# ASDA: Automated Skill Distillation and Adaptation for Financial Reasoning

arXiv: https://arxiv.org/abs/2603.16112 · HTML: https://mlsanity.com/paper/2603.16112/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 17 Mar 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 18 of 18)

- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models](https://mlsanity.com/paper/2510.04618/) (2025)
- [SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks](https://mlsanity.com/paper/2602.12670/) (2026)
- [SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning](https://mlsanity.com/paper/2602.08234/) (2026)
- [TextGrad: Automatic "Differentiation" via Text](https://mlsanity.com/paper/2406.07496/) (2024)
- [FinGPT: Open-Source Financial Large Language Models](https://mlsanity.com/paper/2306.06031/) (2023)
- [FinBen: A Holistic Financial Benchmark for Large Language Models](https://mlsanity.com/paper/2402.12659/) (2024)
- [EvoSkill: Automated Skill Discovery for Multi-Agent Systems](https://mlsanity.com/paper/2603.02766/) (2026)
- [SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?](https://mlsanity.com/paper/2603.15401/) (2026)
- [FinanceMath: Knowledge-Intensive Math Reasoning in Finance Domains](https://mlsanity.com/paper/2311.09797/) (2023)
- [FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation](https://mlsanity.com/paper/2505.24714/) (2025)
- [LEMMA: Learning from Errors for MatheMatical Advancement in LLMs](https://mlsanity.com/paper/2503.17439/) (2025)
- [FAMMA: A Benchmark for Financial Domain Multilingual Multimodal Question Answering](https://mlsanity.com/paper/2410.04526/) (2024)
- [FinanceQA: A Benchmark for Evaluating Financial Analysis Capabilities of Large Language Models](https://mlsanity.com/paper/2501.18062/) (2025)
- [FinMR: A Knowledge-Intensive Multimodal Benchmark for Advanced Financial Reasoning](https://mlsanity.com/paper/2510.07852/) (2025)

## Built on by (most cited first, 5 of 5)

- [Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning](https://mlsanity.com/paper/2605.10923/) (2026)
- [Ace-Skill: Bootstrapping Multimodal Agents with Prioritized and Clustered Evolution](https://mlsanity.com/paper/2605.08887/) (2026)
- [TimeClaw: A Time-Series AI Agent with Exploratory Execution Learning](https://mlsanity.com/paper/2605.10038/) (2026)
- [FinAcumen: Financial Multimodal Reasoning via Self-Evolving Experience Memory Harness](https://mlsanity.com/paper/2606.17642/) (2026)
- [FRAMES: Guarded and Dual-Objective Skill Evolution for Agents in Policy-Governed Enterprise Workflows](https://mlsanity.com/paper/2608.01772/) (2026)

## Abstract (arXiv)

Adapting large language models (LLMs) to specialized financial reasoning typically requires expensive fine-tuning that produces model-locked expertise. Training-free alternatives have emerged, yet our experiments show that leading methods (GEPA and ACE) achieve only marginal gains on the FAMMA financial reasoning benchmark, exposing the limits of unstructured text optimization for complex, multi-step domain reasoning. We introduce Automated Skill Distillation and Adaptation (ASDA), a framework that automatically generates structured skill artifacts through iterative error-corrective learning without modifying model weights. A teacher model analyzes a student model's failures on financial reasoning tasks, clusters errors by subfield and error type, and synthesizes skill files containing reasoning procedures, code templates, and worked examples, which are dynamically injected during inference. Evaluated on FAMMA, ASDA achieves up to +17.33% improvement on arithmetic reasoning and +5.95% on non-arithmetic reasoning, substantially outperforming all training-free baselines. The resulting skill artifacts are human-readable, version-controlled, and compatible with the Agent Skills open standard, offering any organization with a labeled domain dataset a practical and auditable path to domain adaptation without weight access or retraining.