Papers for

multiagent system designers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Economic institutions expanded as design tools for artificial agents

Beyond Named Mechanisms: Economic Institutions as a Design Space for Artificial Agents

Abstract: Multiagent research inherited its economic vocabulary of auctions, markets, prices, bargaining, and matching from a single observed case: human societies. Those institutions bundle identity, competence, execution, ownership, commitment, and settlement in ways that suit agents whose minds are private, who learn rather than copy skills, and who each persist as one person. Engineered agents need not share any of these constraints, making the list of familiar institutions look less like the entirety of economic organization and more like a sample from a larger, unmapped space. We sketch one way to make that space concrete: a provisional chart that records each institution, separately from the agents that run it, as a typed structure over positions, rights and duties, allocation, information, time, state, process, value, and external recognition. In this chart, named institutions become overlapping regions rather than fixed points, neighboring families separate along a few coordinates, and the gaps between them become places to search. We show what the shift in perspective buys with a simulation in which one technical act, copying an agent's competence, is institutionalized as a new independent supplier, as licensed capacity that creates no new participant, and as the splitting of one economic position into successors that inherit some obligations and not others. In a paired task, all three produce an identical technical trace despite differing in who exists, who owns the copy, who is obligated, and who gets paid. We close with a research program: building a principled chart of institution space, mapping how its implementable region shifts with agent capacities, and revising the chart wherever engineered agents expose distinctions it cannot express.

Wed 11 NovMultiagent SystemsArtificial IntelligenceComputer Science and Game Theory
The gist
Many ideas in multiagent systems come from human economic setups like markets and auctions, which fit human characteristics. The authors suggest there’s a much bigger variety of economic institutions possible for artificial agents that don’t share human limitations. They propose a way to map these institutions based on features like rights, duties, and ownership instead of fixed names. By simulating how copying skills can be handled in different institutional ways, they show these alternatives can produce the same outcomes while changing who is responsible or paid. This work opens new directions for designing how artificial agents interact in economic systems.
Open → 2611.15017v1

Bayesian dynamics invert dominance and foster cooperation in games

Bayesian Replicator Dynamics and the Inversion of Strict Dominance in Bimatrix Games

Abstract: Replicator dynamics, the central model of evolutionary game theory, describe populations evolving under selection and agents learning by trial and error. They also admit a third use: continuous-time Bayesian inference, in which an agent planning against an opponent accumulates evidence for each candidate strategy. Here we show that this use divides all two-player games into two classes. With the standard expected-utility payoff, the dynamics can be expressed as Bayesian updating only in games (with any number of actions) where no player has a dominant strategy. The logarithmic payoff of Ay and Erb admits the Bayesian representation in every game. Coordination, anti-coordination, and cyclic games share qualitative dynamics under both payoff definitions, with equilibria displaced and selection thresholds shifted. In contrast, the flows of every game with a dominant strategy are reversed between the payoff definitions, with the strictly dominant strategy eliminated under logarithmic payoffs. Cooperation therefore emerges in the Prisoner's Dilemma, and games of common interest converge to mutual defection. For two-action games the classification is complete and rests on an exact Hamiltonian structure shared by both payoff definitions. The structure gives a behavioural test: cycles in the classic Matching Pennies game have amplitude-independent period (isochronous) under logarithmic payoffs, but not under expected utility. Logarithmic evidence integration thus determines which strategic outcomes dynamical selection can reach, wherever learning approximates Bayesian updating.

Mon 26 OctComputer Science and Game TheoryMultiagent Systems
The gist
This paper studies how players learn and evolve strategies in games where they compete or cooperate. It shows that when players update their beliefs in a Bayesian way using a special logarithmic method, the usual advantage of clearly better strategies can flip. For example, in the classic Prisoner's Dilemma, this approach can promote cooperation instead of defection. The authors also find distinct patterns in how players cycle through strategies under this method compared to traditional payoffs. These insights help explain how different learning rules influence game outcomes.
Open → 2610.36345v1

Two agent game powers linked to neighborhood frames in eight models

Representation Theorems for Actual Powers over Two-Agent General Concurrent Game Frames

Abstract: One of the most well-known connections between logic and games is Pauly's representation theorem: the induced powers of individuals and coalitions in concurrent game frames correspond, in a precise sense, to a certain class of neighborhood frames. The precise sense here is what is called alpha effectivity (or alpha power): the power of a coalition is characterized by the sets of states in which it can ensure that the outcome lies by taking some joint action. This definition is inherently monotonic, and, as pointed out by van Benthem, Bezhanishvili, and Enqvist (2019), that fact can obscure relevant information about the power structure in the game: we do not know whether two sets that a coalition has the power to enforce correspond to the same joint action or to different joint actions. An alternative is to characterize the power of a coalition by its actual power (called basic power by van Benthem, Bezhanishvili, and Enqvist (2019)): the collection of sets of states, each of which corresponds to one joint action by the coalition and all possible joint actions by the other agents. It has recently been argued by Li and Ju (2025, 2026) that standard concurrent game frames rely on three assumptions that may, in some cases, be too strong: seriality, independence of agents, and determinism. This yields a total of eight different classes of general concurrent game frames. In this paper, assuming two agents, we prove that, in terms of actual powers, the eight classes of general concurrent game frames are represented by eight corresponding classes of neighborhood frames. This generalizes a result by van Benthem, Bezhanishvili, and Enqvist (2019).

Sun 11 OctLogic in Computer ScienceComputer Science and Game TheoryMultiagent Systems
The gist
Games where two players make choices simultaneously can be studied using mathematical structures that describe what each player can ensure happens. Earlier work focused on a simplified view that missed details about how specific joint choices affect outcomes. This paper extends the understanding by considering eight different models of such games, each relaxing some standard assumptions. The authors show that each model corresponds neatly to a certain class of mathematical structures called neighborhood frames when considering actual powers, giving a fuller picture of what players can do together.
Open → 2610.15476v1

Optimistic hedge achieves lower regret in multiplayer games

A Logarithmic Regret Bound for Optimistic Hedge in General-Sum Games

Abstract: Can simple no-regret dynamics attain smaller regret in self-play than against arbitrary adversaries? In $n$-player general-sum games, Daskalakis et al. 2021 proved an $O(n\log d_i\log^4 T)$ individual regret bound for Optimistic Hedge, which improves upon the classical $O(\sqrt T)$ adversarial regret bound. In this work, we show that Optimistic Hedge with a constant step size can further achieve $O(\sqrt n\log d_i\log T)$ individual external regret under expected loss-vector feedback. The time-averaged play consequently enjoys a coarse correlated equilibrium gap $O(\sqrt n\log d\log T/T)$, where $d=\max_i d_i$. The improvement comes from a larger admissible step size $η=Θ(1/(\sqrt n\log T))$. Our analysis proves factorial bounds on high-order differences of probability-weighted pairwise loss gaps, then applies finite-difference interpolation in a fixed Euclidean norm. These estimates sharpen the analysis of Daskalakis et al. 2021 and yield a logarithmic regret bound.

Thu 17 SeptComputer Science and Game Theory
The gist
This work looks at how players can get better at making decisions in games where multiple people compete and cooperate. It shows that a specific learning method called Optimistic Hedge can learn faster and make fewer mistakes over time compared to previous approaches. The authors prove this by using a new mathematical analysis that allows the method to use a larger learning step. This improvement means players’ average strategies stabilize closer to an equilibrium faster than before.
Open → 2609.19677v1

Risk attitudes influence long-term outcomes in coordination games

Entropic Risk-Sensitive Evolutionary Learning and Equilibrium Selection in Coordination Games

Abstract: We study risk-sensitive evolutionary learning dynamics and their long-run equilibrium selection behaviors in coordination games. Agents' risk attitudes enter through the classical entropic risk measure, which evaluates opponent-induced payoff uncertainty and feeds into noisy best responses under two standard revision protocols: best response with mutations and logit choice. We first analyze $2\times 2$ coordination games in both single-population symmetric and two-population asymmetric settings. In the single-population setting, unlike the risk-neutral case where the dynamics are known to favor the risk-dominant equilibrium, we show that risk sensitivity can change the stochastically stable outcome: a greater risk-seeking attitude favors the payoff-dominant equilibrium, while a greater risk-averse attitude favors the maximin equilibrium. Thus, the population's risk attitude may act as a control knob for long-run equilibrium selection. In both population settings, we also identify a robust regime: any super-dominant equilibrium is stochastically stable for all risk attitudes, under both protocols, and across populations. We further extend the single-population analysis to symmetric $k$-action games, which include symmetric $k$-action coordination games as a special case, under risk-sensitive best response with mutations. In this setting, we show that, for sufficiently large populations, sufficiently risk-seeking agents uniquely select the strongly payoff-dominant equilibrium when it exists, whereas sufficiently risk-averse agents uniquely select the strongly maximin equilibrium when it exists. These results show that entropic risk sensitivity may serve as a systematic mechanism for steering equilibrium selection in evolutionary games, beyond the classical risk-neutral benchmark.

Tue 8 SeptComputer Science and Game TheoryMultiagent Systems
The gist
Sometimes people or groups have to choose together between different options that benefit them differently. This study looks at how being more or less worried about risk changes which shared choice is made over time. The authors show that when players are more risk-seeking, they tend to pick the option with the highest reward, but when they are more risk-averse, they prefer the safest option. These results suggest that how people feel about risk acts like a control that can steer which outcome becomes stable in repeated decisions.
Open → 2609.08677v1