Vamse Kumar Subbiah

Sahil Sen, Elias Lumer, Anmol Gulati et al.

Recent advances in Large Language Models (LLMs) have enabled conversational AI agents to engage in extended multi-turn interactions spanning weeks or months. However, existing memory systems struggle to reason over temporally grounded facts and preferences that evolve across months of interaction and lack effective retrieval strategies for multi-hop, time-sensitive queries over long dialogue histories. We introduce Chronos, a novel temporal-aware memory framework that decomposes raw dialogue into subject-verb-object event tuples with resolved datetime ranges and entity aliases, indexing them in a structured event calendar alongside a turn calendar that preserves full conversational context. At query time, Chronos applies dynamic prompting to generate tailored retrieval guidance for each question, directing the agent on what to retrieve, how to filter across time ranges, and how to approach multi-hop reasoning through an iterative tool-calling loop over both calendars. We evaluate Chronos with 8 LLMs, both open-source and closed-source, on the LongMemEvalS benchmark comprising 500 questions spanning six categories of dialogue history tasks. Chronos Low achieves 92.60% and Chronos High scores 95.60% accuracy, setting a new state of the art with an improvement of 7.67% over the best prior system. Ablation results reveal the events calendar accounts for a 58.9% gain on the baseline while all other components yield improvements between 15.5% and 22.3%. Notably, Chronos Low alone surpasses prior approaches evaluated under their strongest model configurations.

Hailey Onweller, Elias Lumer, Austin Huber et al.

Large language models (LLMs) power deep research agents that synthesize information from hundreds of web sources into cited reports, yet these citations cannot be reliably verified. Current approaches either trust models to self-cite accurately, risking bias, or employ retrieval-augmented generation (RAG) that does not validate source accessibility, relevance, or factual consistency. We introduce the first source attribution evaluation framework that uses a reproducible AST parser to extract and evaluate inline citations from LLM-generated Markdown reports at scale. Unlike methods that verify claims in isolation, our framework closes the loop by retrieving the actual cited content, enabling human or model evaluators to judge each citation against its source. Citations are evaluated along three dimensions. (1) Link Works verifies URL accessibility, (2) Relevant Content measures topical alignment, and (3) Fact Check validates factual accuracy against source content. We benchmark 14 closed-source and open-source LLMs across three evaluation dimensions using rubric-based LLM-as-a-judge evaluators calibrated through human review. Our results reveal that even the strongest frontier models maintain link validity above 94% and relevance above 80%, yet achieve only 39-77% factual accuracy, while fewer than half of open-source models successfully generate cited reports in a one-shot setting. Ablation studies on research depth show that Fact Check accuracy drops by approximately 42% on average across two frontier models as tool calls scale from 2 to 150, demonstrating that more retrieval does not produce more accurate citations. These findings reveal a critical disconnect between surface-level citation quality and factual reliability, and our framework provides the evaluation infrastructure to assess the disconnect.

Elias Lumer, Pradeep Honaganahalli Basavaraju, Myles Mason et al.

Recent developments in retrieval-augmented generation (RAG) for selecting relevant tools from a tool knowledge base enable LLM agents to scale their complex tool calling capabilities to hundreds or thousands of external tools, APIs, or agents-as-tools. However, traditional RAG-based tool retrieval fails to capture structured dependencies between tools, limiting the retrieval accuracy of a retrieved tool's dependencies. For example, among a vector database of tools, a "get stock price" API requires a "stock ticker" parameter from a "get stock ticker" API, and both depend on OS-level internet connectivity tools. In this paper, we address this limitation by introducing Graph RAG-Tool Fusion, a novel plug-and-play approach that combines the strengths of vector-based retrieval with efficient graph traversal to capture all relevant tools (nodes) along with any nested dependencies (edges) within the predefined tool knowledge graph. We also present ToolLinkOS, a new tool selection benchmark of 573 fictional tools, spanning over 15 industries, each with an average of 6.3 tool dependencies. We demonstrate that Graph RAG-Tool Fusion achieves absolute improvements of 71.7% and 22.1% over naïve RAG on ToolLinkOS and ToolSandbox benchmarks, respectively (mAP@10). ToolLinkOS dataset is available at https://github.com/EliasLumer/Graph-RAG-Tool-Fusion-ToolLinkOS

Sahil Sen, Akhil Kasturi, Elias Lumer et al.

