On UPBench, 25 LLMs show a non-monotonic planning curve—strong Remember/Analyze, weak Understand/Evaluate—with four failure modes that support differential, not blanket, AI delegation.
hub
Arriaga, and Adam Tauman Kalai
13 Pith papers cite this work, alongside 124 external citations. Polarity classification is still indexing.
13
Pith papers citing it
124
external citations · external index
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
unclear 1representative citing papers
A new battery of 30 cognitive tasks demonstrates that process-level behavioral features distinguish humans from frontier AI agents better than performance metrics (mean AUC 0.88), with process-specific fine-tuning improving mimicry but limited cross-task transfer.
LLMs diverge from human goal selection in self-directed learning by exploiting single solutions with low variability across instances.
DoubleAgents shows that a distributed-cognition design with coordination agent, dashboard, and policy module increases user comfort and reliance on AI agents for coordination tasks over time.
Length-controlled AlpacaEval applies regression adjustment to remove length bias from LLM auto-evaluations, raising Spearman correlation with Chatbot Arena from 0.94 to 0.98.
LLM embeddings enable strong retrodiction of masked GSS opinions via cross-validation and external validation but only modest performance on entirely unasked opinions.
Value-prompted LLMs align with human value structures and value-behavior relationships, and incorporating human value distributions improves population-level simulations.
Empirical tests on four new frontier LLMs show cooperative equilibria favored in most balanced conditions, with provider identity correlating more strongly with outcomes than model generation.
Monte Carlo simulations of LLM agents confirm that toxic debates take 25% longer to converge, with larger delays in smaller models, and show a first-mover advantage independent of toxicity.
In the Moltbook AI agent community, identity-claim production is highly concentrated among a few frame entrepreneurs, with event-driven attention not translating into broad claim-making.
Avenir-UX automates web usability testing by using GUI-grounded simulation of user behavior to generate standardized reports with SUS, SEQ, and Think Aloud protocols.
citing papers explorer
-
Can AI Reason Like an Urban Planner? Benchmarking Large Language Models Against Professional Judgment
On UPBench, 25 LLMs show a non-monotonic planning curve—strong Remember/Analyze, weak Understand/Evaluate—with four failure modes that support differential, not blanket, AI delegation.
-
Process Matters more than Output for Distinguishing Humans from Machines
A new battery of 30 cognitive tasks demonstrates that process-level behavioral features distinguish humans from frontier AI agents better than performance metrics (mean AUC 0.88), with process-specific fine-tuning improving mimicry but limited cross-task transfer.
-
Language Model Goal Selection Differs from Humans' in a Self-Directed Learning Task
LLMs diverge from human goal selection in self-directed learning by exploiting single solutions with low variability across instances.
-
DoubleAgents: Human-Agent Alignment in a Socially Embedded Workflow
DoubleAgents shows that a distributed-cognition design with coordination agent, dashboard, and policy module increases user comfort and reliance on AI agents for coordination tasks over time.
-
Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators
Length-controlled AlpacaEval applies regression adjustment to remove length bias from LLM auto-evaluations, raising Spearman correlation with Chatbot Arena from 0.94 to 0.98.
-
AI-Augmented Surveys: Leveraging Large Language Models and Surveys for Opinion Prediction
LLM embeddings enable strong retrodiction of masked GSS opinions via cross-validation and external validation but only modest performance on entirely unasked opinions.
-
Teaching Values to Machines: Simulating Human-Like Behavior in LLMs
Value-prompted LLMs align with human value structures and value-behavior relationships, and incorporating human value distributions improves population-level simulations.
-
Evolutionary Dynamics of Cooperation in Next-Generation LLM Agent Systems: A Cross-Provider Empirical Extension
Empirical tests on four new frontier LLMs show cooperative equilibria favored in most balanced conditions, with provider identity correlating more strongly with outcomes than model generation.
-
Beyond Inefficiency: Systemic Costs of Incivility in Multi-Agent Monte Carlo Simulations
Monte Carlo simulations of LLM agents confirm that toxic debates take 25% longer to converge, with larger delays in smaller models, and show a first-mover advantage independent of toxicity.
-
Frame Entrepreneurs in an AI Agent Community: Concentrated Identity-Claim Production on Moltbook
In the Moltbook AI agent community, identity-claim production is highly concentrated among a few frame entrepreneurs, with event-driven attention not translating into broad claim-making.
-
Avenir-UX: Automated UX Evaluation via Simulated Human Web Interaction with GUI Grounding
Avenir-UX automates web usability testing by using GUI-grounded simulation of user behavior to generate standardized reports with SUS, SEQ, and Think Aloud protocols.
- Honeyquest for LLMs: Rethinking Cyber Deception for AI Attackers
- AgentDynEx: Nudging the Mechanics and Dynamics of Multi-Agent Simulations