Proactive Agentic Orchestration

arXiv 2610.13485 ↗First posted 9 Oct 2026cs.CLcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Agentic orchestration delegates tasks to sub-agents with independent contexts, providing a key path to extending the effective execution horizon of large language model agents. However, existing orchestration methods face two limitations: in execution, current methods fix sub-agents' goals and harnesses at creation time, limiting their adaptability to dynamic real-world environments; in optimization, sparse and delayed feedback constrains effective learning of the orchestration policy. To address these limitations, we introduce POrchestra, an on-the-fly proactive agentic orchestration framework. It allows sub-agents to proactively communicate with the orchestrator at any logical point to request harness adjustments while maintaining continuity of local execution. This mechanism not only enables sub-agents to adapt seamlessly to dynamic environments but also naturally inspires On-Policy Orchestration Distillation (OPOD) based on hindsight feedback. OPOD attributes sub-agents' proactive revision requests back to preceding orchestration decisions to derive targeted improvement signals, and leverages these signals as process supervision alongside the final reward to optimize the orchestration policy. We evaluate POrchestra on three long-horizon agent benchmarks spanning deep research, dynamic digital assistance, and software engineering. POrchestra improves task success by an average of 9.1% relative to the strongest baseline; combined with OPOD, it improves small-orchestrator success by an average of 10.0% relative to existing training baselines. POrchestra also achieves a more favorable cost-performance trade-off. Our code is publicly available at https://github.com/XueyangFeng/POrchestra.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 25 of its 33 references that are in the map. First posted on arXiv 9 Oct 2026.

Builds on

25 of 33 references.

Closest ancestors · 10

Same direction, newest first

Other references · 15

2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,373
2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,737
2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,464
2023GAIA: a benchmark for General AI Assistantscited by 1,128
2026DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligencecited by 1,040
2023On-Policy Distillation of Language Models: Learning from Self-Generated Mistakescited by 939
2025DeepSeek-V3.2: Pushing the Frontier of Open Large Language Modelscited by 815
2025Why Do Multi-Agent LLM Systems Fail?cited by 604
2026Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Modelscited by 455

3 more

2025Context Length Alone Hurts LLM Performance Despite Perfect Retrievalcited by 127
2025ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimizationcited by 56
2026MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarkscited by 32

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way