Pith. sign in

REVIEW 5 cited by

OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.19609 v1 pith:TQU5FA5F submitted 2024-10-25 cs.CL cs.AI

classification cs.CLcs.AI
keywords agentsmultimodalagentreal-worldabilitiesbuildingdevelopmentenvironments
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The rapid development of large language and multimodal models has sparked significant interest in using proprietary models, such as GPT-4o, to develop autonomous agents capable of handling real-world scenarios like web navigation. Although recent open-source efforts have tried to equip agents with the ability to explore environments and continuously improve over time, they are building text-only agents in synthetic environments where the reward signals are clearly defined. Such agents struggle to generalize to realistic settings that require multimodal perception abilities and lack ground-truth signals. In this paper, we introduce an open-source framework designed to facilitate the development of multimodal web agent that can autonomously conduct real-world exploration and improve itself. 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. After that, it further improves its policy by learning from well-performing trajectories judged by another general-purpose model. This exploration-feedback-optimization cycle can continue for several iterations. Experimental results show that our web agent successfully improves itself after each iteration, demonstrating strong performance across multiple test sets.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. RMSWeb: Reflection, Failure-Mode Mining, and Salvage-DS for Web Agent Reinforcement Learning

    cs.AI 2026-07 conditional novelty 6.0 of 10

    RMSWeb combines reflection-conditioned collection, failure-mode mining, and a competence-gated offline RL objective to improve compact web agents' success and step efficiency on live-web benchmarks.

  2. DeepShop: A Benchmark for Deep Research Shopping Agents

    cs.IR 2025-06 conditional novelty 6.0 of 10

    DeepShop, a benchmark of 150 complex online shopping queries with fine-grained evaluation, shows that leading web agents and deep research systems achieve at most a 32% task success rate.

  3. Self-Challenging Language Model Agents

    cs.AI 2025-06 conditional novelty 6.0 of 10

    A language model agent can generate its own verifiable training tasks and improve its tool-use success rate by about 2x without human-annotated data.

  4. Automated Skill Discovery for Language Agents through Exploration and Iterative Feedback

    cs.AI 2025-06 conditional novelty 5.0 of 10

    EXIF repeatedly has a teacher agent explore an environment, relabel the exploration as tasks, train a student agent on it, and use the student's failures to guide the next round, improving 7B-8B agents in Webshop and Crafter.

  5. WorkForceAgent-R1: Incentivizing Reasoning Capability in LLM-based Web Agents via Reinforcement Learning

    cs.CL 2025-05 conditional novelty 5.0 of 10

    R1-style reinforcement learning on single-step web actions lifts open-source agents above gpt-4o on WorkArena while avoiding the reward hacking seen with dense rewards.

Pith tools