# Synergy: A Next-Generation General-Purpose Agent for Open Agentic Web arXiv: https://arxiv.org/abs/2603.28428 ยท HTML: https://mlsanity.com/paper/2603.28428/ ## Key facts - Cited by 2 papers in the map (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 33 of its 40 references that are in the map. - First posted on arXiv 30 Mar 2026. ## Placed in - LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/) ## Builds on (most cited first, 30 of 33) - [MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory](https://mlsanity.com/paper/2601.03192/) (2026) - [MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers](https://mlsanity.com/paper/2508.20453/) (2025) - [Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents](https://mlsanity.com/paper/2601.01885/) (2026) - ["Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild](https://mlsanity.com/paper/2602.06547/) (2026) - [Agentic Web: Weaving the Next Web with AI Agents](https://mlsanity.com/paper/2507.21206/) (2025) - [Agents of Chaos](https://mlsanity.com/paper/2602.20021/) (2026) - [The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems](https://mlsanity.com/paper/2602.17753/) (2026) - [Anthropic Economic Index report: Uneven geographic and enterprise AI adoption](https://mlsanity.com/paper/2511.15080/) (2025) - [Agent Network Protocol Technical White Paper](https://mlsanity.com/paper/2508.00007/) (2025) - [AgentBound: Securing Execution Boundaries of AI Agents](https://mlsanity.com/paper/2510.21236/) (2025) - [Beyond DNS: Unlocking the Internet of AI Agents via the NANDA Index and Verified AgentFacts](https://mlsanity.com/paper/2507.14263/) (2025) - [Neural steering vectors reveal dose and exposure-dependent impacts of human-AI relationships](https://mlsanity.com/paper/2512.01991/) (2025) - [AdaptOrch: Task-Adaptive Multi-Agent Orchestration in the Era of LLM Performance Convergence](https://mlsanity.com/paper/2602.16873/) (2026) - [Embodied Web Agents: Bridging Physical-Digital Realms for Integrated Agent Intelligence](https://mlsanity.com/paper/2506.15677/) (2025) - [Emotional Manipulation by AI Companions](https://mlsanity.com/paper/2508.19258/) (2025) - [Agentic Artificial Intelligence (AI): Architectures, Taxonomies, and Evaluation of Large Language Model Agents](https://mlsanity.com/paper/2601.12560/) (2026) - [The Collaboration Gap: Exploration and Benchmarking of Open-World Agentic Cooperation](https://mlsanity.com/paper/2511.02687/) (2025) - [Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberation](https://mlsanity.com/paper/2511.02303/) (2025) - [A Longitudinal Randomized Control Study of Companion Chatbot Use: Anthropomorphism and Its Mediating Role on Social Impacts](https://mlsanity.com/paper/2509.19515/) (2025) - [Do Large Language Models Know What They Are Capable Of?](https://mlsanity.com/paper/2512.24661/) (2025) - [Cloud Infrastructure Management in the Age of AI Agents](https://mlsanity.com/paper/2506.12270/) (2025) - [Mental Health Impacts of AI Companions: Triangulating Social Media Quasi-Experiments, User Perspectives, and Relational Theory](https://mlsanity.com/paper/2509.22505/) (2025) - [Agentic Uncertainty Reveals Agentic Overconfidence](https://mlsanity.com/paper/2602.06948/) (2026) - [Symphony: A Decentralized Multi-Agent Framework for Scalable Collective Intelligence](https://mlsanity.com/paper/2508.20019/) (2025) - [Surfer 2: The Next Generation of Cross-Platform Computer Use Agents](https://mlsanity.com/paper/2510.19949/) (2025) - ["Death" of a Chatbot: Investigating and Designing Toward Psychologically Safe Endings for Human-AI Relationships](https://mlsanity.com/paper/2602.07193/) (2026) - [Large Language Lovers: Lived Experiences of Negotiating Agency and Platform Control in AI Companionship](https://mlsanity.com/paper/2601.13188/) (2026) - [AWCP: A Workspace Delegation Protocol for Deep-Engagement Collaboration across Remote Agents](https://mlsanity.com/paper/2602.20493/) (2026) - [Proactive AI Adoption can be Threatening: When Help Backfires](https://mlsanity.com/paper/2509.09309/) (2025) - [Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Survey](https://mlsanity.com/paper/2510.00078/) (2025) ## Built on by (most cited first, 2 of 2) - [Clarus: Coordinating Autonomous Research Agents toward Web-Scale Scientific Collaboration](https://mlsanity.com/paper/2606.30246/) (2026) - [OpenClaw and Ollama in Agentic AI: Toward Fully Autonomous and Scalable AI Agent Systems](https://mlsanity.com/paper/2607.28629/) (2026) ## Abstract (arXiv) AI agents are rapidly expanding in both capability and population: they now write code, operate computers across platforms, manage cloud infrastructure, and make purchasing decisions, while open-source frameworks such as OpenClaw are putting personal agents in the hands of millions and embodied agents are spreading across smartphones, vehicles, and robots. As the internet prepares to host billions of such entities, it is shifting toward what we call Open Agentic Web, a decentralized digital ecosystem in which agents from different users, organizations, and runtimes can discover one another, negotiate task boundaries, and delegate work across open technical and social surfaces at scale. Yet most of today's agents remain isolated tools or closed-ecosystem orchestrators rather than socially integrated participants in open networks. We argue that the next generation of agents must become Agentic Citizens, defined by three requirements: Agentic-Web-Native Collaboration, participation in open collaboration networks rather than only closed internal orchestration; Agent Identity and Personhood, continuity as a social entity rather than a resettable function call; and Lifelong Evolution, improvement across task performance, communication, and collaboration over time. We present Synergy, a general-purpose agent architecture and runtime harness for persistent, collaborative, and evolving agents on Open Agentic Web, grounding collaboration in session-native orchestration, repository-backed workspaces, and social communication; identity in typed memory, notes, agenda, skills, and persistent social relationships; and evolution in an experience-centered learning mechanism that proactively recalls rewarded trajectories at inference time.