REVIEW 29 cited by
AgentScope: A Flexible yet Robust Multi-Agent Platform
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
With the rapid advancement of Large Language Models (LLMs), significant progress has been made in multi-agent applications. However, the complexities in coordinating agents' cooperation and LLMs' erratic performance pose notable challenges in developing robust and efficient multi-agent applications. To tackle these challenges, we propose AgentScope, a developer-centric multi-agent platform with message exchange as its core communication mechanism. The abundant syntactic tools, built-in agents and service functions, user-friendly interfaces for application demonstration and utility monitor, zero-code programming workstation, and automatic prompt tuning mechanism significantly lower the barriers to both development and deployment. Towards robust and flexible multi-agent application, AgentScope provides both built-in and customizable fault tolerance mechanisms. At the same time, it is also armed with system-level support for managing and utilizing multi-modal data, tools, and external knowledge. Additionally, we design an actor-based distribution framework, enabling easy conversion between local and distributed deployments and automatic parallel optimization without extra effort. With these features, AgentScope empowers developers to build applications that fully realize the potential of intelligent agents. We have released AgentScope at https://github.com/modelscope/agentscope, and hope AgentScope invites wider participation and innovation in this fast-moving field.
Forward citations
Cited by 29 Pith papers
-
Multi-Agent LLMs Fail to Explore Each Other
Modern multi-agent LLM systems fail to explore peers effectively; explicit LinUCB-style peer selection (MACE) cuts regret and lifts task performance, with gains scaling in agent diversity.
-
Beyond Tier Labels: Role- and Deployment-Dependent Model Substitution in Multi-Call LLM Workflows
Model substitution value in multi-call LLM workflows is deployment-conditioned: the same medium-to-strong swap helps, hurts, or reverses depending on role, scale, pool, and task.
-
Toward an Organizational Science of Multi-Agent LLM Systems: Decoupling Who, How, and Which Algorithm
A framework that decouples team composition, coordination, and fusion algorithm in multi-agent LLM systems, plus an adaptive router that learns per-task protocol choices.
-
SpecBox: Speculative Sandbox Scheduling for Efficient LLM Agent Serving
SpecBox overlaps LLM agent sandbox preparation with token generation and predicts future tool sandboxes, cutting P99 latency by 2.9× and peak memory by 45.9% in its prototype.
-
AgentSociety 2: An Integrated Research Environment for Executable Social Science
An integrated LLM-agent environment runs social-science experiments from hypothesis to manuscript, reproducing several known human patterns while failing on others (implicit self-bias, free-riding decay, norm collapse).
-
AgentJet: A Distributed Swarm Training Framework for Agentic Reinforcement Learning
AgentJet presents a decoupled multi-node swarm architecture for LLM agent RL that enables heterogeneous multi-model training, multi-task isolation, fault tolerance, live code iteration, context-optimized training, and...
-
Declarative by Design, Assistable Only by Convention: Benchmarking Multi-Agent Frameworks for AI-Assistability
A controlled benchmark of AI code generation across ten multi-agent frameworks finds that API convention alignment, not declarative design, predicts how well an AI assistant can write correct framework code.
-
When LLM Meets Time Series: Can LLMs Perform Multi-Step Time Series Reasoning and Inference
TSAIA, a new benchmark, tests eight LLMs on 1,054 multi-step time series tasks and finds they cannot reliably complete the required workflows.
-
KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows
KVFlow uses workflow-aware eviction priorities and overlapped KV prefetching to cut cache-miss latency in LLM multi-agent serving.
-
LLM-based Satisfiability Checking of String Requirements by Consistent Data and Checker Generation
An LLM-based system that generates SMT and Python checkers from natural-language string requirements and uses them with feedback to verify satisfiability improves accuracy over direct LLM generation.
-
Poison Once, Control Anywhere: Clean-Text Visual Backdoors in VLM-based Mobile Agents
Visual-only perturbations in fine-tuning screenshots can implant backdoors in VLM-based mobile agents, triggering attacker-chosen actions at inference.
