EASy is proposed, a trainable agentic framework that jointly optimizes task performance and computational efficiency through reinforcement learning and consistently achieves stronger performance-efficiency trade-offs than strong agentic baselines.
Abstract
Agentic systems have emerged as a promising paradigm for solving complex tasks by coordinating specialized LLM-based agents. However, most existing systems primarily optimize task success while giving limited consideration to execution efficiency under practical constraints such as executor capability and computational cost. Existing router-based methods have limited ability to reason over rich, evolving task contexts, multi-step dependencies, and intermediate execution feedback, and often generalize poorly to unseen executors. We propose EASy, a trainable agentic framework that jointly optimizes task performance and computational efficiency through reinforcement learning. EASy equips an LLM-based orchestrator with explicit knowledge of the capability and cost profiles of heterogeneous executors, enabling context-sensitive coordination beyond performance-only routing. It further introduces a milestone-plan-act workflow that decomposes complex tasks into manageable milestones, constructs dependency-aware execution graphs, assigns suitable executors, and parallelizes independent steps while adapting subsequent decisions to intermediate outcomes. To train the orchestrator, we develop a tree-structured rollout procedure that explores alternative milestone decompositions and execution plans, together with multi-component rewards that capture task correctness, execution efficiency, and trajectory completeness. Extensive experiments on mathematical reasoning, embodied decision-making, and deep research benchmarks show that EASy consistently achieves stronger performance-efficiency trade-offs than strong agentic baselines.
This work introduces AgentSearch, a cost-aware Monte Carlo Tree Search (MCTS) framework that constructs agentic workflows through deliberative lookahead search and attains single-episode success while reducing computational costs by up to 47%, thereby eliminating the trial-and-error exploration required by previous adaptive methods.
D. Attota, Ying Xie· Proceedings of the 15th Inte...· 0 citations
Large Language Models (LLMs) have spurred the development of agentic artificial intelligence systems that can reason autonomously, plan, use tools, integrate memory, and carry out multi-step tasks. Unlike conventional prompt-response systems, LLM-based agents extend generative models to goal-oriented architectures that can decompose complex objectives, interact with external environments, and coordinate actions in iterative workflows. The survey systematically reviews LLM-based agent frameworks, multi-agent collaboration architectures, internal communication mechanisms, emerging cross-system interoperability protocols, and open research challenges. The review uses a PRISMA-based methodology, including literature from 2020 to March 2026, with particular focus on prominent frameworks such as LangChain, AutoGPT, AutoGen, MetaGPT, CAMEL, ChatDev, and CrewAI. The survey discusses the transition from modular chain-oriented to stateful graph-oriented and autonomous execution models and presents a systematic taxonomy of multi-agent collaboration architectures, including hierarchical, peer-to-peer, and role-based models. It also reviews the main internal communication mechanisms used to facilitate coordination and information sharing between LLM-based agents and distinguishes them from emerging interoperability protocols designed to support interaction across heterogeneous agents, tools, services, and frameworks. The analysis indicates that the promise of LLM-based agents for scalable automation, collaborative reasoning, and complex workflow execution comes with significant challenges in long-horizon reliability, evaluation standardization, communication security, cost-efficient orchestration, governance, and the interpretability of emergent multi-agent behavior. The survey covers architectural evolution, collaboration patterns, communication mechanisms, framework-level characteristics, and open research challenges. This provides a structured foundation for future research on reliable and trustworthy agentic artificial intelligence systems.
Unknown authors· Journal of Smart Algorithms...· 0 citations
Multi-agent large language model (LLM) workflows have emerged as a powerful paradigm for solving complex, open-ended tasks through collaborative reasoning among specialized LLM agents, but they incur substantial operating costs due to repeated LLM invocations and long-horizon context accumulation. Existing cascade routing methods make one-shot, query-level decisions and cannot adapt to the dynamic, state-dependent nature of multi-step workflows, in which the right LLM at each step depends on evolving task progress, remaining task difficulty, and cost-efficiency requirements. We present ProgRouter, an online progress-guided routing framework that adaptively selects LLM agents across workflow steps to preserve task-solving quality while adhering to time and cost budgets. ProgRouter introduces a multi-view task progress scorer that combines coarse workflow outcome regimes with fine-grained signals on subtask completion, progress trends, and workflow state quality. Then, a dual-path task progress predictor and an adaptive meta-gating mechanism estimate the progress gain for each candidate routed LLM. ProgRouter makes online step-wise routing decisions that balance progress gain, task time budgets, and long-term operating cost efficiency. Experiments on HumanEval Plus, MBPP, MATH-500, and ASQA, spanning agentic code generation, mathematical reasoning, and retrieval-augmented long-form question answering, demonstrate that ProgRouter reduces the operating cost relative to key baselines while maintaining strong task-solving performance.
Somgyuan Li, Ahmed M. Abdelmoniem, Shi-Qiang Wang· 0 citations
OpenJiuwen provides a shared execution substrate and Rail-based capability composition across single agents, delegated sub-agents, and Swarm Flow, enabling developers to construct sophisticated agent harnesses under common execution semantics.
openJiuwen Team Tao Yu, Xin-Yu Zhang, Qian-Qian Chen et al.· 0 citations
A semantic-uncertainty-guided orchestration approach, HASSUM is introduced as a general framework for uncertainty-aware coordination in multi-agent systems and suggests that semantic uncertainty is a practical and general-purpose signal for improving robustness and trustworthiness in agentic AI systems.
John Knowlton, Aritra Guha, Risto Miikkulainen· 0 citations
Large Language Model (LLM) applications increasingly rely on multi-agent and retrieval-augmented generation (RAG) architectures to solve complex, knowledge-intensive tasks. However, when deployed as generic platforms serving multiple customers and heterogeneous user groups, existing systems often rely on agent-level routing and prompt hardcoding, leading to poor modularity, limited reuse, and weak controllability. In particular, current approaches lack an explicit abstraction for modeling system capabilities and controlling which capabilities are accessible to different users. We propose an expert-guided multi-agent architecture that separates execution from capability modeling. Agents are responsible for LLM interaction and tool execution, while experts represent indivisible business or task capabilities and guide agent orchestration through dynamic prompt injection. This design enables a generic, multi-instance system in which different customer deployments and user groups share the same agent implementations while exposing different capability sets at the business level. The architecture enforces strong guarantees in terms of answerability, traceability, and controllability. A first working implementation has been developed, and an open-source release is currently in preparation.
Ying Zhang, M. Guillaume, Edouard Leleux et al.· 2026 6th International Confe...· 0 citations