2025大模型论文 | 智能体最新进展

最新推荐文章于 2025-04-15 01:48:46 发布

AI Agent开发

最新推荐文章于 2025-04-15 01:48:46 发布

阅读量826

点赞数 15

文章标签：人工智能大模型自然语言处理 LLM AI Agent 智能体

本文链接：https://blog.csdn.net/m0_56255097/article/details/145544899

版权

1.Eliciting Language Model Behaviors with Investigator Agents

Authors: Xiang Lisa Li, Neil Chowdhury, Daniel D. Johnson, Tatsunori Hashimoto, Percy Liang, Sarah Schwettmann, Jacob Steinhardt

Affiliations: Stanford University; MIT; Transluce; UC Berkeley

https://arxiv.org/abs/2502.01236

论文摘要

Language models exhibit complex, diverse behaviors when prompted with free-form text, making it difficult to characterize the space of possible outputs. We study the problem of behavior elicitation, where the goal is to search for prompts that induce specific target behaviors (e.g., hallucinations or harmful responses) from a target language model. To navigate the exponentially large space of possible prompts, we train investigator models to map randomly-chosen target behaviors to a diverse distribution of outputs that elicit them, similar to amortized Bayesian inference. We do this through supervised fine-tuning, reinforcement learning via DPO, and a novel Frank-Wolfe training objective to iteratively discover diverse prompting strategies. Our investigator models surface a variety of effective and human-interpretable prompts leading to jailbreaks, hallucinations, and open-ended aberrant behaviors, obtaining a 100% attack success rate on a subset of AdvBench (Harmful Behaviors) and an 85% hallucination rate.

在这里插入图片描述

论文简评：总的来说，这篇论文提出了一个利用智能代理（investigator agents）自动从语言模型中获取特定行为的方法框架。该方法将行为发现问题视为强化学习问题，并通过多阶段训练管道（supervised fine-tuning、direct preference optimization以及Frank-Wolfe优化）来生成多样化的提示以引发预先定义的行为。然而，尽管论文解决了AI安全中的一个重要问题，但由于其原创性、结果质量和清晰度方面的不足，使其整体上显得平庸。

2.CAMI: A Counselor Agent Supporting Motivational Interviewing through State Inference and Topic Exploration

Authors: Yizhe Yang, Palakorn Achananuparp, Heyan Huang, Jing Jiang, Kit Phey Leng, Nicholas Gabriel Lim, Cameron Tan Shi Ern, Ee-peng Lim

Affiliations: Beijing Institute of Technology; Singapore Management University; Australian National University; National Institute of Education; Singapore University of Social Sciences; National University of Singapore

https://arxiv.org/abs/2502.02807

论文摘要

Conversational counselor agents have become essential tools for addressing the rising demand for scalable and accessible mental health support. This paper introduces CAMI, a novel automated counselor agent grounded in Motivational Interviewing (MI) – a client-centered counseling approach designed to address ambivalence and facilitate behavior change.
CAMI employs a novel STAR framework, consisting of client’s state inference, motivation topic exploration, and response generation modules, leveraging large language models (LLMs). These components work together to evoke change talk, aligning with MI principles and improving counseling outcomes for clients from diverse backgrounds. We evaluate CAMI’s performance through both automated and manual evaluations, utilizing simulated clients to assess MI skill competency, client’s state inference accuracy, topic exploration proficiency, and overall counseling success. Results show that CAMI not only outperforms several state-of-the-art methods but also demonstrates more realistic counselor-like behavior. Additionally, our ablation study underscores the critical roles of state inference and topic exploration in achieving this performance.

在这里插入图片描述

论文简评：本文通过介绍CAMI（Counseling Agent for Mental Health Improvement）这一人工智能辅助心理咨询系统，强调了它基于动机干预理论的独特价值。CAMI系统采用STAR框架，旨在提升咨询师的角色感，并通过模拟现实情景评估其有效性。该研究探讨了CAMI与其他现有技术的优势以及它如何有效地处理心理状态问题。总之，CAMI展示了AI在心理健康支持领域的重要作用，并提出了创新的方法论框架。尽管人工评估不可或缺，自动化工具仍可提供有价值的信息，进一步促进系统优化发展。总体而言，这篇论文对心理学界来说是一个值得参考的研究成果，为未来发展提供了宝贵的启示。

3.Agentic Bug Reproduction for Effective Automated Program Repair at Google

Authors: Runxiang Cheng, Michele Tufano, Jürgen Cito, José Cambronero, Pat Rondon, Renyao Wei, Aaron Sun, Satish Chandra

Affiliations: University of Illinois Urbana-Champaign; Google; TU Wien, Austria

https://arxiv.org/abs/2502.01821

论文摘要

Bug reports often lack sufficient detail for developers to reproduce and fix the underlying defects. Bug Reproduction Tests (BRTs), tests that fail when the bug is present and pass when it has been resolved, are crucial for debugging, but they are rarely included in bug reports, both in open-source and in industrial settings. Thus, automatically generating BRTs from bug reports has the potential to accelerate the debugging process and lower time to repair. This paper investigates automated BRT generation within an industry setting, specifically at Google, focusing on the challenges of a large-scale proprietary codebase and considering real-world industry bugs extracted from Google’s internal issue tracker. We adapt and evaluate a state-of-the-art BRT generation technique, LIBRO, and present our agent-based approach, BRT Agent, which utilizes a fine-tuned Large Language Model (LLM) for code editing. Our BRT Agent significantly outperforms LIBRO, achieving a 28% plausible BRT generation rate, compared to 10% by LIBRO, on 80 human-reported bugs from Google’s internal issue tracker. We further investigate the practical value of generated BRTs by integrating them with an Automated Program Repair (APR) system at Google. Our results show that providing BRTs to the APR system results in 30% more bugs with plausible fixes.
Additionally, we introduce Ensemble Pass Rate (EPR), a metric that leverages the generated BRTs to select the most promising fixes from all fixes generated by the APR system. Our evaluation on EPR for Top-K and threshold-based fix selections demonstrates promising results and trade-offs. For example, EPR correctly selects a plausible fix from a pool of 20 candidates in 70% of cases, based on its top-1 ranking.

在这里插入图片描述

论文简评：本文探讨了Google公司在工业环境中自动生成Bug Reproduction Test（BRT）的方法，提出了基于大型语言模型（LLM）的Agent-Based Approach（BRT Agent）。该方法利用精细调校的LLMs显著提高了BRT生成的有效性。实验结果表明，在生成可接受的BRT方面取得了显著改进，增强了自动化程序修复（APR）系统的bug解决能力，并引入了一个新的评估指标（Ensemble Pass Rate）用于评估合理的修复选择。此外，研究展示了全面且结构清晰的实证评估，为分析代理行为和性能提供了有价值的见解。总体而言，本文的研究对软件调试领域具有重要贡献，尤其是对于提高BRT的生成质量和实用性提供了有益启示。

4.Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies

Authors: Han Zhou, Xingchen Wan, Ruoxi Sun, Hamid Palangi, Shariq Iqbal, Ivan Vulić, Anna Korhonen, Sercan Ö. Arık

Affiliations: Google, 2University of Cambridge

https://arxiv.org/abs/2502.02533

论文摘要

Large language models, employed as multiple agents that interact and collaborate with each other, have excelled at solving complex tasks. The agents are programmed with prompts that declare their functionality, along with the topologies that orchestrate interactions across agents. Designing prompts and topologies for multi-agent systems (MAS) is inherently complex. To automate the entire design process, we first conduct an in-depth analysis of the design space aiming to understand the factors behind building effective MAS. We reveal that prompts together with topologies play critical roles in enabling more effective MAS design. Based on the insights, we propose Multi-Agent System Search (Mass), a MAS optimization framework that efficiently exploits the complex MAS design space by interleaving its optimization stages, from local to global, from prompts to topologies, over three stages: 1) block-level (local) prompt optimization; 2) workflow topology optimization; 3) workflow-level (global) prompt optimization, where each stage is conditioned on the iteratively optimized prompts/topologies from former stages. We show that Mass-optimized multi-agent systems outperform a spectrum of existing alternatives by a substantial margin. Based on the Mass-found systems, we finally propose design principles behind building effective multi-agent systems.

在这里插入图片描述

论文简评：《Multi-Agent System Search (Mass): A Framework for Optimizing Multi-Agent Systems》这篇论文是关于多代理系统搜索（Mass）框架的设计与应用的研究。该框架旨在通过优化提示和拓扑设计来提升多代理系统的性能。研究分析了设计空间的重要性，并对MAS的有效性提出了明确的解释。

Mass框架的目标在于解决多代理系统中提示和拓扑设计之间的交互问题，以实现更高效、更准确的设计多代理系统。论文的全面分析明确了有效提示和拓扑对提高多代理系统性能的重要性。

研究结果表明，Mass在多个任务上均表现出显著的优势，证明了其在多代理系统优化中的有效性。这些成果为未来研究提供了宝贵的参考，也为实际应用提供了一种新的方法论。总体来说，Mass是一个值得进一步深入研究的重要工具，它不仅能改善现有多代理系统的性能，还为未来发展开辟了新思路。

5.QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search

Authors: Zongyu Lin, Yao Tang, Xingcheng Yao, Da Yin, Ziniu Hu, Yizhou Sun, Kai-Wei Chang

Affiliations: University of Califor nia, Los Angeles; Shanghai Jiaotong University

https://arxiv.org/abs/2502.02584

论文摘要

Language agents have become a promising solution to complex interactive tasks. One of the key ingredients to the success of language agents is the reward model on the trajectory of the agentic workflow, which provides valuable guidance during training or inference. However, due to the lack of annotations of intermediate interactions, most existing works use an outcome reward model to optimize policies across entire trajectories. This may lead to sub-optimal policies and hinder overall performance. To address this, we propose Q-guided Language Agent Stepwise Search (QLASS), to automatically generate annotations by estimating Q-values in a stepwise manner for open language agents. By introducing an exploration tree and performing process reward modeling, QLASS provides effective intermediate guidance for each step. With the stepwise guidance, we propose a Q-guided generation strategy to enable language agents to better adapt to long-term value, resulting in significant performance improvement during model inference on complex interactive agent tasks. Notably, even with almost half the annotated data, QLASS retains strong performance, demonstrating its efficiency in handling limited supervision. We also empirically show that QLASS can lead to more effective decision-making through qualitative analysis. \footnote{We will release our code and data in https://github.com/Rafa-zy/QLASS

在这里插入图片描述