When Web Agents Finish but Still Fail: Reproducible Triggers and Trace Diagnostics for Parallel Web Exploration

[Submitted on 16 Jun 2026 (v1), last revised 29 Jun 2026 (this version, v2)]

View PDF HTML (experimental)

Abstract:Long-horizon web agents often fail in ways hidden by final-answer evaluation: they may visit useful pages, produce a well-formed answer, and terminate confidently while still missing fields, over-including unsupported items, or relying on stale evidence. We study these failures with Parallel WebBench, a parallel web-exploration benchmark containing 1,679 verified records: 350 manually curated parallel tasks and 1,329 reconstructed records with verified URL-based trajectories. We train WebExplorer-style agents with GRPO under human-only, balanced human-synthetic, and synthetic-heavy data mixtures. At 16k context and 16 interaction rounds, the best GRPO model improves completion over WebExplorer-8B from 50.7% to 96.0% and GPT-4.1-mini-judged element-wise F1 from 0.2489 to 0.4529, but binary accuracy remains far below completion. Trace-level analysis identifies three persistent failure modes: context-bound search loops, premature termination on partial answers, and synthesis collapse after relevant evidence has already been retrieved. These results show that synthetic-data GRPO reduces abstention and improves partial correctness, but leaves a completion-correctness gap that requires evidence-grounded coverage and synthesis diagnostics.

Submission history

From: Minghao Yan [view email]
[v1] Tue, 16 Jun 2026 23:00:25 UTC (1,845 KB)
[v2] Mon, 29 Jun 2026 04:16:15 UTC (1,979 KB)