Recent advances in Large Language Model (LLM) agents have enabled complex agentic workflows where models autonomously retrieve information, call tools, and reason over large corpora to complete tasks on behalf of users. Despite the growing adoption of retrieval-augmented generation (RAG) in agentic search systems, existing literature lacks a systematic comparison of how retrieval strategy choice interacts with agent architecture and tool-calling paradigm. Important practical dimensions, including how tool outputs are presented to the model and how performance changes when searches must cope with more irrelevant surrounding text, remain under-explored in agent loops. This paper reports an empirical study organized into two experiments. Experiment 1 compares grep and vector retrieval on a 116-question sample from LongMemEval, using a custom agent harness (Chronos) and provider-native CLI harnesses (Claude Code, Codex, and Gemini CLI), for both inline tool results and file-based tool results that the model reads separately. Experiment 2 compares grep-only and vector-only retrieval while progressively mixing in additional unrelated conversation history, so that each query is embedded in more distracting material alongside the passages that matter. Across Chronos and the provider CLIs, grep generally yields higher accuracy than vector retrieval in our comparisons in experiment 1; at the same time, overall scores still depend strongly on which harness and tool-calling style is used, even when the underlying conversation data are the same.

Elias Lumer, Faheem Nizar, Akshaya Jangiti et al.

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 calls with increasingly large context windows. However, although major LLM providers offer prompt caching to reduce cost and latency, its benefits for agentic workloads remain underexplored in the research literature. To our knowledge, no prior work quantifies these cost savings or compares caching strategies for multi-turn agentic tasks. We present a comprehensive evaluation of prompt caching across three major LLM providers (OpenAI, Anthropic, and Google) and compare three caching strategies, including full context caching, system prompt only caching, and caching that excludes dynamic tool results. We evaluate on DeepResearch Bench, a multi-turn agentic benchmark where agents autonomously execute real-world web search tool calls to answer complex research questions, measuring both API cost and time to first token (TTFT) across over 500 agent sessions with 10,000-token system prompts. Our results demonstrate that prompt caching reduces API costs by 41-80% and improves time to first token by 13-31% across providers. We find that strategic prompt cache block control, such as placing dynamic content at the end of the system prompt, avoiding dynamic traditional function calling, and excluding dynamic tool results, provides more consistent benefits than naive full-context caching, which can paradoxically increase latency. An ablation study across prompt sizes (500-50,000 tokens) and tool call counts (3-50) demonstrates universal linear cost and TTFT benefits, after the provider caching token minimum, and reveal provider-specific strategy discrepancies across variants. We provide nuanced discussion and guidance for implementing prompt caching in production agentic systems.

Elias Lumer, Faheem Nizar, Anmol Gulati et al.

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. However, existing retrieval methods typically match queries against coarse agent-level descriptions before routing, which obscures fine-grained tool functionality and often results in suboptimal agent selection. We introduce Tool-to-Agent Retrieval, a unified framework that embeds both tools and their parent agents in a shared vector space and connects them through metadata relationships. By explicitly representing tool capabilities and traversing metadata to the agent level, Tool-to-Agent Retrieval enables granular tool-level or agent-level retrieval, ensuring that agents and their underlying tools or MCP servers are equally represented without the context dilution that arises from chunking many tools together. Evaluating Tool-to-Agent Retrieval across eight embedding models, our approach achieves consistent improvements of 19.4% in Recall@5 and 17.7% in nDCG@5 over previous state-of-the-art agent retrievers on the LiveMCPBench benchmark.

Anmol Gulati, Hariom Gupta, Elias Lumer et al.

