mlsanityData to 7 Oct 2026

TabAgent: A Framework for Replacing Agentic Generative Components with Tabular-Textual Classifiers

arXiv 2602.16429 ↗First posted 18 Feb 2026cs.CLcited by 2

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 39 of its 51 references that are in the map. First posted on arXiv 18 Feb 2026.

Builds on

39 of 51 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025Small Language Models are the Future of Agentic AI2 Jun
  2. 2025Generative to Agentic AI: Survey, Conceptualization, and Challenges26 Apr
  3. 2025Leveraging LLMs as Meta-Judges: A Multi-Agent Framework for Evaluating LLM Judgments23 Apr
  4. 2025Robotouille: An Asynchronous Planning Benchmark for LLM Agents6 Feb
  5. 2023A Survey on Large Language Model based Autonomous Agents22 Aug

Other references · 34

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  6. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  7. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  8. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  9. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  10. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  11. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  12. 2024A Survey on LLM-as-a-Judgecited by 1,384
22 more
  1. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
  2. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 846
  3. 2023Large Language Modelscited by 774
  4. 2022TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Secondcited by 643
  5. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 574
  6. 2024LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methodscited by 451
  7. 2020Movement Pruning: Adaptive Sparsity by Fine-Tuningcited by 398
  8. 2020TabTransformer: Tabular Data Modeling Using Contextual Embeddingscited by 398
  9. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Casescited by 383
  10. 2024AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agentscited by 359
  11. 2024Tool Learning with Large Language Models: A Surveycited by 221
  12. 2023RestGPT: Connecting Large Language Models with Real-World RESTful APIscited by 129
  13. 2024AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Callscited by 121
  14. 2023Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculumcited by 64
  15. 2024ToolNet: Connecting Large Language Models with Massive Tools via Tool Graphcited by 59
  16. 2024ToolRerank: Adaptive and Hierarchy-Aware Reranking for Tool Retrievalcited by 40
  17. 2024Encoder vs Decoder: Comparative Analysis of Encoder and Decoder Language Models on Multilingual NLU Taskscited by 33
  18. 2025Towards Enterprise-Ready Computer Using Generalist Agentcited by 31
  19. 2024Towards Completeness-Oriented Tool Retrieval for Large Language Modelscited by 26
  20. 2024Efficient and Scalable Estimation of Tool Representations in Vector Spacecited by 22
  21. 2025A Survey on Large Language Models for Automated Planningcited by 17
  22. 2024CodeACT: Code Adaptive Compute-efficient Tuning Framework for Code LLMscited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026What Does a Skill Actually Do? Estimands and Evaluation Validity for Tool and Skill Use in LLM Agents: A Critical Reviewcited by 0
  2. 2026What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Agentic Search Spaces for Tabular Machine Learning
  2. 2025TAGAL: Tabular Data Generation using Agentic LLM Methods
  3. 2026AgenticQwen: Training Small Agentic Language Models with Dual Data Flywheels for Industrial-Scale Tool Use
  4. 2026TabTracer: Monte Carlo Tree Search for Complex Table Reasoning with Large Language Models
  5. 2025Agentic Feature Augmentation: Unifying Selection and Generation with Teaming, Planning, and Memories
  6. 2026Memory-Augmented LLM-based Multi-Agent System for Automated Feature Generation on Tabular Data
  7. 2025AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoning
  8. 2026TabFM-Auto: Self-Evolving Pipelines for Tabular Foundation Models