Routing Is Least Learnable Where It Is Most Valuable: Bounds on Representation Routing for Web Agents

arXiv:2608.06171 · cs.CL · Submitted 2026-08-06 · Read on arXiv

Jiaming Wei, Zekun Wu, Adriano Koshiyama, Maria Perez-Ortiz

cs.CL

Submitted: 2026-08-06

Comments: Preprint. Under review at the Second Workshop for Research on Agent Language Models (REALM), EMNLP 2026 (non-archival track)

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 21× in this paper · explained in 2 episodes
• AUROC — 11× in this paper · explained in 3 episodes
• Grounding — 11× in this paper · explained in 3 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Accuracy — 5× in this paper · explained in 1 episode
• Consistency — 4× in this paper · explained in 3 episodes
• Visual Grounding — 4× in this paper · explained in 2 episodes
• Harness — 3× in this paper · explained in 2 episodes
• Action Space — 2× in this paper · explained in 1 episode
• Decode — 2× in this paper · explained in 2 episodes
• Exchangeability — 2× in this paper · explained in 2 episodes
• Provenance — 2× in this paper · explained in 5 episodes
• Scaffold — 2× in this paper · explained in 2 episodes
• Absorb — 1× in this paper · explained in 1 episode
• Admissibility — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Failure Attribution — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Feedback Loop — 1× in this paper · explained in 2 episodes
• Information Bottleneck — 1× in this paper · explained in 3 episodes
• Planner — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Sparsity — 1× in this paper · explained in 4 episodes
• Thinking mode — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
• Language Model Cascades: Token-level uncertainty and beyond
• Are Online Skill and Memory Modules Always Worth Their Tokens? A Budget-Constrained Study of Web Agents
• Language Models (Mostly) Know What They Know
• WebRouter: Query-specific Router via Variational Information Bottleneck for Cost-sensitive Web Agent
• Adaptive Vision-Language Model Routing for Computer Use Agents
• AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories
• Dynamic Model Routing and Cascading for Efficient LLM Inference: A Survey
• An Illusion of Progress? Assessing the Current State of Web Agents
• Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
• Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference

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