Report: Progressive Disclosure of Agent Skills

Users of Workday's deployed LLM-based agents often request features which can be addressed by defining named procedures, also known as skills, in the LLM context, effectively augmenting agents' capabilities. However, as an agent's skills library grows in size, so does the agent's operational cost. Progressive disclosure (lazy-loading) of skills as needed may reduce operational costs, but its…

arxiv.org ·2026-09-28

We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.

Read the original at arxiv.org →

More in AI

Autoheal Raises $7.9M From Innovation Endeavors to Make Enterprise Software Heal Itself

Autoheal raises $7.9M led by Innovation Endeavors for self-healing AI agents that fix incidents, patch security flaws and cut AI coding costs at Nomura.

2026-09-28 ·hackernoon.com

AI agent startup Instinct hits $10 billion valuation following $1 billion round

2026-09-28 ·investing.com

Rethinking Circuit Evaluation: Do Circuits Explain Model Errors?

Mechanistic interpretability (MI) aims to explain a model's behaviour through analyzing its internal computations; circuit-based explanations aim to isolate these computations with compact subnetworks…

2026-09-28 ·arxiv.org

Reasoning with Continuous Latent Diffusion

Continuous diffusion generates complete reasoning solutions through iterative refinement in latent space. We introduce Latent Flow Reasoning Models (LFRMs), an ELF-based training and inference recipe.

2026-09-28 ·arxiv.org

Distillation Defenses Easily Break After Reinforcement Learning

Distillation attacks copy the reasoning capabilities of closed-source large language models, allowing bad actors to replicate state-of-the-art performance at low cost.

2026-09-28 ·arxiv.org

A Unified Uncertainty Representation for Graph Neural Networks via Doubly-Spectral Stochastic Expansion

Reliable deployment of graph neural networks requires calibration, out-of-distribution (OOD) detection, and robustness to distribution shift, yet existing methods address these needs with separate models and objectives.

2026-09-28 ·arxiv.org