Why Generate a Click? Plug-in Decision Heads for Web Agents
cs.CL
Submitted: 2026-10-14
Updated: 2026-10-14
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Understanding intermediate layers using linear classifier probes
- Qwen3-VL Technical Report
- Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
- FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
- The BrowserGym Ecosystem for Web Agent Research
- Can Multimodal Large Language Models Understand OCT?
- LoRA: Low-Rank Adaptation of Large Language Models
- KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls
- AdaTutoRank: Learning to Rerank Document Sets via Adaptive Tutoring Optimization for RAG and Deep Research
- Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking
- Tree Search for Language Model Agents
- KnowHal: A Knowledge-Driven Benchmark for Comprehensive Multimodal Hallucination Evaluation
- Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration
- From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search
- Decoupled Weight Decay Regularization
- WebLINX: Real-World Website Navigation with Multi-Turn Dialogue
- OmniParser for Pure Vision Based GUI Agent
- Can Visual Input Be Compressed? A Visual Token Compression Benchmark for Large Multimodal Models
- UI-TARS: Pioneering Automated GUI Interaction with Native Agents
- Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering