From Imitation to Discrimination: Progressive Curriculum Learning for Robust Web Navigation

arXiv:2604.12666v1 Announce Type: cross Abstract: Text-based web agents offer computational efficiency for autonomous web navigation, yet developing robust agents remains challenging due to the noisy and heterogeneous nature of real-world HTML. Standard Supervised Fine-Tuning (SFT) approaches fail in two critical dimensions: they lack discrimination capabilities to reject plausible but incorrect elements in densely populated pages, and exhibit limited generalization to unseen website layouts. To address these challenges, we introduce the Triton dataset (590k instances) and a progressive training curriculum. Triton is constructed via Structural-Semantic Hard Negative Mining, which explicitly mines topologically similar distractors, and a Dual-Agent Consensus pipeline that synthesizes diverse cross-domain tasks with strict verification. Building upon this foundation, our progressive curriculum produces three models: Triton-SFT-32B for basic imitation, Triton-ORPO-32B for robust discrimination via Odds Ratio Preference Optimization, and Triton-GRPO-32B for long-horizon consistency through Group Relative Policy Optimization. Empirical evaluation on Mind2Web demonstrates that Triton-GRPO-32B achieves state-of-the-art performance among open-source models with 58.7% Step Success Rate, surpassing GPT-4.5 (42.4%) and Claude-4.5 (41.4%) by over 16%, validating that specialized data curriculum outweighs raw parameter scale for web navigation.

Related

• ReCoQA: A Benchmark for Tool-Augmented and Multi-Step Reasoning in Real Estate Question and Answering
• Latent Preference Modeling for Cross-Session Personalized Tool Calling
• PersonalHomeBench: Evaluating Agents in Personalized Smart Homes
• PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory
• Failure Makes the Agent Stronger: Enhancing Accuracy through Structured Reflection for Reliable Tool Interactions

Source: arXiv cs.CL | 2026-04-15