Multi-Agent Negotiation

Ask about this topic

Overview

Multi-agent negotiation studies how autonomous agents reach agreements when their goals, information, or resources differ, from price bargaining and coalition formation to traffic coordination and shared computing. Approaches include game-theoretic mechanisms, reinforcement learning with economic rewards, opponent modeling and theory of mind, and structured communication or contract protocols. Benchmarks increasingly test private information, repeated interaction, multiple parties, and long-horizon decisions, measuring not just deal rates but also surplus, efficiency, fairness, and contract reliability. A central challenge is that agents may agree often or infer others’ preferences accurately without using that knowledge effectively, while stronger economic performance can conflict with honesty, fairness, and dependable execution.

Latest papers

CardsList

53 papers7 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

May 13, 2026

TERMS-Bench: Diagnosing LLM Negotiation Agents Beyond Deal Rate

Negotiation is a central mechanism of economic exchange, shaping markets, procurement, labor agreements, and resource allocation. It is also a canonical testbed for agentic language models, requiring multi-turn interaction under hidden preferences, strategic communication, and binding constraints. These properties make negotiation hard to evaluate: unlike math or code, it has no intrinsic verifier. Existing LLM negotiation evaluations rely on LLM-vs.-LLM interaction or aggregate outcomes such as deal rate, leaving failures opaque. We introduce Terms-Bench, short for Testbed for Economic Reasoning in Multi-turn Strategy, a Bayesian-game framework that makes the environment itself the verifier by specifying the counterpart's latent type, policy, and payoff structure. We instantiate it in bilateral price negotiation, where the counterpart's private state and simulator policy are hidden from the agent but observable to the evaluator. This turns the counterpart from a black-box opponent into a diagnostic instrument, enabling agent-attributable failure analysis and oracle-reference optimality gaps. Evaluating 13 LLM agents spanning frontier systems from major providers, Terms-Bench turns negotiation evaluation from aggregate ranking into actionable diagnosis: where agents fail, why they fail, and what to strengthen. Empirically, frontier models saturate deal rate yet diverge in surplus extraction, cue use, belief calibration, and compliance, revealing agent-specific bargaining bottlenecks masked by prior benchmarks.

Erica Zhang, Fangzhao Zhang, Aneesh Pappu +5

♠Stanford School of Engineering · ♣Stanford Department of Economics · ♥Stanford Graduate School of Business +1

Multi-Agent NegotiationAutomated NegotiationImperfect-Information GamesGame TheoryLLM Agent Evaluation
AskPDF
May 12, 2026

LLM-X: A Scalable Negotiation-Oriented Exchange for Communication Among Personal LLM Agents

We propose a personal-LLM exchange (LLM-X), a scalable negotiation-oriented environment that enables direct, structured communication across populations of personal agents (LLMs), each representing an individual user. Unlike existing tool-centric protocols that focus on agent-API interaction, LLM-X introduces a message bus and routing substrate for LLM-to-LLM coordination with guarantees around schema validity and policy enforcement. We contribute: (1) an architecture for LLM-X comprising federated gateways, topic-based routing, and policy enforcement; (2) a typed message protocol supporting capability negotiation and contract-net-style coordination; and (3) the first empirical evaluation of LLM-based multi-agent negotiation at scale. Experiments span 5, 9, and 12 agents, under distinct negotiation policies (Low, Medium, High), and across both short-run (minutes) and long-run (2h, 12h) load conditions. Results highlight clear policy-performance trade-offs: stricter policies improve robustness and fairness but increase latencies and message volume. Extended runs confirm that LLM-X remains stable under sustained load, with bounded latency drift.

Giuliano Lorenzoni, Paulo Alencar, Donald Cowan

University of Waterloo · University of Waterloo Waterloo, ON, Canada

Multi-Agent LLM SystemsMulti-Agent CoordinationMulti-Agent NegotiationAutomated NegotiationMulti-Agent Communication
AskPDF
May 6, 2026

Distilling Bayesian Belief States into Language Models for Auditable Negotiation

Negotiation agents must infer what their counterpart values, update those beliefs over dialogue turns, and choose actions under uncertainty. End-to-end large language models (LLMs) can imitate negotiation dialogue, but their opponent beliefs are usually implicit and difficult to inspect. We propose BOND (Bayesian Opponent-belief Negotiation Distillation), a framework for auditable negotiation. BOND consists of an LLM-based Bayesian teacher that scores dialogue contexts against the six possible opponent priority orderings, updates a posterior over those orderings, and uses the posterior for menu-based decision making, as well as a smaller 8B student language model that emits both negotiation actions and normalized posterior beliefs as tagged text. In the CaSiNo negotiation dataset, BOND outperforms the state-of-the-art and achieves mean Brier score 0.085 over opponent-priority posteriors. The distilled student preserves much of this belief signal, achieving Brier 0.114, below the uniform six-ordering reference of 5/36, approximately 0.139. Compared with a 70B structured-CoT baseline, the significantly smaller 8B student model yields substantially better elicited posterior calibration. We further showcase auditability through posterior trajectories, belief-versus-policy error decomposition, and posterior-prefix interventions. These diagnostics reveal that distillation preserves a scoreable belief report more strongly than causal belief-conditioned control, making weak belief-action coupling visible, not hidden.

Zongqi Cui, Baihan Lin

Emory University · Icahn School of Medicine at Mount Sinai

Multi-Agent NegotiationOpponent ModelingAutomated NegotiationLLM AuditingLanguage Model CalibrationLanguage Model Distillation+1
AskPDF
May 3, 2026

Talk is Cheap, Communication is Hard: Dynamic Grounding Failures and Repair in Multi-Agent Negotiation

Grounding is the collaborative process of establishing mutual belief sufficient for a communicative goal. While static grounding maps language to a shared context, dynamic grounding requires agents to negotiate meaning across turns. Current multi-agent Large Language Model (LLM) benchmarks largely emphasize static, one-shot tasks, overlooking whether agents can repair grounding breakdowns through interaction. We introduce an iterated multi-turn negotiation game where two agents allocate shared resources to private projects with verifiable jointly optimal outcomes. Although individual agents can identify Pareto-optimal allocations in isolation, agent dyads consistently fail to reach them across models. We identify four failure modes: (1) loss of shared interaction history, (2) stubborn anchoring to early proposals, (3) defaulting to equal splits over reward-maximizing coordination, and (4) referential binding errors across turns. Our baselines show that the coordination gap is not explained by individual reasoning limits or insufficient information exchange alone. Instead, the bottleneck lies in dynamic grounding: joint plan formation, commitment, and execution.

Yiheng Yao, Chelsea Zou, Robert D. Hawkins

Stanford University

Multi-Agent CoordinationMulti-Agent NegotiationAutomated NegotiationMulti-Agent CommunicationMulti-Agent LLMs
AskPDF
Apr 28, 2026

Cooperate to Compete: Strategic Coordination in Multi-Agent Conquest

Language Model (LM)-based agents remain largely untested in mixed-motive settings where agents must leverage short-term cooperation for long-term competitive goals (e.g., multi-party politics). We introduce Cooperate to Compete (C2C), a multi-agent environment where players can engage in private negotiations while competing to be the first to achieve their secret objective. Players have asymmetric objectives and negotiations are non-binding, allowing alliances to form and break as players' short-term interests align and diverge. We run AI only games and conduct a user study pitting human players against AI opponents. We identify significant differences between human and AI negotiation behaviors, finding that humans favor lower-complexity deals and are significantly less reliable partners compared to LM-based agents. We also find that humans are more aggressive negotiators, accepting deals without a counteroffer only 56.3% of the time compared to 67.6% for LM-based agents. Through targeted prompting inspired by these findings, we modify agents' negotiation behavior and improve win rates from 22.2% to 32.7%. We run over 1,100 games with over 16,000 private conversations totaling 15.2 million tokens and over 150,000 player actions. Our results establish C2C as a testbed for studying and building LM-based agents that can navigate the sophisticated coordination required for real-world deployments. The game, code, and dataset may be found at https://negotiationgame.io/c2c.

Abigail O'Neill, Alan Zhu, Mihran Miroyan +2

University of California, Berkeley

Multi-Agent CoordinationMulti-Agent NegotiationAutomated NegotiationHuman-AI InteractionAI Agent BenchmarksMulti-Agent LLMs
AskPDF
Apr 25, 2026

ArgRE: Formal Argumentation for Conflict Resolution in Multi-Agent Requirements Negotiation

As software systems grow in complexity, they must satisfy an increasing number of competing quality attributes, making it essential to balance them in a principled manner -- for example, a safety requirement for sensor-fusion verification may conflict with a tight planning-cycle budget. Multi-agent large language model frameworks support this balancing process by assigning specialized agents to different objectives. However, their conflict resolution is typically heuristic. Requirements are aggregated implicitly without explicit acceptance or rejection, limiting auditability in regulated domains. We present ArgRE, a multi-agent requirements negotiation system that embeds Dung-style abstract argumentation into the negotiation stage. Each proposal, critique, and refinement is modeled as an argument, conflicts are represented as directed attack relations, and the accepted set of arguments is computed under grounded and preferred semantics. The pipeline further integrates KAOS goal modeling, multi-layer verification, and standards-oriented artifact generation. Evaluation across five case studies spanning safety-critical, financial, and information-system domains shows that ArgRE provides argument-level traceability absent from existing frameworks. Independent evaluators rated its decision justifications significantly higher than those of heuristic synthesis (4.32 vs. 3.07, p < 0.001), indicating improved auditability, while semantic intent preservation remains comparable (94.9% BERTScore F1) and compliance coverage reaches 84.7% versus 47.6%--47.8% for baselines. Structural analysis further confirms that the default pairwise protocol yields acyclic graphs in which grounded and preferred semantics coincide, whereas cross-pair arbitration introduces controlled cyclicity, leading to predictable divergence between the two semantics.

Haowei Cheng, Milhan Kim, Chong Liu +6

Department of Computer Science and Communications Engineering, Waseda University, Tokyo, Japan · College of Architecture and Urban Planning, Tongji University, Shanghai, China · Advanced Institute of So-Go-Chi (Convergence Knowledge) Informatics, Tohoku University, Miyagi, Japan +1

Requirements EngineeringMulti-Agent NegotiationAutomated NegotiationComputational ArgumentationMulti-Agent LLMs
AskPDF
Apr 17, 2026

Preference Estimation via Opponent Modeling in Multi-Agent Negotiation

Automated negotiation in complex, multi-party and multi-issue settings critically depends on accurate opponent modeling. However, conventional numerical-only approaches fail to capture the qualitative information embedded in natural language interactions, resulting in unstable and incomplete preference estimation. Although Large Language Models (LLMs) enable rich semantic understanding of utterances, it remains challenging to quantitatively incorporate such information into a consistent opponent modeling. To tackle this issue, we propose a novel preference estimation method integrating natural language information into a structured Bayesian opponent modeling framework. Our approach leverages LLMs to extract qualitative cues from utterances and converts them into probabilistic formats for dynamic belief tracking. Experimental results on a multi-party benchmark demonstrate that our framework improves the full agreement rate and preference estimation accuracy by integrating probabilistic reasoning with natural language understanding.

Yuta Konishi, Kento Yamamoto, Eisuke Sonomoto +8

1Graduate School of Informatics, Kyoto University, Kyoto, Japan · 2Accenture Japan Ltd, Tokyo, Japan

Multi-Agent NegotiationOpponent ModelingAutomated Negotiation
AskPDF
Apr 15, 2026

[COMP25] The Automated Negotiating Agents Competition (ANAC) 2025 Challenges and Results

This paper presents the primary research challenges and key findings from the 15th International Automated Negotiating Agents Competition (ANAC 2025), one of the official competitions of IJCAI 2025. We focus on two critical domains: multi-deal negotiations and the development of agents capable of concurrent negotiation within complex supply chain management environments. Furthermore, this work analyzes the results of the competition and outlines strategic directions for future iterations.

Reyhan Aydoğan, Tim Baarslag, Tamara C. P. Florijn +3

Özye˘gin Üniversity · Delft University of Technology · Centrum Wiskunde & Informatica (CWI) +5

Automated NegotiationMulti-Agent NegotiationAI Agent BenchmarksSupply Chain Management
AskPDF
Apr 12, 2026

Diversity Without Fidelity: A Solver-Sampler Mismatch in Multi-Agent LLM Negotiation Simulation

Language models are increasingly used to simulate people: survey respondents, negotiators, stakeholders in policy exercises. In that role a model should reproduce how people plausibly behave, hesitating, conceding late, and settling for imperfect deals, rather than playing the best move. We call this the sampler role, in contrast to the solver role of finding the best move, and we test how the reasoning modes providers ship to strengthen models as solvers affect it. Our testbed is multi-party negotiation: five agents bargain over a regulation for fifteen turns, and unresolved issues are decided by an authority. Agents without a structured memory of the negotiation almost never reach agreement, whether reasoning is on or off: 314 of 315 such runs end with the authority deciding. What reasoning changes is how the failure looks. With reasoning enabled, one model family negotiates visibly, with varied moves, concessions in most runs, and a different path every time, yet still ends without agreement in fifteen runs of fifteen. Diversity checks would pass a model whose endings never change. Two further results show the task permits agreement: when agents write their own short running notes on the negotiation, agreement becomes the norm, while the same notes supplied ready-made change nothing; and hand-coded agents following textbook concession strategies agree in most runs under identical rules. Simulation pipelines should therefore vet models as samplers, on the distributions of outcomes they produce. Fidelity as a sampler must be tested on its own: solver strength is no guide to it, and switching on reasoning leaves it where it was.

Sandro Andric

Multi-Agent LLM SystemsMulti-Agent NegotiationAutomated NegotiationLLM Agent EvaluationLarge Language Model-Based Social Simulation
AskPDF
Apr 12, 2026

PEMAND: Persona-Enriched Multi-Agent Negotiation for Household Decision-Making

Modeling household-level decisions is central to many real-world applications, including trip planning, residential mobility and migration, disaster management, etc. Existing studies primarily rely on classical machine learning models with limited predictive capacity, while recent LLM-based approaches have yet to incorporate behavioral theory or intra-household interaction dynamics, both of which are essential for modeling realistic household decisions. To address these limitations, we propose Persona-Enriched Multi-Agent Negotiation for household Decision-making (PEMAND), a novel LLM-based framework that integrates behavioral theory into individualized, household-aware persona modeling and simulates household-level decision-making through structured multi-agent negotiation. Specifically, PEMAND transforms static sociodemographic attributes into coherent narrative profiles that explicitly encode household-level attitudes, subjective norms, and perceived behavioral controls, following our proposed Household-Aware Chain-of-Planned-Behavior (HA-CoPB) framework. Building on these theory-grounded personas, PEMAND captures real-world household decision negotiation via a structured two-phase multi-agent conversation framework with a novel persona-alignment control mechanism. Evaluated on national and regional household decision datasets across two major domains, including travel behavior and residential mobility, PEMAND consistently outperforms state-of-the-art benchmarks.

Yuran Sun, Mustafa Sameen, Yaotian Zhang +5

University of Florida

Human Behavior SimulationLarge Language Model-Based Social SimulationMulti-Agent Negotiation
AskPDF
Apr 10, 2026

Instructing LLMs to Negotiate using Reinforcement Learning with Verifiable Rewards

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 negotiation. In this paper, we investigate if Reinforcement Learning from Verifiable Rewards (RLVR) can effectively teach LLMs to negotiate. Specifically, we explore the strategic behaviors that emerge during the learning process. We introduce a framework that trains a mid-sized buyer agent against a regulated LLM seller across a wide distribution of real-world products. By grounding reward signals directly in the maximization of economic surplus and strict adherence to private budget constraints, we reveal a novel four-phase strategic evolution. The agent progresses from naive bargaining to using aggressive starting prices, moves through a phase of deadlock, and ultimately develops sophisticated persuasive skills. Our results demonstrate that this verifiable training allows a 30B agent to significantly outperform frontier models over ten times its size in extracting surplus. Furthermore, the trained agent generalizes robustly to stronger counterparties unseen during training and remains effective even when facing hostile, adversarial seller personas.

Shuze Daniel Liu, Claire Chen, Jiabao Sean Xiao +4

Purdue University · California Institute of Technology · University of Illinois Urbana-Champaign +1

Automated NegotiationMulti-Agent NegotiationRL for LLM AgentsReinforcement Learning with Verifiable Rewards
AskPDF
Apr 10, 2026

Multi-agent Reinforcement Learning for Low-Carbon P2P Energy Trading among Self-Interested Microgrids

Uncertainties in renewable generation and demand dynamics challenge day-ahead scheduling. To enhance renewable penetration and maintain intra-day balance, we develop a multi-agent reinforcement learning framework for self-interested microgrids participating in peer-to-peer (P2P) electricity trading. Each microgrid independently bids both price and quantity while optimizing its own profit via storage arbitrage under time-varying main-grid prices. A market-clearing mechanism coordinating trades and promoting incentive compatibility is proposed. Simulation results show that the learned bidding policy improves renewable utilization and reduces reliance on high-carbon electricity, while increasing community-level economic welfare, delivering a win-win situation in emission reduction and local prosperity.

Junhao Ren, Honglin Gao, Lan Zhao +3

School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore · School of Information Science and Technology, University of Science and Technology of China, Hefei, China · Singapore Institute of Manufacturing Technology, Agency for Science, Technology and Research, Singapore

Power SystemsMulti-Agent Reinforcement LearningMulti-Agent Negotiation
AskPDF
Apr 10, 2026

Training Language Models for Bilateral Trade with Private Information

Bilateral bargaining under incomplete information provides a controlled testbed for evaluating large language model (LLM) agent capabilities. Bilateral trade demands individual rationality, strategic surplus maximization, and cooperation to realize gains from trade. We develop a structured bargaining environment where LLMs negotiate via tool calls within an event-driven simulator, separating binding offers from natural-language messages to enable automated evaluation. The environment serves two purposes: as a benchmark for frontier models and as a training environment for open-weight models via reinforcement learning. In benchmark experiments, a round-robin tournament among five frontier models (15,000 negotiations) reveals that effective strategies implement price discrimination through sequential offers. Aggressive anchoring, calibrated concession, and temporal patience correlate with the highest surplus share and deal rate. Accommodating strategies that concede quickly disable price discrimination in the buyer role, yielding the lowest surplus capture and deal completion. Stronger models scale their behavior proportionally to item value, maintaining performance across price tiers; weaker models perform well only when wide zones of possible agreement offset suboptimal strategies. In training experiments, we fine-tune Qwen3 (8B, 14B) via supervised fine-tuning (SFT) followed by Group Relative Policy Optimization (GRPO) against a fixed frontier opponent. These stages optimize competing objectives: SFT approximately doubles surplus share but reduces deal rates, while RL recovers deal rates but erodes surplus gains, reflecting the reward structure. SFT also compresses surplus variation across price tiers, which generalizes to unseen opponents, suggesting that behavioral cloning instills proportional strategies rather than memorized price points.

Dirk Bergemann, Soheil Ghili, Xinyang Hu +2

Department of Economics, Yale University · Yale School of Management, Yale University · Department of Statistics and Data Science, Yale University +1

Multi-Agent NegotiationLLM Agent TrainingLLM Fine-TuningRL for LLM Agents
AskPDF
Apr 9, 2026

Karma Mechanisms for Decentralised, Cooperative Multi Agent Path Finding

Multi-Agent Path Finding (MAPF) is a fundamental coordination problem in large-scale robotic and cyber-physical systems, where multiple agents must compute conflict-free trajectories with limited computational and communication resources. While centralised optimal solvers provide guarantees on solution optimality, their exponential computational complexity limits scalability to large-scale systems and real-time applicability. Existing decentralised heuristics are faster, but result in suboptimal outcomes and high cost disparities. This paper proposes a decentralised coordination framework for cooperative MAPF based on Karma mechanisms - artificial, non-tradeable credits that account for agents' past cooperative behaviour and regulate future conflict resolution decisions. The approach formulates conflict resolution as a bilateral negotiation process that enables agents to resolve conflicts through pairwise replanning while promoting long-term fairness under limited communication and without global priority structures. The mechanism is evaluated in a lifelong robotic warehouse multi-agent pickup-and-delivery scenario with kinematic orientation constraints. The results highlight that the Karma mechanism balances replanning effort across agents, reducing disparity in service times without sacrificing overall efficiency. Code: https://github.com/DerKevinRiehl/karma_dmapf

Kevin Riehl, Julius Schlapbach, Anastasios Kouvelas +1

Traffic Engineering Group, Institute for Transportation Planning and Systems, ETH Zürich, Stefano Franscini Platz 3, 8053 Zürich, Switzerland.

