Releases a public trace of coding-agent LLM sessions and characterizes workload features including long loops, context lengths, tool diversity, and cache hit rates for serving optimization.
Patil, Tianjun Zhang, Xin Wang, and Joseph E
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
AgentSeer decomposes agent executions into action graphs and reveals higher, context-specific jailbreak success rates in agentic LLM deployments compared with isolated model evaluations.
The paper introduces a collaborative multi-agent framework for LLMs and applies it conceptually to existing models like Auto-GPT, BabyAGI, and Gorilla through case studies in domains such as courtroom simulations and software development.
citing papers explorer
-
TraceLab: Characterizing Coding Agent Workloads for LLM Serving
Releases a public trace of coding-agent LLM sessions and characterizes workload features including long loops, context lengths, tool diversity, and cache hit rates for serving optimization.
-
Mind the Gap: Evaluating Model- and Agentic-Level Vulnerabilities in LLMs with Action Graphs
AgentSeer decomposes agent executions into action graphs and reveals higher, context-specific jailbreak success rates in agentic LLM deployments compared with isolated model evaluations.
-
Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents
The paper introduces a collaborative multi-agent framework for LLMs and applies it conceptually to existing models like Auto-GPT, BabyAGI, and Gorilla through case studies in domains such as courtroom simulations and software development.