ASDA: Automated Skill Distillation and Adaptation for Financial Reasoning

• URL: http://arxiv.org/abs/2603.16112v1
• Date: Tue, 17 Mar 2026 04:25:54 GMT
• Title: ASDA: Automated Skill Distillation and Adaptation for Financial Reasoning
• Abstract summary: We introduce Automated Skill Distillation and Adaptation (ASDA), a framework that automatically generates structured skill artifacts.<n>A teacher model analyzes a student model's failures on financial reasoning tasks.<n>ASDA achieves up to +17.33% improvement on arithmetic reasoning and +5.95% on non-arithmetic reasoning.
• Score: 12.07645818151562
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• SkillTFM: Gated Skill Evolution for Training-Free Adaptation of Tabular Foundation Models [59.078670951794415]
  We propose SkillTFM, a training-free system that shifts Tabular Foundation Models from gated evolution of agentic skills to reusable skills.<n>Across simulated boundary settings and real-world electricity-price forecasting, SkillTFM improves AUC by 0.128--0.142, raises nonlinear-boundary AUC from 0.699 to 0.898.
  arXiv  Detail & Related papers  (2026-08-06T15:09:02Z)
• VASO: Formally Verifiable Self-Evolving Skills for Physical AI Agents [57.240036084348354]
  We introduce VASO, a framework for verification-guided self-evolution of robot skill contracts.<n>VASO verifies logically inconsistent skill contracts, then verifies plans induced by the skill against global and local temporal specifications.<n>On Clearpath Jackal and PX4 quadcopter tasks, VASO reaches 97.2% formal-specification compliance using fewer than 100 optimization samples.
  arXiv  Detail & Related papers  (2026-06-03T20:02:35Z)
• Generating Data-Driven Reasoning Rubrics for Domain-Adaptive Reward Modeling [21.45871501724415]
  We propose a data-driven approach to automatically construct highly granular reasoning model error.<n>Rubrics can be used to build stronger LLM-as-judge reward functions.<n>This extension opens the door for teaching models to solve complex technical problems without a full dataset of gold labels.
  arXiv  Detail & Related papers  (2026-02-06T15:51:52Z)
• Error-Driven Prompt Optimization for Arithmetic Reasoning [0.0]
  We introduce an error-driven optimization framework for arithmetic reasoning that enhances a Code Generation Agent (CGA)<n>We find that while the base model exhibits fundamental limitations in arithmetic tasks, our proposed error-driven method, which clusters erroneous predictions, dramatically improves performance.<n>Our results suggest that developing reliable, interpretable, and industrially deployable AI assistants can be achieved not only through costly fine-tuning but also via systematic, error-driven prompt optimization.
  arXiv  Detail & Related papers  (2025-12-15T13:39:14Z)
• Autoformalizer with Tool Feedback [52.334957386319864]
  Autoformalization addresses the scarcity of data for Automated Theorem Proving (ATP) by translating mathematical problems from natural language into formal statements.<n>Existing formalizer still struggles to consistently generate valid statements that meet syntactic validity and semantic consistency.<n>We propose the Autoformalizer with Tool Feedback (ATF), a novel approach that incorporates syntactic and consistency information as tools into the formalization process.
  arXiv  Detail & Related papers  (2025-10-08T10:25:12Z)
• MAB Optimizer for Estimating Math Question Difficulty via Inverse CV without NLP [3.9566483499208633]
  This study introduces the Approach of Passive Measures among Educands (APME), a reinforcement learning-based Multi-Armed Bandit (MAB) framework.<n>By leveraging the inverse coefficient of variation as a risk-adjusted metric, the model provides an explainable and scalable mechanism for adaptive assessment.
  arXiv  Detail & Related papers  (2025-08-26T13:23:31Z)
• Auto-Search and Refinement: An Automated Framework for Gender Bias Mitigation in Large Language Models [43.20359264464913]
  Pre-training large language models (LLMs) on vast text corpora enhances natural language processing capabilities but risks encoding social biases.<n>Experiments demonstrate that FaIRMaker automatically searches for and dynamically refines Fairwords, effectively mitigating gender bias.
  arXiv  Detail & Related papers  (2025-02-17T08:44:04Z)
• A Comparative Analysis of Instruction Fine-Tuning LLMs for Financial Text Classification [0.8192907805418583]
  Large Language Models (LLMs) have demonstrated impressive capabilities across diverse Natural Language Processing (NLP) tasks. This study investigates the efficacy of instruction fine-tuning to enhance their performance in financial text classification tasks.
  arXiv  Detail & Related papers  (2024-11-04T18:06:36Z)
• Evaluating Mathematical Reasoning Beyond Accuracy [50.09931172314218]
  We introduce ReasonEval, a new methodology for evaluating the quality of reasoning steps.<n>We show that ReasonEval consistently outperforms baseline methods in the meta-evaluation datasets.<n>We observe that ReasonEval can play a significant role in data selection.
  arXiv  Detail & Related papers  (2024-04-08T17:18:04Z)
• An Empirical Study of Automatic Post-Editing [56.86393786396992]
  APE aims to reduce manual post-editing efforts by automatically correcting errors in machine-translated output. To alleviate the lack of genuine training data, most of the current APE systems employ data augmentation methods to generate large-scale artificial corpora. We study the outputs of the state-of-art APE model on a difficult APE dataset to analyze the problems in existing APE systems.
  arXiv  Detail & Related papers  (2022-09-16T07:38:27Z)
• NoiER: An Approach for Training more Reliable Fine-TunedDownstream Task Models [54.184609286094044]
  We propose noise entropy regularisation (NoiER) as an efficient learning paradigm that solves the problem without auxiliary models and additional data. The proposed approach improved traditional OOD detection evaluation metrics by 55% on average compared to the original fine-tuned models.
  arXiv  Detail & Related papers  (2021-08-29T06:58:28Z)
• Learning to Perturb Word Embeddings for Out-of-distribution QA [55.103586220757464]
  We propose a simple yet effective DA method based on a noise generator, which learns to perturb the word embedding of the input questions and context without changing their semantics. We validate the performance of the QA models trained with our word embedding on a single source dataset, on five different target domains. Notably, the model trained with ours outperforms the model trained with more than 240K artificially generated QA pairs.
  arXiv  Detail & Related papers  (2021-05-06T14:12:26Z)
• Uncertainty-Aware Consistency Regularization for Cross-Domain Semantic Segmentation [63.75774438196315]
  Unsupervised domain adaptation (UDA) aims to adapt existing models of the source domain to a new target domain with only unlabeled data. Most existing methods suffer from noticeable negative transfer resulting from either the error-prone discriminator network or the unreasonable teacher model. We propose an uncertainty-aware consistency regularization method for cross-domain semantic segmentation.
  arXiv  Detail & Related papers  (2020-04-19T15:30:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.