用大模型做6G网络切片时，会因思维僵化导致资源浪费，本文提出新方法打破这种惯性。
Mitigating Anchoring Bias in LLM-Based Agents for Energy-Efficient 6G Autonomous Networks
- 用截断三参数威布尔分布设计随机化策略，避免大模型固守初始方案
- 实测可将系统能耗降低25%，且推理延迟仅0.95秒
- 适合关注6G自治网络、大模型认知偏差的科研与工程人员
本文提出一种基于大语言模型（LLM）代理的自主资源协商框架，旨在实现6G架构中的零接触网络切片。尽管LLM具备强大推理能力，但研究发现其代理存在锚定偏差，会固执坚持初始启发式方案，引发严重资源过度配置。为此，我们提出一种基于截断三参数威布尔分布的新型随机锚定策略，该数学受限方法可无缝集成于采用条件风险价值（CVaR）的突发感知数字孪生系统中，严格保障服务等级协议（SLA）尾部延迟。通过引入并证明“双模态避约束效用定理”，我们揭示：在可行协商中遵循经典凸边界，而在高度受限场景下则经历由逆理性衰减包络主导的相变。基于本地部署的10亿参数模型otel-llm-1b-it的实证结果验证了这一双模式边界。认知去偏策略成功打破僵化谈判模式，促使代理主动探索，安全逼近SLA边界，使系统能效提升最高达25%。关键的是，轻量级10亿参数模型实现了均值0.95秒的亚秒级推理延迟，满足O-RAN非实时无线接入网智能控制器（non-RT RIC）的运行时序要求。
原文摘要 · Abstract (English)
This paper presents an autonomous agentic resource negotiation framework designed to enable zero-touch network slicing in 6G architectures using Large Language Model (LLM) agents. While LLMs offer powerful reasoning capabilities, we demonstrate that such agents inherently suffer from anchoring bias, rigidly adhering to initial heuristic proposals and causing severe network over-provisioning. To systematically mitigate this cognitive bias, we propose a novel randomized anchoring strategy modeled via a Truncated 3-Parameter Weibull distribution. This mathematically bounded approach seamlessly integrates with burst-aware Digital Twins (DTs) employing Conditional Value at Risk (CVaR) to rigorously guarantee strict Service Level Agreement (SLA) tail-latencies. To validate our methodology, we introduce and prove the \emph{Bimodal Constraint-Avoidance Utility Theorem}, demonstrating that while feasible negotiations follow classical convex bounds, highly constrained scenarios undergo a phase transition governed by an inverse rational decay envelope. Empirical results generated using a locally hosted 1B-parameter model otel-llm-1b-it confirm these dual-regime bounds. Our cognitive de-biasing successfully dismantles rigid negotiation patterns, forcing agents into active exploration to safely ride SLA boundaries and boost system energy savings up to 25\%. Crucially, the lightweight 1B LLM achieves sub-second inference latencies (0.95s mean), ensuring our multi-agent framework is compatible with the operational timescales of the O-RAN non-Real-Time RAN Intelligent Controller (non-RT RIC)\footnote{Our source code is available for non-commercial use at https://github.com/HatimChergui.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。