Lune

ACL Findings2024

Boosting LLM Agents with Recursive Contemplation for Effective Deception Handling

Shenzhi Wang, Chang Liu, Zilong Zheng, Siyuan Qi, Shuo Chen, Qisen Yang, Andrew Zhao, Chaofei Wang, Shiji Song, Gao Huang

Abstract

Recent advances in large language models (LLMs) have led to significant success in using LLMs as agents. Nevertheless, a common assumption that LLMs always process honest information neglects the widespread deceptive or misleading content in human and AI-generated material. This oversight might expose LLMs to malicious manipulations. To enhance LLMs' ability to identify and counteract deceptive information, in this paper, inspired by humans' recursive thinking and perspective-taking, we introduce a novel cognitive framework, Recursive Contemplation (ReCon). ReCon combines formulation and refinement contemplation processes; formulation contemplation produces initial thoughts and speech, while refinement contemplation further polishes them. Additionally, we incorporate first-order and second-order perspective transitions into these processes respectively. Specifically, the first-order allows an LLM agent to infer others' mental states, and the second-order involves understanding how others perceive the agent's mental state. After integrating ReCon with various LLMs, extensive experiment results from the Avalon game and BigTom benchmark indicate ReCon's efficacy in aiding LLMs to discern and maneuver around deceptive information without extra fine-tuning and data. Finally, we demonstrate ReCon's scaling trend with model parameters, and explore the current limitations of LLMs in terms of safety and reasoning, potentially furnishing insights for subsequent research. Our project page can be found at https:// shenzhi-wang.github.io/avalon_recon.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

8 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • The Stackelberg Speaker: Optimizing Persuasive Communication in Social Deduction Games cites Training language models to follow instructions with human feedback
  • Tree of Thoughts: Deliberate Problem Solving with Large Language Models cites Language Models are Few-Shot Learners
  • Tree of Thoughts: Deliberate Problem Solving with Large Language Models cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Absolute Zero: Reinforced Self-play Reasoning with Zero Data cites Training language models to follow instructions with human feedback
  • CoMet: Metaphor-Driven Covert Communication for Multi-Agent Language Games cites Tree of Thoughts: Deliberate Problem Solving with Large Language Models
  • CoMet: Metaphor-Driven Covert Communication for Multi-Agent Language Games cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Reflexion: language agents with verbal reinforcement learning cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
  • Chain-of-Thought Prompting Elicits Reasoning in Large Language Models cites Training language models to follow instructions with human feedback
  • Training language models to follow instructions with human feedback cites Language Models are Few-Shot Learners
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers8

  1. Absolute Zero: Reinforced Self-play Reasoning with Zero DataAndrew Zhao, Yiran Wu, Tong Wu, Quentin Xu et al.NeurIPS 2025 · 361 citations
  2. T2R-BENCH: A Benchmark for Real World Table-to-Report TaskJie Zhang, Changzai Pan, Sishi Xiong, Kaiwen Wei et al.EMNLP 2025 · 2 citations
  3. CoMet: Metaphor-Driven Covert Communication for Multi-Agent Language GamesShuhang Xu, Fangwei ZhongACL 2025 · 2 citations
  4. The Stackelberg Speaker: Optimizing Persuasive Communication in Social Deduction GamesZheng Zhang, Deheng Ye, Peilin Zhao, Hao WangACL 2026
  5. OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser UseXueyu Hu, Tao Xiong, Biao Yi, Zishu Wei et al.ACL 2025

Builds on19

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida et al.NeurIPS 2022 · 24,707 citations
  3. Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
  4. Reflexion: language agents with verbal reinforcement learningNoah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan et al.NeurIPS 2023 · 5,828 citations
  5. Tree of Thoughts: Deliberate Problem Solving with Large Language ModelsShunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran et al.NeurIPS 2023 · 5,068 citations

Related papers

  1. Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign PromptsZhaomin Wu, Mingzhe Du, See-Kiong Ng, Bingsheng HeICLR 2026 · 11 citations
  2. Are Your Agents Upward Deceivers?Dadi Guo, Qingyu Liu, Dongrui Liu, Qihan Ren et al.ICML 2026 · 5 citations
  3. MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent SystemsXuanming Zhang, Yuxuan Chen, Samuel (Min-Hsuan) Yeh, Sharon LiNeurIPS 2025 · 14 citations
  4. Nuclear Deployed!: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM AgentsRongwu Xu, Xiaojian Li, Shuo Chen, Wei XuACL Findings 2025 · 5 citations
  5. RecToM: A Benchmark for Evaluating Machine Theory of Mind in LLM-based Conversational Recommender SystemsMengfan Li, Xuanhua Shi, Yang DengAAAI 2026
Dusk over the sea between two cliffs drawn in fine vertical lines