Proactive Agentic Orchestration

cs.CL

Submitted: 2026-10-09

Updated: 2026-10-09

Comments: 41 pages including references and appendices, 11 figures. Code: https://github.com/XueyangFeng/POrchestra

Code: https://github.com/XueyangFeng/POrchestra

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
• Why Do Multi-Agent LLM Systems Fail?
• ARE: Scaling Up Agent Environments and Evaluations
• The Llama 3 Herd of Models
• Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems
• DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
• ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
• Orchestra-o1: Omnimodal Agent Orchestration
• LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering