Speculative Rollback Correction for Quality-Diverse Web Agent Imitation

• URL: http://arxiv.org/abs/2606.12485v1
• Date: Wed, 10 Jun 2026 08:56:27 GMT
• Title: Speculative Rollback Correction for Quality-Diverse Web Agent Imitation
• Abstract summary: Training interactive web agents through imitation learning from expert trajectories has emerged as a highly effective approach.<n>We propose Speculative Rollback Correction (SRC), a branch-level imitation framework for resettable agent environments.
• Score: 43.603850569331975
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Training interactive web agents through imitation learning from expert trajectories has emerged as a highly effective approach. However, determining the optimal timing for expert intervention presents a critical challenge in this context. Delayed intervention often leads to the accumulation of early-stage errors, pushing the page state into an irrecoverable regime. Conversely, premature or excessive intervention causes the agent to become overly reliant on expert policies, trapping the model in local optima characterized by a single, rigid trajectory. We propose Speculative Rollback Correction (SRC), a branch-level imitation framework for resettable agent environments. Instead of requesting teacher labels at every visited state or correcting only after a completed trajectory, SRC uses fixed-horizon branch review: the student executes a short speculative segment before teacher review, and the teacher localizes the first harmful deviation only when local progress breaks. Rollback preserves useful prefixes, while successful rollouts are filtered by a hard verifier and retained in a lightweight quality-diversity archive. The resulting data supports next-action supervised fine-tuning on both localized corrections and verifier-passing trajectories. On WebArena-Infinity, SRC collects 977 verifier-passing trajectories and 9,183 next-action examples; fixed-horizon review improves the recovery-versus-query tradeoff over step-level review while retaining verifier-passing solution variants. Code is available at https://github.com/LongkunHao/SRC_gui_agent.

Related papers

• InsightSeg: Reusing Correction Insights for Guideline-Consistent Segmentation [4.501547677532766]
  We introduce InsightSeg, an episodic memory mechanism that converts successful correction episodes into reusable, visually grounded insights.<n>Across and Cityscapes, InsightSeg improves both first-pass and final guideline-consistent segmentation performance while requiring fewer refinement steps.
  arXiv  Detail & Related papers  (2026-09-02T02:22:35Z)
• CAST: Critique-Aware Supervision for Training Reliable Long-Horizon Tool-Calling Agents [66.9575676266637]
  Large language model (LLM) agents are increasingly deployed in long-horizon, interactive, and stateful environments.<n>In these settings, a single wrong action, such as refunding the wrong purchase, can cause irreversible task failure and must be intercepted before execution.<n>We develop CAST, a critique-aware training framework that converts sparse task outcomes into action-level supervision for critique learning and policy optimization.
  arXiv  Detail & Related papers  (2026-08-31T01:59:51Z)
• CAFE: Self-Improving Search Agents Need Co-Evolving Feedback [64.5257526832476]
  Outcome-supervised search agents learn when and how to retrieve evidence, but terminal rewards neither localize intermediate errors nor redirect an ongoing trajectory before those errors compound.<n>Treating corrective feedback as a learned in-trajectory intervention couples the two roles: the agent must decide when to request and use feedback, while the critic must infer useful corrections from outcome-confounded rollouts whose failure patterns shift as the agent improves.
  arXiv  Detail & Related papers  (2026-08-25T16:39:00Z)
• HERO: History-Enriched Rollout Training for Long-Horizon Autoregressive Neural Operators [17.3214708475049]
  Autoregressive rollout feeds every prediction error back as input, so local errors accumulate.<n>Existing rollout-training strategies reduce the mismatch between training inputs and self-generated states, yet their supervision still measures only the absolute discrepancy from the ground-truth trajectory.<n>We propose history-enriched rollout training (HERO), which augments conventional absolute trajectory supervision with relative supervision derived from the model's optimization history.
  arXiv  Detail & Related papers  (2026-07-31T08:05:46Z)
• HERO: Hindsight-Enhanced Reflection from Environment Observations for Agentic Self-Distillation [50.53459634301361]
  HERO is a hindsight-enhanced self-distillation framework that uses next environment observations as locally aligned feedback.<n> HERO improves task success and reduces unnecessary turns over environment-feedback-only self-distillation and GRPO.
  arXiv  Detail & Related papers  (2026-06-10T01:35:34Z)
• Trajectory-Refined Distillation [25.346810464266497]
  Trajectory-Refined Distillation (TRD) is a trajectory-level correction method that revises the student's rollout under the teacher guidance while within on-policy support.<n> TRD can also be applied to on-policy self-distillation (OPSD), a parameter-sharing variant that uses the student model conditioned on privileged informations as the teacher.
  arXiv  Detail & Related papers  (2026-06-07T03:17:25Z)
• ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling [57.42714978834704]
  ExComm is a communication protocol for exploration-stage agentic test-time scaling.<n>We show that ExComm consistently outperforms strong test-time scaling baselines.
  arXiv  Detail & Related papers  (2026-05-21T07:38:44Z)
• AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems [30.172832661173928]
  LLM-based multi-agent systems are increasingly deployed on long-horizon tasks.<n>A single decisive error is often accepted by downstream agents and cascades into trajectory-level failure.<n>We introduce AgentForesight, a framework that reframes this problem as online auditing.
  arXiv  Detail & Related papers  (2026-05-09T05:55:19Z)
• Affordance Agent Harness: Verification-Gated Skill Orchestration [45.231685718099264]
  Affordance grounding requires identifying where and how an agent should interact in open-world scenes.<n>We propose Affordance Agent Harness, a closed-loop runtime that unifies skills with an evidence store and cost control.
  arXiv  Detail & Related papers  (2026-05-01T13:45:16Z)
• Referring-Aware Visuomotor Policy Learning for Closed-Loop Manipulation [91.20850436220267]
  We introduce the Referring-Aware Visuomotor Policy (ReV)<n>ReV incorporates sparse referring points provided by a human or a high-level reasoning planner.<n>It is trained only by applying targeted perturbations to expert demonstrations.
  arXiv  Detail & Related papers  (2026-04-07T07:41:11Z)
• A Rubric-Supervised Critic from Sparse Real-World Outcomes [87.11204512676193]
  Real-world coding agents operate with humans in the loop, where success signals are typically noisy, delayed, and sparse.<n>We propose a process to learn a "critic" model from sparse and noisy interaction data, which can then be used both as a reward model for either RL-based training or inference-time scaling.
  arXiv  Detail & Related papers  (2026-03-04T07:23:54Z)
• Proposal Distribution Calibration for Few-Shot Object Detection [65.19808035019031]
  In few-shot object detection (FSOD), the two-step training paradigm is widely adopted to mitigate the severe sample imbalance. Unfortunately, the extreme data scarcity aggravates the proposal distribution bias, hindering the RoI head from evolving toward novel classes. We introduce a simple yet effective proposal distribution calibration (PDC) approach to neatly enhance the localization and classification abilities of the RoI head.
  arXiv  Detail & Related papers  (2022-12-15T05:09:11Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.