Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2202.06660

Non-Obvious Manipulability for Single-Parameter Agents and Bilateral Trade

Thomas Archbold·Bart de Keijzer·Carmine Ventre
View original source ↗Read source document ↗Export metadata ↓

Abstract

A recent line of work in mechanism design has focused on guaranteeing incentive compatibility for agents without contingent reasoning skills: obviously strategyproof mechanisms guarantee that it is "obvious" for these imperfectly rational agents to behave honestly, whereas non-obviously manipulable (NOM) mechanisms take a more optimistic view and ensure that these agents will only misbehave when it is "obvious" for them to do so. Technically, obviousness requires comparing certain extrema (defined over the actions of the other agents) of an agent's utilities for honest behaviour against dishonest behaviour. We present a technique for designing NOM mechanisms in settings where monetary transfers are allowed based on cycle monotonicity, which allows us to disentangle the specification of the mechanism's allocation from the payments. By leveraging this framework, we completely characterise both allocation and payment functions of NOM mechanisms for single-parameter agents. We then look at the classical setting of bilateral trade and study whether and how much subsidy is needed to guarantee NOM, efficiency, and individual rationality. We prove a stark dichotomy; no finite subsidy suffices if agents look only at best-case extremes, whereas no subsidy at all is required when agents focus on worst-case extremes. We conclude the paper by characterising the NOM mechanisms that require no subsidies whilst satisfying individual rationality.

Explore related subjects

cs.GT

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Thomas Archbold, Bart de Keijzer, Carmine Ventre. 2023-12-13. Non-Obvious Manipulability for Single-Parameter Agents and Bilateral Trade. https://arxiv.org/abs/2202.06660

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Control and Bribery in Stable Marriage and Stable Roommates: A Complete Complexity Landscape

We study control and bribery problems for stable matchings: A central authority (the controller, resp. briber) may add agents, delete agents, delete acceptable pairs, swap two adjacent agents in some agent's preference list, or arbitrarily reorder some agent's preference list, in an instance of Stable Marriage or Stable Roommates. We extend previous work on control and bribery in stable matchings by Boehmer et al. [8]. We consider goals capturing individual and pair inclusion, stability, and uniqueness requirements: Matching a designated agent (MA), matching a designated pair (MP), realizing a stable matching consistent with a given matching (MS), making a given matching the unique stable matching (USM), or guaranteeing that a stable (resp. perfect and stable) matching exists ($\exists$SM/$\exists$PSM). We provide a unified complexity map for all non-trivial action-goal combinations in both settings, consolidating known results and extending the study to the roommates model, where stable matchings need not exist.

cs.GT↗
arXiv2026

How a Cooperative-Override Circuit Suppresses Nash Play in Large Language Models

On the named Prisoner's Dilemma under direct prompting, three larger instruction-tuned models, Llama-3-70B, Qwen2.5-32B, and Qwen2.5-72B, lock at full cooperation, the metric's maximum distance from Nash with zero variance across replicates, while Llama-3-8B plays near-Nash. Opening the models, a logit-lens analysis finds a distributed cooperative override. Intermediate readouts lean toward the Nash action through roughly three quarters of network depth before a late surge toward cooperation, and the final layer settles the contest. The size of that final correction, not the surge, rank-matches chain-of-thought behavior across scale and two architectures. In the 8B the override is a single causally controllable direction in the residual stream; steering it dials the decision, and clamping its component at one position of one layer moves the choice strictly monotonically, Spearman rho = 1.000, with generation fluent. The circuit is lexical. It survives name removal and payoff rescaling but disengages when Cooperate and Defect are replaced with neutral labels, and on 48 payoff-random games with neutral surfaces no model locks cooperative on any dilemma or shows general equilibrium competence. In mixed-model populations a single Nash-playing agent collapses cooperation contagiously. What suppresses Nash play in large language models is a word-triggered circuit rather than missing competence, and it can be measured, bounded, and controlled.

cs.GT↗
arXiv2026

Auction Design with ROI-Constrained Bidders: Truthfulness and Revenue Maximization

The return-on-investment (ROI) constraint is central to many auctions, particularly in online advertising, where a bidder is unwilling to pay more than a fixed fraction of the value obtained. We study truthful and revenue-maximizing auctions for ROI-constrained bidders. We first characterize truthful auctions when both valuations and ROI constraints are private, showing that the allocation rule uniquely determines the payment rule. Building on this characterization, for multiple bidders we introduce $σ$-increment mechanisms that resemble Myerson's optimal mechanism~\cite{journals/mor/Myerson81}; as $σ$ vanishes, these mechanisms become asymptotically optimal among deterministic truthful mechanisms, and their revenue approaches at least a $1/\bar r$ fraction of the optimal expected revenue over all truthful mechanisms, where $\bar r$ is the largest possible ROI constraint. In the single-bidder setting, we prove that every truthful auction can be replaced by a convex pricing function with weakly higher payments for every type, and we derive the optimal pricing functions when either the valuation or the ROI constraint is public.

cs.GT↗