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

Reyhan Aydoğan; Tim Baarslag; Tamara C. P. Florijn; Katsuhide Fujita; Catholijn M. Jonker; Yasser Mohammad

cs.MAApr 15, 2026

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

Authors: Reyhan Aydoğan, Tim Baarslag, Tamara C. P. Florijn, Katsuhide Fujita, Catholijn M. Jonker, Yasser Mohammad

Organizations: Özye˘gin Üniversity · Delft University of Technology · Centrum Wiskunde & Informatica (CWI) · Eindhoven University of Technology ·

Abstract

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.

Figures & tables

Rank	Agent	As Center	As Edge	Final Score
1	RUFL	0.714	0.084	0.399
1	SAC Agent	0.733	0.064	0.399
3	UFunAtAgent	0.686	0.078	0.382

Table 1: ANL 2025 Results

Track	Rank	Agent	Score
OnShot		CautiousOneShotAgent	1.0915
	1	CostAverseAgent	1.0896
	1	Rchan	1.0895
	1	AlmostEqualAgent	1.0892
Standard	1	AS0	1.009
		PenguinAgent	0.992

Table 2: SCML 2025 Results

Automated Negotiation

Automated negotiation studies computational agents that bargain over prices, preferences, and agreements in human, market, and multi-agent settings.

See all 44 papers

Cooperate to Compete: Strategic Coordination in Multi-Agent Conquest
Apr 28, 2026Abigail O'Neill, Alan Zhu, Mihran Miroyan +2Multi-Agent Coordination Multi-Agent Negotiation
University of California, Berkeley
Parallelism or Concession? Concurrency-Aware Procurement Negotiation for Agentic Commerce
Oct 5, 2026Xiaolin Xu, Donghao ZhuMulti-Agent System Optimization Automated Negotiation
School of Business Nanjing University Nanjing, Jiangsu, China · Institute of Business Sciences University of Tsukuba Bunkyo-ku, Tokyo, Japan · University of Tokyo Market Design Center Bunkyo-ku, Tokyo, Japan
TERMS-Bench: Diagnosing LLM Negotiation Agents Beyond Deal Rate
May 13, 2026Erica Zhang, Fangzhao Zhang, Aneesh Pappu +5Multi-Agent Negotiation Automated Negotiation
♠Stanford School of Engineering · ♣Stanford Department of Economics · ♥Stanford Graduate School of Business +1

Apr 28, 2026J/K move · Enter open · S save

Cooperate to Compete: Strategic Coordination in Multi-Agent Conquest

Abigail O'Neill, Alan Zhu, Mihran Miroyan, Narges Norouzi+1

University of California, Berkeley

Multi-Agent Coordination Multi-Agent Negotiation Automated Negotiation Human-AI Interaction AI Agent Benchmarks Multi-Agent LLMs

Open paper AskPDF arXiv

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.

Abstract

Automated Negotiation

Explore similar work

Cooperate to Compete: Strategic Coordination in Multi-Agent Conquest

Parallelism or Concession? Concurrency-Aware Procurement Negotiation for Agentic Commerce

TERMS-Bench: Diagnosing LLM Negotiation Agents Beyond Deal Rate