-
YuLan-OneSim: Towards the Next Generation of Social Simulator with Large Language Models
YuLan-OneSim combines natural-language scenario generation, 50 prebuilt simulation scenarios, feedback-driven agent fine-tuning, 100,000-agent scale, and an automated AI social researcher into one social simulation platform.
-
MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework
A mean-field LLM framework that iterates between summarizing population state and generating individual decisions matches real social-media behavior distributions better than existing LLM simulation baselines.
-
MiniRAG: Towards Extremely Simple Retrieval-Augmented Generation
MiniRAG uses a heterogeneous entity-chunk graph and topology-enhanced retrieval to bring LLM-level RAG accuracy to small language models at 25% of the storage cost.
-
Scalable LLM Agent Tool Access in the Cloud
A cloud-scale MCP gateway with hybrid dense-sparse retrieval lets LLM agents work with 3,000+ tools at 98% Top-15 recall, cutting tool-selection time 8.9× and token use 23.8×.
-
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration
A multi-agent web-search framework that stores progress in shared evidence, coverage, and failure state reports the best F1 scores among compared baselines on WideSearch (80.3 item F1) and GISA (76.5 set F1).
-
RecoWorld: Building Simulated Environments for Agentic Recommender Systems
A design proposal, not a tested system: a dual-view simulation loop in which an LLM-simulated user issues reflective instructions when about to disengage, and an instruction-following recommender adapts to maximize si...
-
Maestro: Joint Graph & Config Optimization for Reliable AI Agents
Maestro jointly searches agent graph topology and node configurations, reporting higher test scores than prompt-only optimizers on HotpotQA, IFBench, and two internal agent tasks.
-
RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory
RCR-Router selects role-relevant memory slices under token budgets for multi-agent LLM systems, reporting token savings and quality gains on HotPotQA, MuSiQue, and 2WikiMultihop, but several experimental claims are un...
-
From Conversation to Orchestration: HCI Challenges and Opportunities in Interactive Multi-Agentic Systems
A position paper identifies six HCI design challenges for end-user interaction with hierarchical multi-agentic systems and proposes a research agenda.
-
AI-Researcher: Autonomous Scientific Innovation
AI-Researcher runs an end-to-end ML research pipeline with LLM agents, and Scientist-Bench measures how close the resulting papers come to human-authored publications.
-
MemEngine: A Unified and Modular Library for Developing Advanced Memory of LLM-based Agents
MemEngine is a modular library that standardizes and reimplements nine memory models from LLM-agent research under a unified function-operation-model hierarchy.
-
Towards Mitigation of Hallucination for LLM-empowered Agents: Progressive Generalization Bound Exploration and Watchdog Monitor
A black-box hallucination watchdog that stores previously hallucinated queries in a vector database and flags new queries by embedding similarity and semantic entropy.
-
Dynamic Knowledge Exchange and Dual-diversity Review: Concisely Unleashing the Potential of a Multi-Agent Research Team
IDVSCI, a multi-agent LLM framework with Dynamic Knowledge Exchange and Dual-Diversity Review, reports improved scientific abstract generation over AI-Scientist and VIRSCI on computer science and health sciences benchmarks.
-
A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Application
This survey organizes recent LLM-based multi-agent research into task-solving, simulation, and agent-evaluation applications, and identifies efficiency and evaluation gaps as key open problems.
-
ROMAS: A Role-Based Multi-Agent System for Database monitoring and Planning
A role-based multi-agent framework with a monitor that triggers re-planning is reported to outperform other LLM agent systems on two QA benchmarks, but no code, data, or error bars are provided.
-
From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents
A structured survey that categorizes LLM-based social simulation into individual, scenario, and society simulation, with associated methods, benchmarks, and observed trends.
-
KIMAs: A Configurable Knowledge Integrated Multi-Agent System
A configurable multi-agent RAG system that rewrites queries from conversation context, routes to knowledge sources by embedding centroids, and generates answers with separately produced citations, shown in three indus...
-
LLM-based Multi-Agent Systems: Techniques and Business Perspectives
LLM-based multi-agent systems, with standardized protocols and monetization incentives, are forecast to become the next AI business paradigm.
Discussion (0). Continue with ORCID to comment.