arXiv subjects

David Marn

Publications and source records attributed to David Marn.

4 recordsLinked to original sources

arXiv2026

AgentBeats: Agentifying Agent Assessment for Openness, Standardization, and Reproducibility

Agent systems are advancing quickly across domains, but their evaluation remains fragmented. Most benchmarks rely on fixed, LLM-centric harnesses that require heavy integration, create test-production mismatch, and limit fair comparison across diverse agent designs. The root problem is the lack of an open, agent-agnostic assessment interface. We advocate Agentified Agent Assessment (AAA), where evaluation is performed by judge agents and all participants interact through standardized protocols: A2A for task management and MCP for tool access. Conventional benchmarking defines two separate interfaces, one for the benchmark and one for the agent, while AAA only needs one; this yields a generic, unified framework that separates assessment logic from agent implementation and enables reproducible, interoperable, and multi-agent evaluation. We further introduce AgentBeats as a concrete realization of AAA: we identify five practical operation modes that make standardized assessment compatible with real-world constraints on openness, privacy, and reproducibility. To evaluate our design at scale, we conduct two studies: a five-month open competition that drew 298 judge agents across 12 categories together with 467 subject agents from independent participants, showing that AAA applies across a heterogeneous range of benchmarks; and a case study on coding agents that confirms agentified evaluation preserves fidelity with the public record while surfacing previously missing head-to-head results, yielding research insights about agent design. Combining a community-scale field study and a controlled coding case study, we verify that AAA delivers coverage, practicality, and fidelity across heterogeneous scenarios at scale. Together, AAA and AgentBeats offer a clear path toward open, standardized, and reproducible agent assessment.

cs.AI↗

arXiv2021

A General Purpose Transpiler for Fully Homomorphic Encryption

Fully homomorphic encryption (FHE) is an encryption scheme which enables computation on encrypted data without revealing the underlying data. While there have been many advances in the field of FHE, developing programs using FHE still requires expertise in cryptography. In this white paper, we present a fully homomorphic encryption transpiler that allows developers to convert high-level code (e.g., C++) that works on unencrypted data into high-level code that operates on encrypted data. Thus, our transpiler makes transformations possible on encrypted data. Our transpiler builds on Google's open-source XLS SDK (https://github.com/google/xls) and uses an off-the-shelf FHE library, TFHE (https://tfhe.github.io/tfhe/), to perform low-level FHE operations. The transpiler design is modular, which means the underlying FHE library as well as the high-level input and output languages can vary. This modularity will help accelerate FHE research by providing an easy way to compare arbitrary programs in different FHE schemes side-by-side. We hope this lays the groundwork for eventual easy adoption of FHE by software developers. As a proof-of-concept, we are releasing an experimental transpiler (https://github.com/google/fully-homomorphic-encryption/tree/main/transpiler) as open-source software.

cs.CR↗

arXiv2017

Iterative Local Voting for Collective Decision-making in Continuous Spaces

Many societal decision problems lie in high-dimensional continuous spaces not amenable to the voting techniques common for their discrete or single-dimensional counterparts. These problems are typically discretized before running an election or decided upon through negotiation by representatives. We propose a algorithm called {\sc Iterative Local Voting} for collective decision-making in this setting. In this algorithm, voters are sequentially sampled and asked to modify a candidate solution within some local neighborhood of its current value, as defined by a ball in some chosen norm, with the size of the ball shrinking at a specified rate. We first prove the convergence of this algorithm under appropriate choices of neighborhoods to Pareto optimal solutions with desirable fairness properties in certain natural settings: when the voters' utilities can be expressed in terms of some form of distance from their ideal solution, and when these utilities are additively decomposable across dimensions. In many of these cases, we obtain convergence to the societal welfare maximizing solution. We then describe an experiment in which we test our algorithm for the decision of the U.S. Federal Budget on Mechanical Turk with over 2,000 workers, employing neighborhoods defined by $\mathcal{L}^1, \mathcal{L}^2$ and $\mathcal{L}^\infty$ balls. We make several observations that inform future implementations of such a procedure.

cs.MA↗

arXiv2015

The Square Root Agreement Rule for Incentivizing Truthful Feedback on Online Platforms

A major challenge in obtaining evaluations of products or services on e-commerce platforms is eliciting informative responses in the absence of verifiability. This paper proposes the Square Root Agreement Rule (SRA): a simple reward mechanism that incentivizes truthful responses to objective evaluations on such platforms. In this mechanism, an agent gets a reward for an evaluation only if her answer matches that of her peer, where this reward is inversely proportional to a popularity index of the answer. This index is defined to be the square root of the empirical frequency at which any two agents performing the same evaluation agree on the particular answer across evaluations of similar entities operating on the platform. Rarely agreed-upon answers thus earn a higher reward than answers for which agreements are relatively more common. We show that in the many tasks regime, the truthful equilibrium under SRA is strictly payoff-dominant across large classes of natural equilibria that could arise in these settings, thus increasing the likelihood of its adoption. While there exist other mechanisms achieving such guarantees, they either impose additional assumptions on the response distribution that are not generally satisfied for objective evaluations or they incentivize truthful behavior only if each agent performs a prohibitively large number of evaluations and commits to using the same strategy for each evaluation. SRA is the first known incentive mechanism satisfying such guarantees without imposing any such requirements. Moreover, our empirical findings demonstrate the robustness of the incentive properties of SRA in the presence of mild subjectivity or observational biases in the responses. These properties make SRA uniquely attractive for administering reward-based incentive schemes (e.g., rebates, discounts, reputation scores, etc.) on online platforms.

cs.GT↗