6 papers
Don't Break the Cache: An Evaluation of Prompt Caching for Long-Horizon Agentic Tasks
Elias Lumer, Faheem Nizar, Akshaya Jangiti +4
Recent advancements in Large Language Model (LLM) agents have enabled complex multi-turn agentic tasks requiring extensive tool calling, where conversations can span dozens of API…
Agent-as-a-Graph: Knowledge Graph-Based Tool and Agent Retrieval for LLM Multi-Agent Systems
Faheem Nizar, Elias Lumer, Anmol Gulati +2
Recent advances in Large Language Model Multi-Agent Systems enable scalable orchestration and retrieval of specialized, parallelized subagents, each equipped with hundreds or thous…
Tool-to-Agent Retrieval: Bridging Tools and Agents for Scalable LLM Multi-Agent Systems
Elias Lumer, Faheem Nizar, Anmol Gulati +2
Recent advances in LLM Multi-Agent Systems enable scalable orchestration of sub-agents, each coordinating hundreds or thousands of tools or Model Context Protocol (MCP) servers. Ho…
Jackal: A Real-World Execution-Based Benchmark Evaluating Large Language Models on Text-to-JQL Tasks
Kevin Frank, Anmol Gulati, Elias Lumer +2
Enterprise teams rely on the Jira Query Language (JQL) to retrieve and filter issues from Jira. Yet, to our knowledge, there is no open, real-world, execution-based benchmark for m…
MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Calling in LLM Agent Multi-Turn Conversations
Elias Lumer, Anmol Gulati, Vamse Kumar Subbiah +2
Large Language Model (LLM) agents have shown significant autonomous capabilities in dynamically searching and incorporating relevant tools or Model Context Protocol (MCP) servers f…
ScaleMCP: Dynamic and Auto-Synchronizing Model Context Protocol Tools for LLM Agents
Elias Lumer, Anmol Gulati, Vamse Kumar Subbiah +2
Recent advancements in Large Language Models (LLMs) and the introduction of the Model Context Protocol (MCP) have significantly expanded LLM agents' capability to interact dynamica…