arXiv subjects

Dutao Zhang

Publications and source records attributed to Dutao Zhang.

4 recordsLinked to original sources

arXiv2026

Queen-Bee Agents: A BeeSpec-Centered Architecture for Governed Enterprise MCP Orchestration

Enterprise agent systems increasingly need to connect large language models to private tools, internal knowledge, and Model Context Protocol (MCP) interfaces. In this setting, raw task capability is insufficient: organizations also require policy enforcement, tenant-scoped isolation, and execution that remains within explicit operational boundaries. We present Queen-Bee, a governed multi-agent architecture in which a Queen control plane retrieves capabilities, plans task-scoped execution, and compiles a structured BeeSpec that is executed by specialized Bee agents under constrained tool access. We implement a working prototype with tenant-scoped MCP connectors, audit-backed execution-time governance, retrieval-driven weak incubation, and multiple provisioning backends. We evaluate the system on 59 enterprise-style tasks spanning governance-sensitive requests, retrieval-driven provisioning, scoped local execution, and chemistry workflow integration. The retrieval-driven Queen-Bee variant achieves a task success rate of 0.964, zero governance failures, and substantially better scoped execution quality than both a static Queen-Bee baseline and a permissive single-agent baseline. We further show a multi-Bee chemistry workflow with explicit approval gating and a concrete top-3 shortlist grounded in real upstream evidence and screening artifacts. Additional comparisons with hybrid retrieval and LLM-guided provisioning show that richer provisioning backends are viable but do not outperform the lightweight structured retriever on the current small, highly structured capability registry. The results provide prototype-level systems evidence rather than a production deployment study, and suggest that enterprise agent platforms should be evaluated not only by capability, but also by governed provisioning, isolation behavior, scoped execution quality, and artifact-aware workflow coordination.

cs.SE↗

arXiv2026

An Agent-Oriented Pluggable Experience-RAG Skill for Experience-Driven Retrieval Strategy Orchestration

Retrieval-augmented generation systems often assume that one fixed retrieval pipeline is sufficient across heterogeneous tasks, yet factoid question answering, multi-hop reasoning, and scientific verification exhibit different retrieval preferences. We present Experience-RAG Skill, an agent-oriented pluggable retrieval orchestration layer positioned between the agent and the retriever pool. The proposed skill analyzes the current scene, consults an experience memory, selects an appropriate retrieval strategy, and returns structured evidence to the agent. Under a fixed candidate pool, Experience-RAG Skill achieves an overall nDCG@10 of 0.8924 on BeIR/nq, BeIR/hotpotqa, and BeIR/scifact, outperforming fixed single-retriever baselines and remaining competitive with Adaptive-RAG-style routing. The results suggest that retrieval strategy selection can be productively encapsulated as a reusable agent skill rather than being hard-coded in the upper workflow.

cs.AI↗

arXiv2026

Opinion dynamics and mutual influence with LLM agents through dialog simulation

A fundamental challenge in opinion dynamics research is the scarcity of real-world longitudinal opinion data, which complicates the validation of theoretical models. To address this, we propose a novel simulation framework using large language model (LLM) agents in structured multi-round dialogs. Each agent's dialog history is iteratively updated with its own previously stated opinions and those of others analogous to the classical DeGroot model. Furthermore, by retaining each agent's initial opinion throughout the dialog, we simulate anchoring effects consistent with the Friedkin-Johnsen model of opinion dynamics. Our framework thus bridges classical opinion dynamics models and modern multi-agent LLM systems, providing a scalable tool for simulating and analyzing opinion formation when real-world data is limited or inaccessible.

cs.GT↗

arXiv2026

Style2Code: A Style-Controllable Code Generation Framework with Dual-Modal Contrastive Representation Learning

Controllable code generation, the ability to synthesize code that follows a specified style while maintaining functionality, remains a challenging task. We propose a two-stage training framework combining contrastive learning and conditional decoding to enable flexible style control. The first stage aligns code style representations with semantic and structural features. In the second stage, we fine-tune a language model (e.g., Flan-T5) conditioned on the learned style vector to guide generation. Our method supports style interpolation and user personalization via lightweight mixing. Compared to prior work, our unified framework offers improved stylistic control without sacrificing code correctness. This is among the first approaches to combine contrastive alignment with conditional decoding for style-guided code generation.

cs.AI↗