EPS Dashboard

Authors: Kun Zeng, Yu Huo, Siyu Zhang et al.

Summary

The authors tackle a practical problem in agent systems: when an AI agent needs to retrieve skills from a large library, returning a flat list of individual skills forces the agent to figure out which one to run first, which are helpers, and how they fit together. Their "Group of Skills" method instead packages retrieved skills into a structured bundle with explicit labels—Start (the entry point), Support (helper skills), Check (preconditions), and Avoid (failure modes)—so the agent receives ready-to-execute context rather than raw pieces. Tests on two benchmarks (SkillsBench and ALFWorld) show this structured retrieval keeps important requirements visible even under tight memory budgets and often speeds up task completion.

Main takeaways:

Traditional skill retrieval returns atomic skills or dependency bundles but leaves the agent to infer execution order and roles, which wastes inference cycles and risks missing preconditions.
GoSkills builds a typed graph of skills, clusters them around "anchor" skills, and outputs a fixed contract with four fields: Start, Support, Check, and Avoid.
The method works at inference time—no retraining of the agent, the skill payloads, or the execution environment.
Experiments show better coverage of requirements under memory constraints and improved task success and runtime compared to flat-list baselines.
The approach is modular: you get structured context without changing how skills are stored or how the agent executes them.

Relevance

Not directly related to my persona or midtraining work—this is about skill libraries for tool-using agents rather than behavior installation or prompt/steering equivalence. Tangentially useful if I ever need to organize retrieval for multi-step agent behaviors.

Threat model

Potential threat/caveat for clean result "Stretching turn count, completion length, or system-prompt length at train time fails to amplify marker uptake; the longest system prompt instead leaks across bystander personas (LOW confidence)": this item discusses failure.

Abstract

arXiv:2605.06978v1 Announce Type: new Abstract: Skill-augmented agents increasingly rely on large reusable skill libraries, but retrieving relevant skills is not the same as presenting usable context. Existing methods typically return atomic skills or dependency-aware bundles whose internal roles remain implicit, leaving the agent to infer the execution entry point, support skills, visible requirements, and failure-avoidance guidance. We introduce Group of Skills (GoSkills), an inference-time group-structured retrieval method that changes the agent-facing retrieval object from a flat skill list to a compact, role-labeled execution context. GoSkills builds anchor-centered skill groups from a typed skill graph, expands support groups through a group graph, bottlenecks the selected group plan into a bounded set of atomic skill payloads, and renders a fixed execution contract with Start, Support, Check, and Avoid fields, without changing the downstream agent, skill payloads, or execution environment. Experiments on SkillsBench and ALFWorld show that GoSkills preserves visible-requirement coverage under a small skill budget, improves over flat skill-access baselines, and often improves reward and agent-only runtime relative to structural retrieval references.