RSI-Router: Evolving Subtask-Level LLM Routing and Skills for Cost-Efficient Agents
cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Sources
- Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement
- AgentPanel: Toward a New Paradigm for Human--AI Collaboration in Exploring Scientific Questions
- Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
- RouterBench: A Benchmark for Multi-LLM Routing System
- SkillOrchestra: Learning to Route Agents via Skill Transfer
- Budget-Aware Agentic Routing via Boundary-Guided Training
- Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignment
- PAPO: Stabilizing Rubric Integration Training via Decoupled Advantage Normalization
- Learning Compact Representations of LLM Abilities via Item Response Theory
- SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks
- Agent-as-a-Router: Agentic Model Routing for Coding Tasks
- Learning What to Retain: Gated-Memory Routing for Efficient Collaboration in Multi-Agent LLM Systems
- Meta-Harness: End-to-End Optimization of Model Harnesses
- Self-Harness: Harnesses That Improve Themselves
- HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
- Harness Continual Learning: Continual Adaptation Beyond Model Parameters
- SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
- Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
- SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
- Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems