Counterparty Modeling is Not Strategy: The Limits of LLM Negotiators

• URL: http://arxiv.org/abs/2605.16575v1
• Date: Fri, 15 May 2026 19:27:05 GMT
• Title: Counterparty Modeling is Not Strategy: The Limits of LLM Negotiators
• Abstract summary: We study whether large language model (LLM) agents do this in a controlled multi-attribute bargaining environment.<n>We find that current LLM agents can model a counterparty's preferences, but do not reliably turn that knowledge into strategic bargaining.<n>Because agents fail to leverage this underlying utility structure for strategic advantage, their final agreements are heavily dictated by surface-level opening anchors rather than actual utility weights.
• Score: 29.84830992033132
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Negotiation requires more than inferring what the other side wants: it requires using that information to make advantageous offers and counteroffers over multiple turns. We study whether large language model (LLM) agents do this in a controlled multi-attribute bargaining environment. We find that current LLM agents can model a counterparty's preferences, but do not reliably turn that knowledge into strategic bargaining. When given negotiating partner preference information, agents model it accurately and early in their reasoning traces, yet this does not reliably improve outcomes for the informed side. Turn-level analyses show why: agents often respond to what they believe the counterparty values, but do not consistently pair those moves with gains on their own high-value attributes. Sellers are more accommodating overall, and in asymmetric-information conditions, the informed side often makes the more weakly compensated concessions. Because agents fail to leverage this underlying utility structure for strategic advantage, their final agreements are heavily dictated by surface-level opening anchors rather than actual utility weights. Finally, requiring agents to explicitly state concession-for-reciprocity trades before making an offer makes individual turns look more strategic, but ultimately fails to improve the efficiency of the final agreements.

Related papers

• Used Car Salesbots? Honesty and Credulity of LLMs as Bargaining Agents under Partial Information [26.60109719186885]
  We study agents in simulated bargaining scenarios, where a buyer and a seller communicate through a text channel.<n>We evaluate their performance and investigate their honesty as well as their credulity.<n>We find that off-the-shelf LLMs all substantially deviate from game-theoretical equilibria.<n>Fine-tuning on financial utility makes the agents stronger at achieving better deals but also more dishonest.
  arXiv  Detail & Related papers  (2026-05-29T15:40:29Z)
• TERMS-Bench: Diagnosing LLM Negotiation Agents Beyond Deal Rate [34.67393151003599]
  Negotiation is a canonical testbed for agentic language models.<n>Unlike math or code, it has no intrinsic verifier.<n>We introduce Terms-Bench, a Bayesian-game framework that makes the environment itself the verifier.
  arXiv  Detail & Related papers  (2026-05-13T06:22:50Z)
• Instructing LLMs to Negotiate using Reinforcement Learning with Verifiable Rewards [45.56436052535799]
  We investigate if Reinforcement Learning from Verifiable Rewards can effectively teach Large Language Models to negotiate.<n>We introduce a framework that trains a mid-sized buyer agent against a regulated seller across a wide distribution of real-world products.<n>Our results demonstrate that this verifiable training allows a 30B agent to significantly outperform frontier models over ten times its size in extracting surplus.
  arXiv  Detail & Related papers  (2026-04-10T19:35:39Z)
• Training Language Models for Bilateral Trade with Private Information [47.25254982913256]
  Bilateral trade demands individual, strategic surplus rationality, and cooperation to realize gains from trade.<n>We develop a structured bargaining environment where large language models negotiate via tool calls within an event-driven simulator.<n>The environment serves two purposes: a benchmark for frontier models and as a training environment for open-weight models via reinforcement learning.
  arXiv  Detail & Related papers  (2026-04-10T03:04:20Z)
• MERIT Feedback Elicits Better Bargaining in LLM Negotiators [38.1466669265123]
  AgoraBench is a new benchmark spanning nine challenging settings.<n>This is operationalized via agent utility, negotiation power, and acquisition ratio that implicitly measure how well the negotiation aligns with human preference.<n>Our mechanism substantially improves negotiation performance, yielding deeper strategic behavior and stronger opponent awareness.
  arXiv  Detail & Related papers  (2026-02-11T03:09:45Z)
• EQ-Negotiator: Dynamic Emotional Personas Empower Small Language Models for Edge-Deployable Credit Negotiation [66.09161596959771]
  Small language models (SLMs) offer a practical alternative, but suffer from a significant performance gap compared to large language models (LLMs)<n>This paper introduces EQ-Negotiator, a novel framework that bridges this capability gap using emotional personas.<n>We show that a 7B parameter language model with EQ-Negotiator achieves better debt recovery and negotiation efficiency than baseline LLMs more than 10 times its size.
  arXiv  Detail & Related papers  (2025-11-05T11:25:07Z)
• Information Bargaining: Bilateral Commitment in Bayesian Persuasion [60.3761154043329]
  We introduce a unified framework and a well-structured solution concept for long-term persuasion.<n>This perspective makes explicit the common knowledge of the game structure and grants the receiver comparable commitment capabilities.<n>The framework is validated through a two-stage validation-and-inference paradigm.
  arXiv  Detail & Related papers  (2025-06-06T08:42:34Z)
• How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis [50.15061156253347]
  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. We develop NegotiationArena: a flexible framework for evaluating and probing the negotiation abilities of LLM agents.
  arXiv  Detail & Related papers  (2024-02-08T17:51:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.