Beyond Top-$k$ Skill Retrieval: Diversity-Aware Skill Routing for LLM Agents

• URL: http://arxiv.org/abs/2609.05824v1
• Date: Sat, 05 Sep 2026 02:39:28 GMT
• Title: Beyond Top-$k$ Skill Retrieval: Diversity-Aware Skill Routing for LLM Agents
• Abstract summary: We propose Diverse Skill Routing (DSR), a diversity-aware reranking framework.<n>DSR penalizes redundant skill overlap while reducing penalties caused only by shared query relevance.<n>On the Skill routing benchmark, DSR improves recall and full coverage over a strong pointwise reranking baseline.
• Score: 79.02474149053074
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language model (LLM) agents increasingly rely on external skills, but routing user requests over large skill registries is difficult because many skills are functionally redundant while complex tasks often require complementary skill sets. Existing skill routers typically rank candidates independently by query relevance, which can waste context budget on redundant skills. We propose Diverse Skill Routing (DSR), a diversity-aware reranking framework that uses a Determinantal Point Process to balance relevance and non-redundancy. DSR introduces a query-residual diversity kernel that penalizes redundant skill overlap while reducing penalties caused only by shared query relevance. On the SkillRouter benchmark, DSR improves recall and full coverage over a strong pointwise reranking baseline, with larger gains on multi-skill queries. These results suggest that skill routing should be treated not only as relevance ranking, but also as complementary set selection.

Related papers

• Task Decomposition-Guided Reranking for Adaptive Agent Skill Retrieval [16.270741233471107]
  We propose SkillReranker, an inference-time reranking framework for adaptive skill selection.<n>We show that SkillReranker effectively improves task performance, reduces environment interaction steps, and lowers token consumption.
  arXiv  Detail & Related papers  (2026-07-07T13:49:08Z)
• Co-Evolving Skill Generation and Policy Optimization [35.41582114275514]
  Existing methods typically use strong language models to analyze trajectories, generate skills, and update a retrievable skill bank during online training.<n>We propose an online reinforcement learning framework for pre-storage skill validation.
  arXiv  Detail & Related papers  (2026-06-07T17:55:55Z)
• SkillBrew: Multi-Objective Curation of Skill Banks for LLM Agents [71.54500730593263]
  LLM agents increasingly rely on curated skill banks.<n>Existing approaches expand these banks in an append-only fashion.<n>We introduce SkillBrew, a multi-objective curation framework.
  arXiv  Detail & Related papers  (2026-05-28T06:33:52Z)
• SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs [70.1970574147839]
  We propose SKILLGRAPH, a framework that represents reusable skills as nodes in a directed graph.<n>SKILLGRAPH retrieves not just individual skills, but an ordered skill subgraph that can guide multi-step decision making.<n> Experiments show that SKILLGRAPH achieves state-of-the-art performance against memory-augmented RL methods.
  arXiv  Detail & Related papers  (2026-05-12T12:21:49Z)
• Skill-R1: Agent Skill Evolution via Reinforcement Learning [84.35984979949502]
  Skill-R1 is a reinforcement learning framework for instance-level recurrent skill optimization from verifiable rewards.<n>It preserves black-box compatibility with both open- and closed-source models while making adaptation substantially cheaper than model-level updates.
  arXiv  Detail & Related papers  (2026-05-10T06:19:15Z)
• SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agents [6.293920920196533]
  SkillLens is a hierarchical skill-evolution framework that organizes skills into a four-layer graph of policies, strategies, procedures, and primitives.<n>It retrieves semantically relevant skill seeds, expands them through degree-corrected random walk over the skill graph, and then uses a verifier to decide whether each visited unit should be accepted, decomposed, rewritten, or skipped.<n>Across MuLocbench and ALFWorld, SkillLens consistently improves over strong skill-based baselines.
  arXiv  Detail & Related papers  (2026-05-08T18:48:04Z)
• SkillOS: Learning Skill Curation for Self-Evolving Agents [67.94374107466957]
  We propose SkillOS, an experience-driven RL training recipe for learning skill curation in self-evolving agents.<n>SkillOS pairs a frozen agent executor that retrieves and applies skills with a trainable skill curator that updates an external SkillRepo from accumulated experience.<n>We show that SkillOS consistently outperforms memory-free and strong memory-based baselines in both effectiveness and efficiency.
  arXiv  Detail & Related papers  (2026-05-07T17:31:50Z)
• From Context to Skills: Can Language Models Learn from Context Skillfully? [56.5857437218136]
  Ctx2Skill is a self-evolving framework that autonomously discovers, refines, and selects context-specific skills.<n>It can be plugged into any language model to obtain better context learning capability.
  arXiv  Detail & Related papers  (2026-04-30T09:53:15Z)
• Skill Retrieval Augmentation for Agentic AI [28.71123853744993]
  In existing agent systems, the dominant strategy for incorporating skills is to enumerate available skills within the context window.<n>This paper formulates Skill Retrieval Augmentation (SRA), a new paradigm in which agents dynamically retrieve, incorporate, and apply relevant skills from large external skill corpora on demand.<n>SRA-Bench is the first benchmark for evaluation of the full SRA pipeline, covering skill retrieval, skill incorporation, and end-task execution.
  arXiv  Detail & Related papers  (2026-04-27T15:19:59Z)
• SkillRouter: Skill Routing for LLM Agents at Scale [18.540967600258607]
  Given a user task, the system must identify relevant skills before downstream planning or execution.<n>Existing agent stacks often rely on progressive disclosure, exposing only skill names and descriptions while hiding the full implementation body.<n>We present Skill, a compact 1.2B full-text retrieve-and-rerank pipeline.
  arXiv  Detail & Related papers  (2026-03-23T18:23:59Z)
• Skill-Based Reinforcement Learning with Intrinsic Reward Matching [77.34726150561087]
  We present Intrinsic Reward Matching (IRM), which unifies task-agnostic skill pretraining and task-aware finetuning. IRM enables us to utilize pretrained skills far more effectively than previous skill selection methods.
  arXiv  Detail & Related papers  (2022-10-14T00:04:49Z)

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.