让大模型在多轮任务中更可靠，通过行为引导机制提升可信度。
Towards Trustworthy Multi-Turn LLM Agents via Behavioral Guidance
- 用轻量级任务分析器选择推理与生成策略
- 多轮交互中自适应学习可验证的观测量-动作映射
- 生成模块强制输出符合约束，适合高可靠性场景
大型语言模型具备强大的推理与生成能力，但在多轮任务中行为常缺乏可靠性与可验证性。本文提出一种任务完成框架，使基于大模型的智能体能在强化学习形式化环境中，依据明确的行为引导进行操作，该环境包含定义好的观测、动作和奖励信号。框架整合三个组件：轻量级任务分析器用于选择推理与生成策略；推理模块学习可验证的观测量-动作映射；生成模块通过验证或确定性合成确保输出符合约束。实验表明，随着智能体与环境的交互，各组件协同进化，最终实现可信行为。
原文摘要 · Abstract (English)
Large Language Models demonstrate strong reasoning and generation abilities, yet their behavior in multi-turn tasks often lacks reliability and verifiability. We present a task completion framework that enables LLM-based agents to act under explicit behavioral guidance in environments described by reinforcement learning formalisms with defined observation, action, and reward signals. The framework integrates three components: a lightweight task profiler that selects reasoning and generation strategies, a reasoning module that learns verifiable observation - action mappings, and a generation module that enforces constraint-compliant outputs through validation or deterministic synthesis. We show that as the agent interacts with the environment, these components co-evolve, yielding trustworthy behavior.
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。