This paper proposes Expert-Following Strategies, a framework that identifies top-performing investors based on historical ROI and recommends assets they purchased, scoring by ROI-weighted purchase fre…

The paper introduces ProbMoE, a probabilistic routing framework that tackles the non-differentiability of top-$k$ routing in Mixture-of-Experts (MoE) models, achieving strong performance with improved…

This paper proposes Workflow Cognition as a theoretical framework for explaining expertise as a dynamic cognitive phenomenon.

COLLEAGUE.SKILL introduces an automated system that distills heterogeneous traces of human expertise and role-specific knowledge into portable, inspectable, and usable AI skill packages.

The paper proposes HiSME, a lightweight hierarchical skill meta-evolving solution that jointly optimizes skills and the skill evolving strategy by learning meta-skills from task execution traces, lead…

MoG proposes a novel Mixture of Experts framework for graph-based RAG, which uses hub graphs to guide the sparse activation of domain-specific expert graphs, significantly improving retrieval accuracy…

The paper introduces MASA, a model-aware skill alignment framework that adaptively rewrites general and task-specific skills for LLM agents, achieving superior performance across diverse backbones and…

The paper introduces MMG2Skill, a closed-loop framework that converts noisy, human-oriented web guides into editable, executable skills, significantly improving agent performance across diverse tasks.

The paper develops a minimal dynamical model showing that adaptive softmax routing in Mixture-of-Experts (MoE) layers can undergo abrupt transitions to load imbalance via bifurcation mechanisms.

This paper proposes Hypothesis-Driven Skill Optimization (HDSO), a train-free framework for improving action-oriented LLM agents with external skills while preserving their frozen inference endpoints.

This paper introduces a controlled environment to study multi-turn long-horizon planning ability acquisition, shaping, and integration in foundation model agents.

This paper studies the problem of aggregating calibrated Bayesian experts into a new calibrated expert.

SkillRevise is an execution-grounded framework that iteratively refines initial, imperfect LLM agent skills by diagnosing defects from execution evidence and applying empirically validated edits, sign…

The paper introduces an uncertainty-aware framework that uses regulated expert advice to guide safe and efficient exploration for autonomous driving policies, significantly improving performance in co…

The paper proposes DAG-MoE, a novel sparse Mixture-of-Experts framework that replaces standard weighted-sum aggregation with structural aggregation to enhance model performance and enable multi-step r…

This paper develops a policy-learning framework to optimally assign prediction tasks to multiple agents, considering individual agent expertise and capacity constraints, achieving systematic performan…

This paper empirically demonstrates that the choice of plan representation (e.g., checklist vs. narrative) significantly impacts the robustness and success rate of LLM-based web agents.

The paper analyzes the routing behavior of Mixtral MoE under benign and harmful prompts using activation and gradient signals, finding that safety-relevant routing is subtle, depth-dependent, and dist…

The paper proposes Skill-RM, a unified framework that treats reward modeling as an agentic task to consistently integrate diverse evaluation criteria, achieving superior performance over traditional m…