ASDA: Automated Skill Distillation and Adaptation for Financial Reasoning

arXiv:2603.16112 · cs.CL, cs.AI, cs.CE · Submitted 2026-03-17 · Read on arXiv

cs.CL, cs.AI, cs.CE

Submitted: 2026-03-17

Updated: 2026-09-07

Comments: Accepted to ECML-PKDD 2026, ADS Track

Code: https://github.com/SallyTan13/ASDA-skill

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

Terminology

• Adaptation — 24× in this paper · explained in 1 episode
• Distillation — 23× in this paper · explained in 2 episodes
• Benchmark — 12× in this paper · explained in 2 episodes
• Automated Skill Distillation and Adaptation — 11× in this paper
• Agent Skills — 7× in this paper · explained in 1 episode
• Fine-Tuning — 6× in this paper · explained in 5 episodes
• Accuracy — 5× in this paper · explained in 1 episode
• Iterative Refinement — 5× in this paper · explained in 3 episodes
• Verification — 5× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Domain Adaptation — 3× in this paper · explained in 5 episodes
• LLM judge — 3× in this paper · explained in 2 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Agent Architectures — 1× in this paper · explained in 1 episode
• Clustering — 1× in this paper · explained in 2 episodes
• Cross-Model Transfer — 1× in this paper · explained in 2 episodes
• Data Augmentation — 1× in this paper · explained in 7 episodes
• Error Taxonomy — 1× in this paper · explained in 2 episodes
• Hybrid Approach — 1× in this paper · explained in 4 episodes
• Modularity — 1× in this paper · explained in 9 episodes
• Progressive Disclosure — 1× in this paper · explained in 2 episodes
• Pruning — 1× in this paper · explained in 4 episodes

Sources

• Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
• GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
• LEMMA: Learning from Errors for MatheMatical Advancement in LLMs
• FinMR: A Knowledge-Intensive Multimodal Benchmark for Advanced Financial Reasoning
• FinBen: A Holistic Financial Benchmark for Large Language Models
• DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
• FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation
• FinanceQA: A Benchmark for Evaluating Financial Analysis Capabilities of Large Language Models
• Voyager: An Open-Ended Embodied Agent with Large Language Models
• BloombergGPT: A Large Language Model for Finance
• SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
• FAMMA: A Benchmark for Financial Domain Multilingual Multimodal Question Answering
• FinGPT: Open-Source Financial Large Language Models
• TextGrad: Automatic "Differentiation" via Text
• FinanceMath: Knowledge-Intensive Math Reasoning in Finance Domains

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