# TabAgent: Distilling LLM Agent Components into Cheap Classifiers

Authors: Ido Levy, Segev Shlomov, Avi Yaeli, Nir Mashkif, Asaf Adi, Yinon Goldshtein, Eilam Shapira, Leshem Choshen
Venue: preprint (2026)

## Abstract
Agentic systems, AI architectures that autonomously execute multi-step workflows to achieve complex goals, are often built using repeated large language model (LLM) calls for closed-set decision tasks such as routing, shortlisting, gating, and verification. While convenient, this design makes deployments slow and expensive due to cumulative latency and token usage. We propose TabAgent, a framework for replacing generative decision components in closed-set selection tasks with a compact textual-tabular classifier trained on execution traces. TabAgent (i) extracts structured schema, state, and dependency features from trajectories (TabSchema), (ii) augments coverage with schema-aligned synthetic supervision (TabSynth), and (iii) scores candidates with a lightweight classifier (TabHead). On the long-horizon AppWorld benchmark, TabAgent maintains task-level success while eliminating shortlist-time LLM calls, reducing latency by approximately 95% and inference cost by 85-91%. Beyond tool shortlisting, TabAgent generalizes to other agentic decision heads, establishing a paradigm for learned discriminative replacements of generative bottlenecks in production agent architectures.

## Links
- arXiv: https://arxiv.org/abs/2602.16429
- PDF: https://arxiv.org/pdf/2602.16429
- HTML: https://arxiv.org/html/2602.16429
- Hugging Face: https://huggingface.co/papers/2602.16429
- alphaXiv: https://www.alphaxiv.org/abs/2602.16429
- Semantic Scholar: https://www.semanticscholar.org/paper/285726119