5 papers
AgentDynEx: Nudging the Mechanics and Dynamics of Multi-Agent Simulations
Jenny Ma, Riya Sahni, Karthik Sreedhar +1
Multi-agent large language model simulations have the potential to model complex human behaviors and interactions. If the mechanics are set up properly, unanticipated and valuable…
JumpStarter: Human-AI Planning with Task-Structured Context Curation
Xuanming Zhang, Sitong Wang, Jenny Ma +3
Human-AI collaboration on complex planning goals is bottlenecked by how LLM interfaces handle context: users must manually curate and re-surface relevant information across long an…
ZORO: Active Rules for Reliable Vibe Coding
Jenny Ma, Sitong Wang, Joshua H. Kung +1
Rules files (e.g., AGENTSmd, CLAUDEmd) are the primary mechanism for human-agent alignment when developers vibe code. However, they remain passive: it is not immediately apparent w…
Simulating Cooperative Prosocial Behavior with Multi-Agent LLMs: Evidence and Mechanisms for AI Agents to Inform Policy Decisions
Karthik Sreedhar, Alice Cai, Jenny Ma +2
Human prosocial cooperation is essential for our collective health, education, and welfare. However, designing social systems to maintain or incentivize prosocial behavior is chall…
DynEx: Dynamic Code Synthesis with Structured Design Exploration for Accelerated Exploratory Programming
Jenny Ma, Karthik Sreedhar, Vivian Liu +4
Recent advancements in large language models have significantly expedited the process of generating front-end code. This allows users to rapidly prototype user interfaces and ideat…