Multi-Agent Path FindingMechanism DesignMulti-Agent Negotiation
AskPDF
Apr 8, 2026

Agentic Copyright, Data Scraping & AI Governance: Toward a Coasean Bargain in the Era of Artificial Intelligence

This paper examines how the rapid deployment of multi-agentic AI systems is reshaping the foundations of copyright law and creative markets. It argues that existing copyright frameworks are ill-equipped to govern AI agent-mediated interactions that occur at scale, speed, and with limited human oversight. The paper introduces the concept of agentic copyright, a model in which AI agents act on behalf of creators and users to negotiate access, attribution, and compensation for copyrighted works. While multi-agent ecosystems promise efficiency gains and reduced transaction costs, they also generate novel market failures, including miscoordination, conflict, and collusion among autonomous agents. To address these market failures, the paper develops a supervised multi-agent governance framework that integrates legal rules and principles, technical protocols, and institutional oversight. This framework emphasizes ex ante and ex post coordination mechanisms capable of correcting agentic market failures before they crystallize into systemic harm. By embedding normative constraints and monitoring functions into multi-agent architectures, supervised governance aims to align agent behavior with the underlying values of copyright law. The paper concludes that AI should be understood not only as a source of disruption, but also as a governance tool capable of restoring market-based ordering in creative industries. Properly designed, agentic copyright offers a path toward scalable, fair, and legally meaningful copyright markets in the age of AI.

Paulius Jurcys, Mark Fenwick

Senior IP Counsel at Vinted · visiting Scholar at UC Berkeley School of Law · Professor of International Business Law at Kyushu University (Japan)

AI Agent GovernanceMulti-Agent Negotiation
AskPDF
Apr 8, 2026

EmoMAS: Emotion-Aware Multi-Agent System for High-Stakes Edge-Deployable Negotiation with Bayesian Orchestration

Large language models (LLMs) has been widely used for automated negotiation, but their high computational cost and privacy risks limit deployment in privacy-sensitive, on-device settings such as mobile assistants or rescue robots. Small language models (SLMs) offer a viable alternative, yet struggle with the complex emotional dynamics of high-stakes negotiation. We introduces EmoMAS, a Bayesian multi-agent framework that transforms emotional decision-making from reactive to strategic. EmoMAS leverages a Bayesian orchestrator to coordinate three specialized agents: game-theoretic, reinforcement learning, and psychological coherence models. The system fuses their real-time insights to optimize emotional state transitions while continuously updating agent reliability based on negotiation feedback. This mixture-of-agents architecture enables online strategy learning without pre-training. We further introduce four high-stakes, edge-deployable negotiation benchmarks across debt, healthcare, emergency response, and educational domains. Through extensive agent-to-agent simulations across all benchmarks, both SLMs and LLMs equipped with EmoMAS consistently surpass all baseline models in negotiation performance while balancing ethical behavior. These results show that strategic emotional intelligence is also the key driver of negotiation success. By treating emotional expression as a strategic variable within a Bayesian multi-agent optimization framework, EmoMAS establishes a new paradigm for effective, private, and adaptive negotiation AI suitable for high-stakes edge deployment.

Yunbo Long, Yuhan Liu, Liming Xu

University of Cambridge, UK · University of Toronto, Canada

Multi-Agent NegotiationAutomated NegotiationMulti-Agent LLM SystemsMulti-Agent OrchestrationAI Agent Benchmarks
AskPDF
Mar 23, 2026

MIND: Multi-agent inference for negotiation dialogue in travel planning

While Multi-Agent Debate (MAD) research has advanced, its efficacy in coordinating complex stakeholder interests such as travel planning remains largely unexplored. To bridge this gap, we propose MIND (Multi-agent Inference for Negotiation Dialogue), a framework designed to simulate realistic consensus-building among travelers with heterogeneous preferences. Grounded in the Theory of Mind (ToM), MIND introduces a Strategic Appraisal phase that infers opponent willingness (w) from linguistic nuances with 90.2% accuracy. Experimental results demonstrate that MIND outperforms traditional MAD frameworks, achieving a 20.5% improvement in High-w Hit and a 30.7% increase in Debate Hit-Rate, effectively prioritizing high-stakes constraints. Furthermore, qualitative evaluations via LLM-as-a-Judge confirm that MIND surpasses baselines in Rationality (68.8%) and Fluency (72.4%), securing an overall win rate of 68.3%. These findings validate that MIND effectively models human negotiation dynamics to derive persuasive consensus.

Hunmin Do, Taejun Yoon, Kiyong Jung

School of Mechanical Engineering, Sungkyunkwan University, Suwon, Korea · Department of Applied Artificial Intelligence, Sungkyunkwan University, Seoul, Korea · Department of Software, Sungkyunkwan University, Suwon, Korea

Travel PlanningMulti-Agent NegotiationMulti-Agent ConsensusMulti-Agent DebateLLM Planning
AskPDF
Mar 14, 2026

A Benchmark for Multi-Party Negotiation Games from Real Negotiation Data

Many real-world multi-party negotiations unfold as sequences of binding, action-level commitments rather than a single final outcome, yet this regime remains under-studied in existing benchmarks. We introduce a benchmark and evaluation framework for this setting, combining a configurable negotiation game generator with document-grounded instances derived from a climate negotiation exercise. We also provide several baseline solvers. Exact evaluation on small games and comparative evaluation on larger instances show that no solver dominates across regimes; performance depends on the structural properties of the game. These results motivate the creation of novel negotiation methods that value partial commitments robustly across diverse strategic regimes. Code and data for the benchmark are available at: https://anonymous.4open.science/r/negotiation_MARL-46B8

Leo Benac, Jonas Raedler, Zilin Ma +1

School of Engineering and Applied Sciences, Harvard University

Multi-Agent NegotiationAutomated Negotiation
AskPDF
Mar 11, 2026

Learning to Negotiate: Multi-Agent Deliberation for Collective Value Alignment in LLMs

LLM alignment has progressed in single-agent settings through paradigms such as RL with human feedback (RLHF), while recent work explores scalable alternatives such as RL with AI feedback (RLAIF) and dynamic alignment objectives. However, these approaches remain limited in multi-stakeholder settings, where conflicting values arise and deliberative negotiation is required. This work proposes a multi-agent negotiation-based alignment framework that aligns LLMs to Collective Agency (CA)-an existing alignment objective introduced to promote the continual expansion of agency-while simultaneously improving conflict-resolution capability. To enable scalable training, two self-play LLM instances are assigned opposing personas and engage in turn-based dialogue to synthesize mutually beneficial solutions. We generate synthetic moral-dilemma prompts and conflicting persona pairs, and optimize the policy via RLAIF using Group Relative Policy Optimization (GRPO) with an external LLM reward model. While rewards are computed from CA scores assigned to the final completion, gradients are applied to dialogue tokens to directly improve deliberative interaction dynamics. Experiments show that the model achieves CA alignment comparable to a single-agent baseline while substantially improving conflict-resolution performance without degrading general language capabilities. These results suggest that negotiation-driven deliberation training provides a practical path toward LLMs that better support collective decision-making in value-conflict scenarios.

Panatchakorn Anantaprayoon, Nataliia Babina, Nima Asgharbeygi +1

Integral AI · The University of Tokyo · MATS

Multi-Agent DeliberationLLM AlignmentValue AlignmentMulti-Agent NegotiationMulti-Agent Systems
AskPDF
Mar 4, 2026

Capability-Priced Micro-Markets: A Micro-Economic Framework for the Agentic Web over HTTP 402

This paper introduces Capability-Priced Micro-Markets (CPMM), a micro-economic framework designed to enable robust, scalable, and secure commerce among autonomous AI agents on the agentic web. The framework addresses the fundamental challenge of economic coordination in decentralized agent ecosystems, where entities must transact with minimal human oversight. CPMM synthesizes three key technologies into a unified system: MIT originated, Project NANDA infrastructure for cryptographically verifiable, capability-based security and discovery; the HTTP 402 "Payment Required" status code, with modern X402/H402 extensions for efficient, low-cost micropayments; and the Agent Capability Negotiation and Binding Protocol (ACNBP) for secure, multi-step negotiation and commitment. The paper formalizes agent interactions as a repeated bilateral game with incomplete information, demonstrating theoretically that the CPMM mechanism converges to a constrained Radner equilibrium, ensuring efficient outcomes under information asymmetry. A key theoretical contribution is the concept of "privacy elasticity of demand," which is introduced to quantify the trade-off between an agent's information disclosure and the market price of its services. By integrating secure capabilities, micropayment protocols, and formal negotiation mechanisms, CPMM provides a comprehensive, theoretically-grounded solution for creating functional micro-markets for the emergent agentic web.

Ken Huang, Jerry Huang, Mahesh Lambe +8

CSA and DistributedApps.ai · Kleiner Perkins · Unify Dynamics +4

Agentic CommerceMulti-Agent SystemsMulti-Agent Negotiation
AskPDF
Feb 22, 2026

Scaling Inference-Time Computation via Opponent Simulation: Enabling Online Strategic Adaptation in Repeated Negotiation

While large language models (LLMs) have emerged as powerful decision-makers across a wide range of single-agent and stationary environments, fewer efforts have been devoted to settings where LLMs must engage in repeated and strategic interactions with unknown or dynamic opponents. In such settings, recipes built upon offline pre-training or fine-tuning, though robust against worst-case adversaries, do not fully exploit the capability of LLMs to adapt online based on interaction feedback. Instead, we explore the more natural perspective of scaling inference-time computation as a mechanism for adaptation, embedding the principles of a classical game-theoretical learning dynamic, smooth Fictitious Play (sFP), into LLM inference: (i) for belief formation, we employ an auxiliary opponent model that in-context learns to imitate the time-averaged behavior of the opponent; (ii) for best response, we advance best-of-NN (BoN) sampling by simulating against the opponent model. Empirical evaluations on two distinct forms of repeated negotiation games demonstrate that our method enables significant performance improvement over repeated online interaction compared to various baselines, offering a scalable and principled approach to repeated strategic decision-making without any parameter updates.

Xiangyu Liu, Di Wang, Zhe Feng +1

Google Research · University of Maryland, College Park

Repeated GamesMulti-Agent NegotiationInference-Time ScalingOpponent Modeling
AskPDF
Feb 20, 2026

[Re] Benchmarking LLM Capabilities in Negotiation through Scoreable Games

Large Language Models (LLMs) demonstrate significant potential in multi-agent negotiation tasks, yet evaluation in this domain remains challenging due to a lack of robust and generalizable benchmarks. Abdelnabi et al. (2024) introduce a negotiation benchmark based on Scoreable Games, with the aim of developing a highly complex and realistic evaluation framework for LLMs. Our work investigates the reproducibility of claims in their benchmark, and provides a deeper understanding of its usability and generalizability. We replicate the original experiments on additional models, and introduce additional metrics to verify negotiation quality and evenness of evaluation. Our findings reveal that while the benchmark is indeed complex, model comparison is ambiguous, raising questions about its objectivity. Furthermore, we identify limitations in the experimental setup, particularly in information leakage detection and thoroughness of the ablation study. By examining and analyzing the behavior of a wider range of models on an extended version of the benchmark, we reveal insights that provide additional context to potential users. Our results highlight the importance of context in model-comparative evaluations.

Jorge Carrasco Pollo, Ioannis Kapetangeorgis, Joshua Rosenthal +1

Informatics Institute University of Amsterdam

LLM EvaluationAI Agent BenchmarksMulti-Agent Negotiation
AskPDF
Jan 7, 2026

The Language of Bargaining: Linguistic Effects in LLM Negotiations

Negotiation is a core component of social intelligence, requiring agents to balance strategic reasoning, cooperation, and social norms. Recent work shows that LLMs can engage in multi-turn negotiation, yet nearly all evaluations occur exclusively in English. Using controlled multi-agent simulations across Ultimatum, Buy-Sell, and Resource Exchange games, we systematically isolate language effects across English and four Indic framings (Hindi, Punjabi, Gujarati, Marwadi) by holding game rules, model parameters, and incentives constant across all conditions. We find that language choice can shift outcomes more strongly than changing models, reversing proposer advantages and reallocating surplus. Crucially, effects are task-contingent: Indic languages reduce stability in distributive games yet induce richer exploration in integrative settings. Our results demonstrate that evaluating LLM negotiation solely in English yields incomplete and potentially misleading conclusions. These findings caution against English-only evaluation of LLMs and suggest that culturally-aware evaluation is essential for fair deployment.

Stuti Sinha, Himanshu Kumar, Aryan Raju Mandapati +2

BITS Pilani

Multilingual Language Model EvaluationMulti-Agent NegotiationAutomated NegotiationMulti-Agent LLMs
AskPDF