Learning What to Activate: Combinatorial Capability Allocation for Long-Horizon Multimodal Agents

arXiv:2609.27869 · cs.AI · Submitted 2026-08-20 · Read on arXiv

cs.AI

Submitted: 2026-08-20

Updated: 2026-08-20

Terminology

• Distillation — 34× in this paper · explained in 2 episodes
• Benchmark — 20× in this paper · explained in 2 episodes
• On-Policy Distillation — 12× in this paper · explained in 3 episodes
• Reinforcement Learning — 10× in this paper · explained in 4 episodes
• Accuracy — 8× in this paper · explained in 1 episode
• Ablation — 7× in this paper · explained in 1 episode
• Adaptation — 7× in this paper · explained in 1 episode
• Allocator — 5× in this paper · explained in 1 episode
• Ablation study — 4× in this paper · explained in 1 episode
• Action Space — 4× in this paper · explained in 1 episode
• Benchmarking — 4× in this paper · explained in 3 episodes
• Distribution Shift — 4× in this paper · explained in 6 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Consistency — 3× in this paper · explained in 3 episodes
• Grounding — 3× in this paper · explained in 3 episodes
• Ablation Studies — 2× in this paper · explained in 1 episode
• Demand-Shift Adaptation Accuracy — 2× in this paper
• Multimodal Reasoning — 2× in this paper · explained in 5 episodes
• Pairwise Comparisons — 2× in this paper · explained in 2 episodes
• Redundancy — 2× in this paper · explained in 2 episodes
• Teacher-Agreement Rate — 2× in this paper
• Visual Grounding — 2× in this paper · explained in 2 episodes
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Agent Skills — 1× in this paper · explained in 1 episode
• Agentic Reasoning — 1× in this paper · explained in 1 episode
• Agentic System — 1× in this paper · explained in 2 episodes
• Bradley-Terry model — 1× in this paper · explained in 2 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Distribution Matching — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Multi-agent Collaboration — 1× in this paper · explained in 2 episodes
• Preference Prediction Accuracy — 1× in this paper
• Regularization — 1× in this paper · explained in 3 episodes
• Task Planning — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale
• SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
• The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration
• OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning
• MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark
• EvoRoute: Experience-Driven Self-Routing LLM Agent Systems
• SkillSelect-Serve: QoS-Aware Budgeted Skill Service Recommendation for LLM Agents
• SOD: Step-wise On-policy Distillation for Small Language Model Agents

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
• 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
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection