8 papers
SCARCE: Emergent Institutions in Long-Horizon Multi-Agent Coding Systems
Abhinav Kumar, Rediet Abebe, Eugene Bagdasarian +1
As autonomous agents become widely deployed, coordinating access to shared computing resources and services will become increasingly important. Recent incidents have already reveal…
DeFiFlowBench: Benchmarking and Improving Safe Executability in Natural-Language DeFi Workflow Synthesis
Abhinav Rajeev Kumar, Harshit Arora, Varun Singh +1
A structurally valid DeFi workflow can still authorize a costly trade. We introduce DeFiFlowBench, a benchmark of 207 team-authored prompts for natural-language DeFi workflow synth…
PiSAs: Benchmarking Contextual Integrity in Multi-User Agentic Systems
Shubham Gupta, Nazanin Mohammadi Sepahvand, Abhinav Kumar +6
As LLM agents evolve from single-user assistants into shared organizational infrastructure, new privacy risks emerge: inappropriate information may not only be exposed through outp…
Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems
Mason Nakamura, Abhinav Kumar, Saswat Das +5
Multi-agent systems, where LLM agents communicate through free-form language, enable sophisticated coordination for solving complex cooperative tasks. This surfaces a unique safety…
Terrarium: Revisiting the Blackboard for Multi-Agent Safety, Privacy, and Security Studies
Mason Nakamura, Abhinav Kumar, Saaduddin Mahmud +3
A multi-agent system (MAS) powered by large language models (LLMs) can automate tedious user tasks such as meeting scheduling that requires inter-agent collaboration. LLMs enable n…
Throttling Web Agents Using Reasoning Gates
Abhinav Kumar, Jaechul Roh, Ali Naseh +2
AI web agents use Internet resources at far greater speed, scale, and complexity -- changing how users and services interact. Deployed maliciously or erroneously, these agents coul…
Network-Level Prompt and Trait Leakage in Local Research Agents
Hyejun Jeong, Mohammadreza Teymoorianfard, Abhinav Kumar +2
We show that Web and Research Agents (WRAs) -- language-model-based systems that investigate complex topics on the Internet -- are vulnerable to inference attacks by passive networ…
OverThink: Slowdown Attacks on Reasoning LLMs
Abhinav Kumar, Jaechul Roh, Ali Naseh +4
A reasoning language model (RLM) generates costly reasoning tokens, often hidden from the users, that help it excel at many tasks. Our Overthink attack targets RLM-based applicatio…