Disentangled Skill Representations for Predictive Human Modeling

• URL: http://arxiv.org/abs/2608.23776v1
• Date: Mon, 24 Aug 2026 19:13:47 GMT
• Title: Disentangled Skill Representations for Predictive Human Modeling
• Abstract summary: Skill Abstraction with Interpretable Latents (SAIL) is a method for modeling human skill as an interpretable, multi-dimensional construct inferred from naturalistic behavior.<n>Our approach produces a skill embedding that is robust to transient performance fluctuations and learns a transferable representation of human subskills.
• Score: 6.71775308061443
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Understanding human skill is important for AI systems that collaborate with, coach, or assist people. Unlike typical latent variable estimation problems which rely on single observations, skill is a persistent, compositional, and behaviorally grounded construct that must be inferred from patterns over time. We introduce Skill Abstraction with Interpretable Latents (SAIL), a method for modeling human skill as an interpretable, multi-dimensional construct inferred from naturalistic behavior. Our approach produces a skill embedding that is robust to transient performance fluctuations and learns a transferable representation of human subskills. Furthermore, SAIL supports skill-informed behavior prediction that generalizes across a variety of in-domain contexts. We represent each individual with a persistent skill embedding that controls a blend between expert and novice bases and is trained using counterfactual subskill swaps for disentanglement. This design encourages representations that are both robust to performance variation and structured for interpretability. We demonstrate across racing and baseball that SAIL achieves strong predictive performance and consistently improves behaviorally grounded disentanglement over the evaluated baselines, while also improving downstream AI coaching performance.

Related papers

• Mind the Student: Behavioral and Contextual Cues for Automated Engagement Prediction in Online Learning [9.31020526280198]
  We develop a framework that integrates implicit features extracted from video, audio, and image encoders along with structured behavioral modalities like head pose, gaze, facial action units, emotion, and wavelet-based audio features.<n>We employ evidential regression and spectral-normalized Gaussian process classification heads for uncertainty-aware prediction to improve and calibration robustness.
  arXiv  Detail & Related papers  (2026-08-25T10:03:07Z)
• Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills [53.15216425100295]
  We introduce Skill Self-Play (Skill-SP), a co-evolutionary framework comprising a proposer, a solver, and a skill controller.<n>The proposer generates challenging tasks conditioned on dynamically sampled skills; the solver explores candidate solutions to push its capability boundaries; and the skill controller collects execution feedback to update and expand the skill library.<n>This interactive co-evolution effectively bridges the gap between structured verification and open-ended exploration.
  arXiv  Detail & Related papers  (2026-07-24T17:59:22Z)
• SkillComposer: Learning to Evolve Agent Skills for Specification and Generalization [99.18305770138677]
  Agent skills are reusable strategies that guide agent reasoning and action.<n>Current skill construction methods treat the problem as one-shot extraction.<n>We introduce SkillComposer, a framework that decomposes skill construction into three learnable operations.
  arXiv  Detail & Related papers  (2026-06-04T12:16:08Z)
• From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills [46.76651106969111]
  We show that model-generated skills are beneficial on average but exhibit non-trivial negative transfer.<n>A model can be a strong extractor yet a weak consumer, or vice versa, with skill utility independent of model scale or baseline task strength.<n>We translate these findings into a concrete emphmeta-skill that guides skill extraction.
  arXiv  Detail & Related papers  (2026-05-22T17:59:12Z)
• Enhanced Interpretable Knowledge Tracing for Students Performance Prediction with Human understandable Feature Space [2.053999499982333]
  Knowledge Tracing (KT) plays a central role in assessing students skill mastery and predicting their future performance.<n>Our contributions aim to balance predictive power with interpretability, advancing the utility of adaptive learning systems.
  arXiv  Detail & Related papers  (2025-09-22T13:47:28Z)
• SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution [75.2573501625811]
  Diffusion models have demonstrated strong potential for robotic trajectory planning. generating coherent trajectories from high-level instructions remains challenging. We propose SkillDiffuser, an end-to-end hierarchical planning framework.
  arXiv  Detail & Related papers  (2023-12-18T18:16:52Z)
• Real-time Addressee Estimation: Deployment of a Deep-Learning Model on the iCub Robot [52.277579221741746]
  Addressee Estimation is a skill essential for social robots to interact smoothly with humans. Inspired by human perceptual skills, a deep-learning model for Addressee Estimation is designed, trained, and deployed on an iCub robot. The study presents the procedure of such implementation and the performance of the model deployed in real-time human-robot interaction.
  arXiv  Detail & Related papers  (2023-11-09T13:01:21Z)
• AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model [69.12623428463573]
  AlignDiff is a novel framework to quantify human preferences, covering abstractness, and guide diffusion planning. It can accurately match user-customized behaviors and efficiently switch from one to another. We demonstrate its superior performance on preference matching, switching, and covering compared to other baselines.
  arXiv  Detail & Related papers  (2023-10-03T13:53:08Z)
• C$\cdot$ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characters [49.83342243500835]
  We present C$cdot$ASE, an efficient framework that learns conditional Adversarial Skill Embeddings for physics-based characters. C$cdot$ASE divides the heterogeneous skill motions into distinct subsets containing homogeneous samples for training a low-level conditional model. The skill-conditioned imitation learning naturally offers explicit control over the character's skills after training.
  arXiv  Detail & Related papers  (2023-09-20T14:34:45Z)

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.