TabAgent: Distilling LLM Agent Components into Cheap Classifiers

arXiv:2602.16429 · cs.CL · Submitted 2026-02-18 · Read on arXiv

cs.CL

Submitted: 2026-02-18

Updated: 2026-10-21

Comments: 67 pages, 14 figures, 26 tables. v2 is a substantial revision with a new title and two added authors. The evaluation is extended from AppWorld to seven agent benchmarks across three decision families (set retrieval, classification, policy and reward), and TabHead is now a CatBoost classifier with an ablation over classical and neural heads

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

Terminology

• Agentic System — 1× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

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