundaries.<n>Our framework offers a scalable and generalizable solution for building truly autonomous and adaptive web agents.
Score: 41.778518335766215
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Recent advances in Multimodal Large Language Models (MLLMs) have led to promising progress in web agents. However, existing web agents often rely on handcrafted execution pipelines or expensive expert trajectories, limiting their adaptability to complex, dynamic environments. To address these challenges, we propose SCALE (Self-Cognitive-Aware Learning and Exploration), which leverages three adversarial roles, Selector, Predictor, and Judger to autonomously discover the agent's limitations and expand its cognitive boundaries through environmental exploration. Moreover, we propose SCALE-Hop, a graph exploration strategy that facilitates global planning and helps agents avoid local exploration traps. To further support learning, we construct SCALE-20k, a large-scale dataset collected from 19 real-world websites, containing diverse task types and structured demonstrations generated from SCALE's exploration traces. Experimental results show that our approach significantly improves the performance and generalization of multiple MLLMs in various web environments. Our framework offers a scalable and generalizable solution for building truly autonomous and adaptive web agents.

Related papers

Multi-Agent LLMs Fail to Explore Each Other [34.74439361133657]
We show that modern large language model (LLM) agents fail to explore effectively when interacting with one another.<n>We introduce Multi- Agent Contextual Exploration (MACE), a lightweight framework that explicitly promotes exploration through structured peer selection.
arXiv Detail & Related papers (2026-07-13T08:34:05Z)
APEX: Autonomous Policy Exploration for Self-Evolving LLM Agents [54.213455157510445]
Self-evolving agents learn by accumulating memory and reflection across episodes rather than requiring model-weight updates.<n>As memory grows, behavior concentrates around familiar high-reward routines, reducing the chance of discovering better alternatives.<n>We propose Autonomous Policy EXploration (APEX), which builds and maintains an explicit strategy space through a strategy map.
arXiv Detail & Related papers (2026-05-20T14:29:27Z)
A Survey on Agentic Multimodal Large Language Models [84.18778056010629]
We present a comprehensive survey on Agentic Multimodal Large Language Models (Agentic MLLMs)<n>We explore the emerging paradigm of agentic MLLMs, delineating their conceptual foundations and distinguishing characteristics from conventional MLLM-based agents.<n>To further accelerate research in this area for the community, we compile open-source training frameworks, training and evaluation datasets for developing agentic MLLMs.
arXiv Detail & Related papers (2025-10-13T04:07:01Z)
OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization [66.22117723598872]
We introduce an open-source framework designed to facilitate the development of multimodal web agent. We first train the base model with imitation learning to gain the basic abilities. We then let the agent explore the open web and collect feedback on its trajectories.
arXiv Detail & Related papers (2024-10-25T15:01:27Z)
Glider: Global and Local Instruction-Driven Expert Router [83.785832410832]
"Model MoErging" methods prioritize generalization to unseen tasks at the expense of performance on held-in tasks. We propose Global and Local Instruction Driven Expert Router (GLIDER) that integrates a multi-scale routing mechanism. GLIDER achieves substantially improved held-in performance while maintaining strong generalization on held-out tasks.
arXiv Detail & Related papers (2024-10-09T17:59:14Z)
WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Exploration [42.8636989730348]
Existing LLM-based web agents rely on rigid, expert-designed policies specific to certain states and actions. Humans excel by exploring unknowns, continuously adapting strategies, and resolving ambiguities through exploration. We develop WebPilot, a multi-agent system with a dual optimization strategy that improves Monte Carlo Tree Search (MCTS) to better handle complex web environments.
arXiv Detail & Related papers (2024-08-28T17:49:29Z)
Imagine, Initialize, and Explore: An Effective Exploration Method in Multi-Agent Reinforcement Learning [27.81925751697255]
We propose a novel method for efficient multi-agent exploration in complex scenarios. We formulate the imagination as a sequence modeling problem, where the states, observations, prompts, actions, and rewards are predicted autoregressively. By initializing agents at the critical states, IIE significantly increases the likelihood of discovering potentially important underexplored regions.
arXiv Detail & Related papers (2024-02-28T01:45:01Z)
On the Multi-turn Instruction Following for Conversational Web Agents [83.51251174629084]
We introduce a new task of Conversational Web Navigation, which necessitates sophisticated interactions that span multiple turns with both the users and the environment. We propose a novel framework, named self-reflective memory-augmented planning (Self-MAP), which employs memory utilization and self-reflection techniques.
arXiv Detail & Related papers (2024-02-23T02:18:12Z)

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