CB-Orchestrator: Adaptive Workflow Optimization for LLM Agents via Contextual Bandits
cs.LG
Submitted: 2026-10-09
Updated: 2026-10-09
Terminology
Sources
- Program Synthesis with Large Language Models
- TapeAgents: a Holistic Framework for Agent Development and Optimization
- Evaluating Large Language Models Trained on Code
- Training Verifiers to Solve Math Word Problems
- FlowReasoner: Reinforcing Query-Level Meta-Agents
- The Llama 3 Herd of Models
- Polymath: A Self-Optimizing Agent with Dynamic Hierarchical Workflow
- OMAC: A Holistic Optimization Framework for LLM-Based Multi-Agent Collaboration
- AutoFlow: Automated Workflow Generation for Large Language Model Agents
- SEW: Self-Evolving Agentic Workflows for Automated Code Generation
- ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization
- Sibyl: Simple yet Effective Agent Framework for Complex Real-world Reasoning
- RobustFlow: Towards Robust Agentic Workflow Generation
- EvoFlow: Evolving Diverse Agentic Workflows On The Fly
- Failure-Driven Workflow Refinement
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
- MermaidFlow: Redefining Agentic Workflow Generation via Safety-Constrained Evolutionary Programming
- Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks