# Task-Adaptive Rubrics for GUI Reward Modeling

arXiv: https://arxiv.org/abs/2608.24174 · HTML: https://mlsanity.com/paper/2608.24174/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 25 of its 52 references that are in the map.
- First posted on arXiv 25 Aug 2026.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)
- LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/)
- LLM alignment / RLHF / preference optimisation / [Process reward models for reasoning](https://mlsanity.com/alignment/process-reward-models-for-reasoning/)

## Builds on (most cited first, 25 of 25)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [CogAgent: A Visual Language Model for GUI Agents](https://mlsanity.com/paper/2312.08914/) (2023)
- [Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains](https://mlsanity.com/paper/2507.17746/) (2025)
- [WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning](https://mlsanity.com/paper/2411.02337/) (2024)
- [Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale](https://mlsanity.com/paper/2409.08264/) (2024)
- [DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning](https://mlsanity.com/paper/2406.11896/) (2024)
- [On the Effects of Data Scale on UI Control Agents](https://mlsanity.com/paper/2406.03679/) (2024)
- [InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners](https://mlsanity.com/paper/2504.14239/) (2025)
- [Autonomous Evaluation and Refinement of Digital Agents](https://mlsanity.com/paper/2404.06474/) (2024)
- [MAI-UI Technical Report: Real-World Centric Foundation GUI Agents](https://mlsanity.com/paper/2512.22047/) (2025)
- [Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents](https://mlsanity.com/paper/2602.16855/) (2026)
- [MobileWorld: Benchmarking Autonomous Mobile Agents in Agent-User Interactive and MCP-Augmented Environments](https://mlsanity.com/paper/2512.19432/) (2025)
- [DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agents](https://mlsanity.com/paper/2410.14803/) (2024)
- [InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection](https://mlsanity.com/paper/2501.04575/) (2025)
- [Learning to Navigate the Web](https://mlsanity.com/paper/1812.09195/) (2018)
- [ZeroGUI: Automating Online GUI Learning at Zero Human Cost](https://mlsanity.com/paper/2505.23762/) (2025)
- [AgentRM: Enhancing Agent Generalization with Reward Modeling](https://mlsanity.com/paper/2502.18407/) (2025)
- [CARMO: Dynamic Criteria Generation for Context-Aware Reward Modelling](https://mlsanity.com/paper/2410.21545/) (2024)
- [ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents](https://mlsanity.com/paper/2604.11784/) (2026)
- [STEP: Success-Rate-Aware Trajectory-Efficient Policy Optimization](https://mlsanity.com/paper/2511.13091/) (2025)
- [Adaptive Milestone Reward for GUI Agents](https://mlsanity.com/paper/2602.11524/) (2026)
- [ProRe: A Proactive Reward System for GUI Agents via Reasoner-Actor Collaboration](https://mlsanity.com/paper/2509.21823/) (2025)
- [OS-Themis: A Scalable Critic Framework for Generalist GUI Rewards](https://mlsanity.com/paper/2603.19191/) (2026)

## Built on by (most cited first, 1 of 1)

- [SCOUT: Synergizing Reasoning and Tool-Use for Computer-Use Safety](https://mlsanity.com/paper/2609.36201/) (2026)

## Abstract (arXiv)

Recent studies on GUI agents have increasingly focused on outcome reward modeling, which assigns outcome rewards by judging whether an executed trajectory satisfies the success criteria implied by the user instruction. Existing GUI reward verifiers, however, often under-specify how these criteria should be constructed for each task instance. Whether using generic rubric structures or implicit model reasoning, their judging criteria are not sufficiently task-adaptive: they can transfer checks across tasks, overlook concrete constraints in the current instruction, or become overly strict by enforcing unstated requirements. To address this limitation, we propose AdaptRubric, a Coarse-to-Fine Rubrics Framework that constructs task-adaptive judging criteria through a category-level coarse stage and an instance-level fine stage. AdaptRubric performs category-level coarse rubric retrieval by routing the instruction to a GUI task family and retrieving reusable task-family criteria, then conducts instance-level fine rubric generation to surface compact cues for concrete values, scopes, and constraints in the current instruction. Across offline reward evaluation and online reinforcement learning optimization, AdaptRubric consistently outperforms prior reward agents, improving F1 by 3.6 points over the baseline average under a matched image budget and yielding a 4.23-point task-success gain.