4 citations · 6 across the 13 of their papers we have counts for
8 papers · 1 filter
AM-Bench: A Unified Taxonomy and Evaluation Suite for Agentic Misalignment
Eric Zhang, Terry Jingchen Zhang, Chijioke Ugwuanyi +3
As LLM-based agents are deployed with increasing autonomy in real-world environments, a critical failure mode emerges: agentic misalignment, where agents choose harmful actions ove…
When Agents Lie: Premeditation, Persistence, and Exploitation in Repeated Games
Jerick Shi, Terry Jingcheng Zhang, Bernhard Schölkopf +2
As large language models are deployed as autonomous agents that communicate intentions before acting, a critical safety question is whether agents that publicly commit to actions w…
Mechanism Design Is Not Enough: Prosocial Agents for Cooperative AI
Xuanqiang Angelo Huang, Charlie Tharas, Samuele Marro +4
Ensuring that AI agents behave safely and beneficially when interacting with other parties has emerged as one of the central challenges of modern AI safety. While mechanism design,…
Stargazer: A Scalable Model-Fitting Benchmark Environment for AI Agents under Astrophysical Constraints
Xinge Liu, Terry Jingchen Zhang, Bernhard Schölkopf +2
The rise of autonomous AI agents suggests that dynamic benchmark environments with built-in feedback on scientifically grounded tasks are needed to evaluate the capabilities of the…
Evaluating Cooperation in LLM Social Groups through Elected Leadership
Ryan Faulkner, Anushka Deshpande, David Guzman Piedrahita +2
Governing common-pool resources requires agents to develop enduring strategies through cooperation and self-governance to avoid collective failure. While foundation models have sho…
Cheap Talk, Empty Promise: Frontier LLMs easily break public promises for self-interest
Jerick Shi, Terry Jingcheng Zhang, Zhijing Jin +1
Large language models are increasingly deployed as autonomous agents in multi-agent settings where they communicate intentions and take consequential actions with limited human ove…
CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas
Emanuel Tewolde, Xiao Zhang, David Guzman Piedrahita +2
It is increasingly important that LLM agents interact effectively and safely with other goal-pursuing agents, yet, recent works report the opposite trend: LLMs with stronger reason…
From Sycophancy to Deception: A Unified Taxonomy for LLM Spontaneous Misalignment
Jerick Shi, Terry Jingcheng Zhang, Zhijing Jin +1
Large language models (LLMs) could produce systematically misaligned output, from hallucinated citations to strategic deception of evaluators, yet these phenomena are studied by se…