SeekJudge: A Practical Reward Framework for Reinforcement Learning in Computer-Use Agents

arXiv:2607.23263 · cs.AI · Submitted 2026-07-25 · Read on arXiv

cs.AI

Submitted: 2026-07-25

Updated: 2026-09-26

Code: https://github.com/ZJUSCL/SeekJudge

Terminology

• Benchmark — 48× in this paper · explained in 2 episodes
• Reinforcement Learning — 18× in this paper · explained in 4 episodes
• Actor — 10× in this paper · explained in 3 episodes
• Distillation — 10× in this paper · explained in 2 episodes
• Calibration — 9× in this paper · explained in 7 episodes
• Accuracy — 6× in this paper · explained in 1 episode
• Benchmarking — 6× in this paper · explained in 3 episodes
• GRPO — 5× in this paper · explained in 6 episodes
• Verifier — 5× in this paper · explained in 2 episodes
• Fidelity — 4× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Alignment — 3× in this paper · explained in 1 episode
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• In International Conference on Learning Representations — 2× in this paper
• LLM-as-a-Judge — 2× in this paper · explained in 3 episodes
• Meeting of the Association for Computational Linguistics — 2× in this paper
• Adaptation — 1× in this paper · explained in 1 episode
• Credit assignment — 1× in this paper · explained in 3 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• In First Conference on Language Modeling — 1× in this paper
• KV cache — 1× in this paper · explained in 3 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 24 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Gym-Anything: Turn any Software into an Agent Environment
• DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
• WebGym: Scaling Training Environments for Visual Web Agents with Realistic Tasks
• Mind2Web: Towards a Generalist Agent for the Web
• WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models
• PRO-CUA: Process-Reward Optimization for Computer Use Agents
• Expanding Computation Spaces of LLMs at Inference Time
• VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks
• On the Effects of Data Scale on UI Control Agents
• OS-Themis: A Scalable Critic Framework for Generalist GUI Rewards
• Let's Verify Step by Step
• CUARewardBench: A Benchmark for Evaluating Reward Models on Computer-using Agent
• AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories
• Autonomous Evaluation and Refinement of Digital Agents
• WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning
• UI-TARS: Pioneering Automated GUI Interaction with Native Agents
• AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents
• The Art of Building Verifiers for Computer Use Agents
• SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience
• CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection