Online Agent-as-a-Judge deploys an in-world evaluator agent to generate relevant situations via native interactions, improving criteria coverage and human label agreement over passive trajectory scoring in a life-simulation with 32 social criteria.
Title resolution pending
10 Pith papers cite this work, alongside 175 external citations. Polarity classification is still indexing.
10
Pith papers citing it
175
external citations · external index
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
PRAXA is a compositional grammar for what-if analysis with data, model, and interaction primitives, encoded in PSL, shown to reconstruct existing workflows and enable new multi-step compositions.
LLMs default to responses more similar to opinions from the USA and some European and South American countries; prompting for a country shifts alignment but can introduce stereotypes, while translation does not reliably match language speakers.
A survey of 457 papers yields a six-dimensional design space for abstraction in interactive systems that reframes gulfs of execution and evaluation while articulating cognitive and design processes for bridging abstraction gaps.
Co-design study with immigrants and journalists identifies an unaddressed-or-unaccountable paradox and proposes four metaphors for conversational AI agents in reader-oriented news.
SenseWalk is an LLM-powered agent-based simulation system for semantic trajectories that combines LLMs with the social force model, supported by a user interface, quantitative evaluation, and a user study with 12 participants.
Qualitative study of 19 CS students using multi-view visualizations reveals selective engagement driven by agency, fit, and legitimacy rather than cognitive load reduction alone.
Large-scale experiment with 1440 task executions finds dynamic routing of coordination strategies achieves near-best quality scores across models and classes but does not reliably identify exact winners.
Introduces the Mechanism Plausibility Scale, a four-level framework separating generative sufficiency from mechanistic plausibility in LLM-based agent-based models.
LLM agents in controlled network debates show agreement drift toward specific opinion positions, requiring separation of structural effects from LLM biases before using them as human behavioral proxies.
citing papers explorer
-
Online Agent-as-a-Judge: Situation-Generating Evaluation for Interactive Agents
Online Agent-as-a-Judge deploys an in-world evaluator agent to generate relevant situations via native interactions, improving criteria coverage and human label agreement over passive trajectory scoring in a life-simulation with 32 social criteria.
-
PRAXA: A Grammar for What-If Analysis
PRAXA is a compositional grammar for what-if analysis with data, model, and interaction primitives, encoded in PSL, shown to reconstruct existing workflows and enable new multi-step compositions.
-
Towards Measuring the Representation of Subjective Global Opinions in Language Models
LLMs default to responses more similar to opinions from the USA and some European and South American countries; prompting for a country shifts alignment but can introduce stereotypes, while translation does not reliably match language speakers.
-
Making Abstraction Concrete: A Design Space and Interaction Model of Abstraction in Interactive Systems
A survey of 457 papers yields a six-dimensional design space for abstraction in interactive systems that reframes gulfs of execution and evaluation while articulating cognitive and design processes for bridging abstraction gaps.
-
Are Conversational AI Agents the Way Out? Co-Designing Reader-Oriented News Experiences with Immigrants and Journalists
Co-design study with immigrants and journalists identifies an unaddressed-or-unaccountable paradox and proposes four metaphors for conversational AI agents in reader-oriented news.
-
SenseWalk: Agent-Based Semantic Trajectory Simulation Powered by Large Language Models in Zoned Environments
SenseWalk is an LLM-powered agent-based simulation system for semantic trajectories that combines LLMs with the social force model, supported by a user interface, quantitative evaluation, and a user study with 12 participants.
-
Code as Anchor, Memory and Metaphor as Support: Learner Experiences with Multi-View Visualizations
Qualitative study of 19 CS students using multi-view visualizations reveals selective engagement driven by agency, fit, and legitimacy rather than cognitive load reduction alone.
-
Dynamic Coordination Strategy Selection for Enterprise Multi-Agent Systems
Large-scale experiment with 1440 task executions finds dynamic routing of coordination strategies achieves near-best quality scores across models and classes but does not reliably identify exact winners.
-
Mechanism Plausibility in Generative Agent-Based Modeling
Introduces the Mechanism Plausibility Scale, a four-level framework separating generative sufficiency from mechanistic plausibility in LLM-based agent-based models.
-
Network Effects and Agreement Drift in LLM Debates
LLM agents in controlled network debates show agreement drift toward specific opinion positions, requiring separation of structural effects from LLM biases before using them as human behavioral proxies.