Fusion is the New Mutation: Bandit-Guided Evolution on Workflow Graphs
cs.AI
Submitted: 2026-10-04
Updated: 2026-10-04
Sources
- Program Synthesis with Large Language Models
- Evaluating Large Language Models Trained on Code
- Training Verifiers to Solve Math Word Problems
- FlowReasoner: Reinforcing Query-Level Meta-Agents
- DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
- JudgeFlow: Agentic Workflow Optimization via Block Judge
- Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicine
- ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization
- EvoFlow: Evolving Diverse Agentic Workflows On The Fly
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
- MermaidFlow: Redefining Agentic Workflow Generation via Safety-Constrained Evolutionary Programming
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