Image de couverture de livre

Beyond Scalar Rewards: Dense Feedback for LLM Policy Synthesis in Sequential Social Dilemmas

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Gallego, Víctor
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language Computer Science and Game Theory
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Will Systems of LLM Agents Cooperate: An Investigation into a Social Dilemma
par: Willis, Richard, et autres
Publié: (2025)

Beyond Game Theory Optimal: Profit-Maximizing Poker Agents for No-Limit Holdem
par: Yi, SeungHyun, et autres
Publié: (2025)

Emergent LLM behaviors are observationally equivalent to data leakage
par: Barrie, Christopher, et autres
Publié: (2025)

Environment Complexity and Nash Equilibria in a Sequential Social Dilemma
par: Yasir, Mustafa, et autres
Publié: (2024)

STRIDE: A Tool-Assisted LLM Agent Framework for Strategic and Interactive Decision-Making
par: Li, Chuanhao, et autres
Publié: (2024)

Online Learning and Equilibrium Computation with Ranking Feedback
par: Liu, Mingyang, et autres
Publié: (2026)

Inference of Altruism and Intrinsic Rewards in Multi-Agent Systems
par: Villin, Victor, et autres
Publié: (2025)

Adversarial Knapsack for Sequential Competitive Resource Allocation
par: Thakoor, Omkar, et autres
Publié: (2025)

Mechanism Design for LLM Fine-tuning with Multiple Reward Models
par: Sun, Haoran, et autres
Publié: (2024)

Sequential Decision Making in Stochastic Games with Incomplete Preferences over Temporal Objectives
par: Kulkarni, Abhishek Ninad, et autres
Publié: (2025)

Emergence of Cooperation and Commitment in Optional Prisoner's Dilemma
par: Song, Zhao, et autres
Publié: (2025)

Properties of Winning Iterated Prisoner's Dilemma Strategies
par: Glynatsi, Nikoleta E., et autres
Publié: (2020)

Who Gets the Reward, Who Gets the Blame? Evaluation-Aligned Training Signals for Multi-LLM Agents
par: Yang, Chih-Hsuan, et autres
Publié: (2025)

Quantifying the Self-Interest Level of Markov Social Dilemmas
par: Willis, Richard, et autres
Publié: (2025)

Ad Insertion in LLM-Generated Responses
par: Xu, Shengwei, et autres
Publié: (2026)

The Language of Bargaining: Linguistic Effects in LLM Negotiations
par: Sinha, Stuti, et autres
Publié: (2026)

Incentive-Aligned Multi-Source LLM Summaries
par: Jiang, Yanchen, et autres
Publié: (2025)

Inferring Strategies from Observations in Long Iterated Prisoner's Dilemma Experiments
par: Montero-Porras, Eladio, et autres
Publié: (2022)

Online Scalarization in Vector-Valued Games
par: Asadollahi, Ehsan, et autres
Publié: (2026)

Framing the Game: How Context Shapes LLM Decision-Making
par: Robinson, Isaac, et autres
Publié: (2025)

Reply to "Emergent LLM behaviors are observationally equivalent to data leakage"
par: Ashery, Ariel Flint, et autres
Publié: (2025)

Self-Play Q-learners Can Provably Collude in the Iterated Prisoner's Dilemma
par: Bertrand, Quentin, et autres
Publié: (2023)

Verification Required: The Impact of Information Credibility on AI Persuasion
par: Mahmud, Saaduddin, et autres
Publié: (2026)

Evolving Diverse Red-team Language Models in Multi-round Multi-agent Games
par: Ma, Chengdong, et autres
Publié: (2023)

Measuring Bargaining Abilities of LLMs: A Benchmark and A Buyer-Enhancement Method
par: Xia, Tian, et autres
Publié: (2024)

Fairshare Data Pricing via Data Valuation for Large Language Models
par: Zhang, Luyang, et autres
Publié: (2025)

Make an Offer They Can't Refuse: Grounding Bayesian Persuasion in Real-World Dialogues without Pre-Commitment
par: He, Buwei, et autres
Publié: (2025)

Incremental Data-Driven Policy Synthesis via Game Abstractions
par: Sağlam, Irmak, et autres
Publié: (2025)

EconEvals: Benchmarks and Litmus Tests for Economic Decision-Making by LLM Agents
par: Fish, Sara, et autres
Publié: (2025)

Generating Fair Consensus Statements with Social Choice on Token-Level MDPs
par: Blair, Carter, et autres
Publié: (2025)

Unending Sequential Auctions
par: Ban, Amir
Publié: (2025)

ALYMPICS: LLM Agents Meet Game Theory -- Exploring Strategic Decision-Making with AI Agents
par: Mao, Shaoguang, et autres
Publié: (2023)

The Fairness of Maximum Nash Social Welfare Under Matroid Constraints and Beyond
par: Wang, Yuanyuan, et autres
Publié: (2024)

How memory can affect collective and cooperative behaviors in an LLM-Based Social Particle Swarm
par: Hishiki, Taisei, et autres
Publié: (2026)

Sequential Linear Contracts on Matroids
par: Pashkovich, Kanstantsin, et autres
Publié: (2026)

Contract Design for Sequential Actions
par: Ezra, Tomer, et autres
Publié: (2024)

Symbolic Computation of Sequential Equilibria
par: Graf, Moritz, et autres
Publié: (2024)

Augmented Probability Simulation Methods for Sequential Games
par: Ekin, Tahir, et autres
Publié: (2019)

Regret Minimization for Piecewise Linear Rewards: Contracts, Auctions, and Beyond
par: Bacchiocchi, Francesco, et autres
Publié: (2025)

Selfish Mining under General Stochastic Rewards
par: Bahrani, Maryam, et autres
Publié: (2025)