Research map / Multi-agent systems and games / Human-AI and goal-conditioned
WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents
Shunyu Yao, Howard Chen, John Yang, Karthik R Narasimhan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| fine-tune IL agent with RL | IL agent · WebShop test | task score: 59.9 -> 62.4 | Improved |
| fine-tune IL agent with RL | IL agent · WebShop test | success rate: 29.1% -> 28.7% | Hurt |
| RL fine-tuning makes agent greedier, lowering option score | IL agent · WebShop test | option score: 45.2 -> 38.9 | Hurt |
| add language pre-training (BERT init) to choice model (ablation) | IL agent · WebShop test | success rate | Improved |
| add BART search query generator instead of instruction-text rule (ablation) | IL agent · WebShop test | score and success rate: around 3 points | Improved |
| add history (one past observation, last five actions) (ablation) | IL agent · WebShop test | task score: 59.9 -> 57.3 | Hurt |
| warm-start RL from IL instead of directly from pre-trained BERT (ablation) | RL agent · WebShop test | task score | Improved |
| use Transformer (BERT) encoder instead of RNN in RL (ablation) | IL+RL · WebShop test | success rate: more than 10% better | Improved |
| use top-1 search query instead of sampling from top-5 (ablation) | IL agent · WebShop test | score: 60.56 -> 61.96 | Improved |
| use top-1 choice instead of sampling (ablation) | IL agent · WebShop test | score: 60.56 -> 45.10 | Hurt |
| add image features (ResNet) (ablation) | IL agent · WebShop test | score: 60.3 -> 60.6 | No clear effect |
| use Choice oracle with human last query instead of instruction text query | Choice oracle · WebShop test | success rate: 85.4% -> 87.8% | Improved |
Closest papers by meaning
- WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents (ICLR 2026 · similarity 0.90)
- WebArena: A Realistic Web Environment for Building Autonomous Agents (ICLR 2024 · similarity 0.90)
- ShopGym: An Integrated Framework for Realistic Simulation and Scalable Benchmarking of E-Commerce Web Agents (NeurIPS 2026 · similarity 0.90)
- REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real Websites (NeurIPS 2025 · similarity 0.89)
- RealWebAssist: A Benchmark for Long-Horizon Web Assistance with Real-World Users (AAAI 2026 · similarity 0.89)
- WebGym: Scaling Training Environments for Long-Horizon Visual Web Agents with Realistic Tasks (CVPR 2026 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
