Related papers: SkillRouter: Skill Routing for LLM Agents at Scale

Large language models excel at many tasks but often incur high inference costs during deployment. To mitigate hallucination, many systems use a knowledge graph to enhance retrieval-augmented generation (KG-RAG). However, the large amount of…

Skill routing is an important component in large-scale conversational systems. In contrast to traditional rule-based skill routing, state-of-the-art systems use a model-based approach to enable natural conversations. To provide supervision…

LLM agents now draw on growing skill libraries to handle complex tasks. However, injecting more skills does not always improve task completion and can even degrade it. Existing methods still treat skill injection as a static step, selecting…

Enterprise routers assign queries to expert agents, yet deployed profiles stay static while agents evolve (prompts, tools, models), and developers rarely keep descriptions or exemplars current. We present FlyRoute, a self-evolving profiling…

While most efforts to improve LLM-based tool-using agents focus on the agent itself - through larger models, better prompting, or fine-tuning - agent performance increasingly plateaus due to the quality of the tool interfaces these agents…

Prompt routing dynamically selects the most appropriate large language model from a pool of candidates for each query, optimizing performance while managing costs. As model pools scale to include dozens of frontier models with narrow…

Multi-agent AI systems have proven effective for complex reasoning. These systems are compounded by specialized agents, which collaborate through explicit communication, but incur substantial computational overhead. A natural question…

Evaluating AI agents on comprehensive benchmarks is expensive because each evaluation requires interactive rollouts with tool use and multi-step reasoning. We study whether small task subsets can preserve agent rankings at substantially…

Talent search is a cornerstone of modern recruitment systems, yet existing approaches often struggle to capture nuanced job-specific preferences, model recruiter behavior at a fine-grained level, and mitigate noise from subjective human…

Routing large language models (LLMs) is a new paradigm that uses a router to recommend the best LLM from a pool of candidates for a given input. In this paper, our comprehensive analysis with more than 8,500 LLMs reveals a novel model-level…

Large language model (LLM) routing assigns each query to the most suitable model from an ensemble. We introduce LLMRouterBench, a large-scale benchmark and unified framework for LLM routing. It comprises over 400K instances from 21 datasets…

With the rapid evolution of Large Language Model (LLM) agent ecosystems, centralized skill marketplaces have emerged as pivotal infrastructure for augmenting agent capabilities. However, these marketplaces face unprecedented security…

LLM-based web agents have recently made significant progress, but much of it has occurred in closed-source systems, widening the gap with open-source alternatives. Progress has been held back by two key challenges: first, a narrow focus on…

Skill ecosystems have emerged as an increasingly important layer in Large Language Model (LLM) agent systems, enabling reusable task packaging, public distribution, and community-driven capability sharing. However, despite their rapid…

While reasoning-augmented large language models (RLLMs) significantly enhance complex task performance through extended reasoning chains, they inevitably introduce substantial unnecessary token consumption, particularly for simpler problems…

Large language models (LLMs) and agent-based frameworks have advanced rapidly, enabling diverse applications. Yet, with the proliferation of models and agentic strategies, practitioners face substantial uncertainty in selecting the best…

As real-world datasets become more complex and heterogeneous, supervised learning is often bottlenecked by input representation design. Modeling multimodal data, such as time-series, free text, and structured records, often requires…

OpenClaw's ClawHub marketplace hosts tens of thousands of community-contributed agent skills (49,592 in our 2026-04-04 snapshot), and recent audits report that 13-26% contain security vulnerabilities. Regex scanners miss obfuscated…

LLM agents are rapidly becoming the practical interface for task automation, yet the ecosystem lacks a principled way to choose among an exploding space of deployable configurations. Existing LLM leaderboards and tool/agent benchmarks…

Large Language Model (LLM) agents are increasingly extended at runtime via skill packages, structured natural-language instruction bundles loaded from a well-known directory. Community install tooling and registries exist, but two gaps…