How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis

2024-02-08 · Federico Bianchi, Patrick John Chia, Mert Yuksekgonul, Jacopo Tagliabue, Dan Jurafsky, James Zou

Negotiation is the basis of social interactions; humans negotiate everything from the price of cars to how to share common resources. With rapidly growing interest in using large language models (LLMs) to act as agents on behalf of human users, such LLM agents would also need to be able to negotiate. In this paper, we study how well LLMs can negotiate with each other. We develop NegotiationArena: a flexible framework for evaluating and probing the negotiation abilities of LLM agents. We implemented three types of scenarios in NegotiationArena to assess LLM's behaviors in allocating shared resources (ultimatum games), aggregate resources (trading games) and buy/sell goods (price negotiations). Each scenario allows for multiple turns of flexible dialogues between LLM agents to allow for more complex negotiations. Interestingly, LLM agents can significantly boost their negotiation outcomes by employing certain behavioral tactics. For example, by pretending to be desolate and desperate, LLMs can improve their payoffs by 20\% when negotiating against the standard GPT-4. We also quantify irrational negotiation behaviors exhibited by the LLM agents, many of which also appear in humans. Together, \NegotiationArena offers a new environment to investigate LLM interactions, enabling new insights into LLM's theory of mind, irrationality, and reasoning abilities.

📄 PDF Abstract BibTeX arXiv:2402.05863

Code (1)

vinid/negotiationarena 공식 구현

Methods 이 논문이 사용한 방법론

Attention 설명 없음

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Position-Wise Feed-Forward Layer 설명 없음

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Language of Bargaining

2023-06-12 · Mourad Heddaya, Solomon Dworkin, Chenhao Tan, Rob Voigt 외

Leveraging an established exercise in negotiation education, we build a novel dataset for studying how the use of language shapes bilateral bargaining. Our dataset extends existing work in two ways: 1) we recruit partici…

User Negotiations of Authenticity, Ownership, and Governance on AI-Generated Video Platforms: Evidence from Sora

2025-12-05 · Bohui Shen, Shrikar Bhatta, Alex Ireebanije, Zexuan Liu 외 arxiv

As AI-generated video platforms rapidly advance, ethical challenges such as copyright infringement emerge. This study examines how users make sense of AI-generated videos on OpenAI's Sora by conducting a qualitative cont…

LLM Rationalis? Measuring Bargaining Capabilities of AI Negotiators

2025-12-15 · Cheril Shah, Akshit Agarwal, Kanak Garg, Mourad Heddaya arxiv

Bilateral negotiation is a complex, context-sensitive task in which human negotiators dynamically adjust anchors, pacing, and flexibility to exploit power asymmetries and informal cues. We introduce a unified mathematica…

Instructing LLMs to Negotiate using Reinforcement Learning with Verifiable Rewards

2026-04-10 · Shuze Daniel Liu, Claire Chen, Jiabao Sean Xiao, Lei Lei 외 arxiv

The recent advancement of Large Language Models (LLMs) has established their potential as autonomous interactive agents. However, they often struggle in strategic games of incomplete information, such as bilateral price …

Reinforcement Learning

Ambiguity Collapse by LLMs: A Taxonomy of Epistemic Risks

2026-03-06 · Shira Gur-Arieh, Angelina Wang, Sina Fazelpour arxiv

Large language models (LLMs) are increasingly used to make sense of ambiguous, open-textured, value-laden terms. Platforms routinely rely on LLMs for content moderation, asking them to label text based on disputed concep…