mlsanityData to 7 Oct 2026

From Language to Action in Arabic: Reliable Structured Tool Calling via Data-Centric Fine-Tuning

arXiv 2603.16901 ↗First posted 4 Mar 2026cs.LG cs.AIcited by 0

On the map: LLM agents and tool use → Tool learning and function calling

Abstract (arXiv)

Function-calling language models are essential for agentic AI systems that translate natural language into executable structured actions, yet existing models exhibit severe structural instability when applied to Arabic. We present AISA-AR-FunctionCall, a production-oriented Arabic function-calling framework built on a 270M-parameter FunctionGemma backbone and trained through systematic dataset auditing, schema repair, tool-aware prompt restructuring, and full-parameter supervised fine-tuning. On a held-out test set, fine-tuning reduces parse failures from 87% to below 1%, improves function name accuracy by more than eightfold, and substantially enhances argument alignment across dialects and domains. Error analysis reveals a transition from structural collapse to semantic misalignment, suggesting that serialization stability and decision-level reasoning are separable challenges. We further explore a reasoning-augmented LoRA variant that introduces explicit intermediate reasoning prior to tool invocation. All datasets and models are publicly released under the AISA framework.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 14 of its 29 references that are in the map. First posted on arXiv 4 Mar 2026.

Builds on

14 of 29 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models12 Mar
  2. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs31 Jul
  3. 2023ToolQA: A Dataset for LLM Question Answering with External Tools23 Jun
  4. 2023Toolformer: Language Models Can Teach Themselves to Use Tools9 Feb

Other references · 10

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,928
  4. 2025Gemma 3 Technical Reportcited by 1,686
  5. 2023AgentBench: Evaluating LLMs as Agentscited by 1,211
  6. 2020AraBERT: Transformer-based Model for Arabic Language Understandingcited by 359
  7. 2020ARBERT & MARBERT: Deep Bidirectional Transformers for Arabiccited by 164
  8. 2022MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoningcited by 153
  9. 2023AceGPT, Localizing Large Language Models in Arabiccited by 75
  10. 2023Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Modelscited by 68

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Arabic Prompts with English Tools: A Benchmark
  2. 2025Tool Calling for Arabic LLMs: Data Strategies and Instruction Tuning
  3. 2026Small Reasoning Models are Instruction Followers in Function Calling
  4. 2025On the Robustness of Agentic Function Calling
  5. 2024ToolACE: Winning the Points of LLM Function Calling
  6. 2026AgentWeave: Routing Before Reasoning for Efficient Function Calling in Tool-Rich Language Models
  7. 2025Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templates
  8. 2026Think-Augmented Function Calling: Improving LLM Parameter Accuracy Through Embedded Reasoning