Communicative Agents for Software Development

By Chen Qian, Wei Liu, Xin Cong, Cheng Yang, Weize Chen, Yusheng Su, Juyuan Xu, Zhiyuan Liu, Maosong Sun. arXiv.org, 2023

393 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/4747e72c5bc706c50e76953188f0144df18992d0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Zhiyuan Liu
2. Maosong Sun
3. Jie Zhou
4. Yankai Lin
5. Heng Ji
6. Hao Peng
7. Mohit Bansal
8. Quoc V. Le

In Information Systems

1. Maosong Sun
2. Zhiyuan Liu
3. Xingyao Wang
4. Gao Huang
5. Heng Ji
6. Nitesh V. Chawla
7. Karthik Narasimhan
8. Hao Peng

Citations in the corpus

• Empowering Biomedical Discovery with AI Agents (2024, neutral): “This memory can be internal, encoded within the model’s weights via learning processes [8, 146], or external, maintained in auxiliary knowledge bases [147, 148].”
• AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors in Agents (2023, positive): “Parallel findings from recent research suggest that designating specific roles for autonomous agents, similar to recruiting experts to form a group, can augment their efficacy (Li et al., 2023; Salewski et al., 2023; Qian et al., 2023a).”
• ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate (2023, background): “This approach leads to enhanced factuality of generated responses (Du et al., 2023) and improvement in the completion of arduous tasks (Li et al., 2023a; Qian et al., 2023).”
• AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation (2023, neutral): “Empirical studies demonstrate the effectiveness of the framework in many example applications, with domains ranging from mathematics, coding, question answering, operations research, online decision-making, entertainment, etc.”
• A survey on large language model based autonomous agents (2023, neutral): “For a comprehensive overview, please refer to the right portion of Figure 5.”
• MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning (2023, neutral): “…to guide the model output to the corresponding domains based on the input question and options, respectively: where r qd , prompt qd and ( r od , prompt od ) stand for the system role and guideline prompt to gather domain experts for the question q and options op . of (Singhal et al., 2023a).”
• UltraFeedback: Boosting Language Models with High-quality Feedback (2023, positive): “With more powerful backbone models, we believe U LTRA F EEDBACK will greatly benefit autonomous agents (Park et al., 2023; Qin et al., 2023; Qian et al., 2023) and feedback learning (Yao et al., 2023; Shinn et al., 2023) research.”
• Large Language Model based Multi-Agents: A Survey of Progress and Challenges (2024, methodology): “…demonstrated promising re-sults in utilizing LLM-based multi-agents for solving various tasks, such as software development [ Hong et al. , 2023; Qian et al. , 2023 ] , multi-robot systems [ Mandi et al. , 2023; Zhang et al. , 2023c ] , society simulation [ Park et al. , 2023; Park et al. ,…”
• ULTRAFEEDBACK: Boosting Language Models with Scaled AI Feedback (2023, positive): “With more powerful backbone models, we believe U LTRA F EEDBACK will greatly benefit autonomous agents (Park et al., 2023; Qin et al., 2023; Qian et al., 2023) and feedback learning (Yao et al., 2023; Shinn et al., 2023) research.”
• Executable Code Actions Elicit Better LLM Agents (2024, background): “…in (Wang et al., 2023b), LLM-based autonomous agents are typically structured around four components: customized profiles (Park et al., 2023; Qian et al., 2023), long-term memory capabilities (Zhu et al., 2023; Fischer, 2023), reasoning and planning algorithms (Wei et al., 2022; Chen et…”
• ExpeL: LLM Agents Are Experiential Learners (2023, background): “Memory Mechanisms Agents with persistent long-term memory have demonstrated exciting results in multi-agent settings (Park et al. 2023; Maas et al. 2023; Qian et al. 2023).”
• Cognitive Architectures for Language Agents (2023, background): “…multiple language agents for social simulation (Park et al., 2023; Jinxin et al., 2023; Gao et al., 2023), debate (Chan et al., 2023; Liang et al., 2023b; Du et al., 2023), improved safety (Irving et al., 2018), or collabrative task solving (Qian et al., 2023; Wu et al., 2023; Hong et al., 2023).”