Long-horizon AI agents execute complex workflows spanning hundreds of sequential actions, yet a single wrong assumption early on can cascade into irreversible errors. When instructions are incomplete, the agent must decide not only whether to ask for clarification but when, and no prior work measures how clarification value changes over the course of execution. We introduce a forced-injection framework that provides ground-truth clarifications at controlled points in the agent's trajectory across four information dimensions (goal, input, constraint, context), three agent benchmarks, and four frontier models (three per benchmark; one on a single benchmark only; 84 task variants; 6,000+ runs). Counter to the common intuition that "earlier is always better," we find that the value of clarification depends sharply on what information is missing: goal clarification loses nearly all value after 10% of execution (pass@3 drops from 0.78 to baseline), while input clarification retains value through roughly 50%. Deferring any clarification type past mid-trajectory degrades performance below never asking at all. Cross-model Kendall tau correlations (0.78-0.87 among models sharing identical task coverage; 0.34-0.67 across the full 4-model panel) confirm these timing profiles are substantially task-intrinsic. A complementary study of 300 unscripted sessions reveals that no current frontier model asks within the empirically optimal window, with strategies ranging from over-asking (52% of sessions) to never asking at all. These empirical demand curves provide the quantitative foundation that existing theoretical frameworks require but have lacked, and establish concrete design targets for timing-aware clarification policies. Code and data will be publicly released.

Elias Lumer, Vamse Kumar Subbiah, James A. Burke et al.

Recent advancements in tool-equipped Agents (LLMs) have enabled complex tasks like secure database interactions and multi-agent code development. However, scaling tool capacity beyond agent reasoning or model limits remains a challenge. In this paper, we address these challenges by introducing Toolshed Knowledge Bases, a tool knowledge base (vector database) designed to store enhanced tool representations and optimize tool selection for large-scale tool-equipped Agents. Additionally, we propose Advanced RAG-Tool Fusion, a novel ensemble of tool-applied advanced retrieval-augmented generation (RAG) techniques across the pre-retrieval, intra-retrieval, and post-retrieval phases, without requiring model fine-tuning. During pre-retrieval, tool documents are enhanced with key information and stored in the Toolshed Knowledge Base. Intra-retrieval focuses on query planning and transformation to increase retrieval accuracy. Post-retrieval refines the retrieved tool documents and enables self-reflection. Furthermore, by varying both the total number of tools (tool-M) an Agent has access to and the tool selection threshold (top-k), we address trade-offs between retrieval accuracy, agent performance, and token cost. Our approach achieves 46%, 56%, and 47% absolute improvements on the ToolE single-tool, ToolE multi-tool and Seal-Tools benchmark datasets, respectively (Recall@5).

Elias Lumer, Anmol Gulati, Vamse Kumar Subbiah et al.

Recent advancements in Large Language Models (LLMs) and the introduction of the Model Context Protocol (MCP) have significantly expanded LLM agents' capability to interact dynamically with external tools and APIs. However, existing tool selection frameworks do not integrate MCP servers, instead relying heavily on error-prone manual updates to monolithic local tool repositories, leading to duplication, inconsistencies, and inefficiencies. Additionally, current approaches abstract tool selection before the LLM agent is invoked, limiting its autonomy and hindering dynamic re-querying capabilities during multi-turn interactions. To address these issues, we introduce ScaleMCP, a novel tool selection approach that dynamically equips LLM agents with a MCP tool retriever, giving agents the autonomy to add tools into their memory, as well as an auto-synchronizing tool storage system pipeline through CRUD (create, read, update, delete) operations with MCP servers as the single source of truth. We also propose a novel embedding strategy, Tool Document Weighted Average (TDWA), designed to selectively emphasize critical components of tool documents (e.g. tool name or synthetic questions) during the embedding process. Comprehensive evaluations conducted on a created dataset of 5,000 financial metric MCP servers, across 10 LLM models, 5 embedding models, and 5 retriever types, demonstrate substantial improvements in tool retrieval and agent invocation performance, emphasizing ScaleMCP's effectiveness in scalable, dynamic tool selection and invocation.

Elias Lumer, Anmol Gulati, Vamse Kumar Subbiah et al.

Large Language Model (LLM) agents have shown significant autonomous capabilities in dynamically searching and incorporating relevant tools or Model Context Protocol (MCP) servers for individual queries. However, fixed context windows limit effectiveness in multi-turn interactions requiring repeated, independent tool usage. We introduce MemTool, a short-term memory framework enabling LLM agents to dynamically manage tools or MCP server contexts across multi-turn conversations. MemTool offers three agentic architectures: 1) Autonomous Agent Mode, granting full tool management autonomy, 2) Workflow Mode, providing deterministic control without autonomy, and 3) Hybrid Mode, combining autonomous and deterministic control. Evaluating each MemTool mode across 13+ LLMs on the ScaleMCP benchmark, we conducted experiments over 100 consecutive user interactions, measuring tool removal ratios (short-term memory efficiency) and task completion accuracy. In Autonomous Agent Mode, reasoning LLMs achieve high tool-removal efficiency (90-94% over a 3-window average), while medium-sized models exhibit significantly lower efficiency (0-60%). Workflow and Hybrid modes consistently manage tool removal effectively, whereas Autonomous and Hybrid modes excel at task completion. We present trade-offs and recommendations for each MemTool mode based on task accuracy, agency, and model capabilities.

Vishnu Murali, Anmol Gulati, Elias Lumer et al.

Translating natural language into Jira Query Language (JQL) requires resolving ambiguous field references, instance-specific categorical values, and complex Boolean predicates. Single-pass LLMs cannot discover which categorical values (e.g., component names or fix versions) actually exist in a given Jira instance, nor can they verify generated queries against a live data source, limiting accuracy on paraphrased or ambiguous requests. No open, execution-based benchmark exists for mapping natural language to JQL. We introduce Jackal, the first large-scale, execution-based text-to-JQL benchmark comprising 100,000 validated NL-JQL pairs on a live Jira instance with over 200,000 issues. To establish baselines on Jackal, we propose Agentic Jackal, a tool-augmented agent that equips LLMs with live query execution via the Jira MCP server and JiraAnchor, a semantic retrieval tool that resolves natural-language mentions of categorical values through embedding-based similarity search. Among 9 frontier LLMs evaluated, single-pass models average only 43.4% execution accuracy on short natural-language queries, highlighting that text-to-JQL remains an open challenge. The agentic approach improves 7 of 9 models, with a 9.0% relative gain on the most linguistically challenging variant; in a controlled ablation isolating JiraAnchor, categorical-value accuracy rises from 48.7% to 71.7%, with component-field accuracy jumping from 16.9% to 66.2%. Our analysis identifies inherent semantic ambiguities, such as issue-type disambiguation and text-field selection, as the dominant failure modes rather than value-resolution errors, pointing to concrete directions for future work. We publicly release the benchmark, all agent transcripts, and evaluation code to support reproducibility.

Elias Lumer, Alex Cardenas, Matt Melich et al.

Recent advancements in Retrieval-Augmented Generation (RAG) have enabled Large Language Models (LLMs) to access multimodal knowledge bases containing both text and visual information such as charts, diagrams, and tables in financial documents. However, existing multimodal RAG systems rely on LLM-based summarization to convert images into text during preprocessing, storing only text representations in vector databases, which causes loss of contextual information and visual details critical for downstream retrieval and question answering. To address this limitation, we present a comprehensive comparative analysis of two retrieval approaches for multimodal RAG systems, including text-based chunk retrieval (where images are summarized into text before embedding) and direct multimodal embedding retrieval (where images are stored natively in the vector space). We evaluate all three approaches across 6 LLM models and a two multi-modal embedding models on a newly created financial earnings call benchmark comprising 40 question-answer pairs, each paired with 2 documents (1 image and 1 text chunk). Experimental results demonstrate that direct multimodal embedding retrieval significantly outperforms LLM-summary-based approaches, achieving absolute improvements of 13% in mean average precision (mAP@5) and 11% in normalized discounted cumulative gain. These gains correspond to relative improvements of 32% in mAP@5 and 20% in nDCG@5, providing stronger evidence of their practical impact. We additionally find that direct multimodal retrieval produces more accurate and factually consistent answers as measured by LLM-as-a-judge pairwise comparisons. We demonstrate that LLM summarization introduces information loss during preprocessing, whereas direct multimodal embeddings preserve visual context for retrieval and inference.

Faheem Nizar, Elias Lumer, Anmol Gulati et al.

Recent advances in Large Language Model Multi-Agent Systems enable scalable orchestration and retrieval of specialized, parallelized subagents, each equipped with hundreds or thousands of Model Context Protocol (MCP) servers and tools. However, existing agent, MCP, and retrieval methods typically match queries against a single agent description, obscuring fine-grained tool capabilities of each agent, resulting in suboptimal agent selection. We introduce Agent-as-a-Graph retrieval, a knowledge graph retrieval augmented generation approach that represents both tools and their parent agents as nodes and edges in a knowledge graph. During retrieval, i) relevant agents and tool nodes are first retrieved through vector search, ii) we apply a type-specific weighted reciprocal rank fusion (wRRF) for reranking tools and agents, and iii) parent agents are traversed in the knowledge graph for the final set of agents. We evaluate Agent-as-a-Graph on the LiveMCPBenchmark, achieving 14.9% and 14.6% improvements in Recall@5 and nDCG@5 over prior state-of-the-art retrievers, and 2.4% improvements in wRRF optimizations.

Elias Lumer, Matt Melich, Olivia Zino et al.

Recent advancements in Retrieval-Augmented Generation (RAG) have enabled Large Language Models to answer financial questions using external knowledge bases of U.S. SEC filings, earnings reports, and regulatory documents. However, existing work lacks systematic comparison of vector-based and non-vector RAG architectures for financial documents, and the empirical impact of advanced RAG techniques on retrieval accuracy, answer quality, latency, and cost remain unclear. We present the first systematic evaluation comparing vector-based agentic RAG using hybrid search and metadata filtering against hierarchical node-based systems that traverse document structure without embeddings. We evaluate two enhancement techniques applied to the vector-based architecture, i) cross-encoder reranking for retrieval precision, and ii) small-to-big chunk retrieval for context completeness. Across 1,200 SEC 10-K, 10-Q, and 8-K filings on a 150-question benchmark, we measure retrieval metrics (MRR, Recall@5), answer quality through LLM-as-a-judge pairwise comparisons, latency, and preprocessing costs. Vector-based agentic RAG achieves a 68% win rate over hierarchical node-based systems with comparable latency (5.2 compared to 5.98 seconds). Cross-encoder reranking achieves a 59% absolute improvement at optimal parameters (10, 5) for MRR@5. Small-to-big retrieval achieves a 65% win rate over baseline chunking with only 0.2 seconds additional latency. Our findings reveal that applying advanced RAG techniques to financial Q&A systems improves retrieval accuracy, answer quality, and has cost-performance tradeoffs to be considered in production.

Kevin Frank, Anmol Gulati, Elias Lumer et al.

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 mapping natural language queries to JQL. We introduce Jackal, a novel, large-scale text-to-JQL benchmark comprising 100,000 natural language (NL) requests paired with validated JQL queries and execution-based results on a live Jira instance with over 200,000 issues. To reflect real-world usage, each JQL query is associated with four types of user requests: (i) Long NL, (ii) Short NL, (iii) Semantically Similar, and (iv) Semantically Exact. We release Jackal, a corpus of 100,000 text-to-JQL pairs, together with an execution-based scoring toolkit, and a static snapshot of the evaluated Jira instance for reproducibility. We report text-to-JQL results on 23 Large Language Models (LLMs) spanning parameter sizes, open and closed source models, across execution accuracy, exact match, and canonical exact match. In this paper, we report results on Jackal-5K, a 5,000-pair subset of Jackal. On Jackal-5K, the best overall model (Gemini 2.5 Pro) achieves only 60.3% execution accuracy averaged equally across four user request types. Performance varies significantly across user request types: (i) Long NL (86.0%), (ii) Short NL (35.7%), (iii) Semantically Similar (22.7%), and (iv) Semantically Exact (99.3%). By benchmarking LLMs on their ability to produce correct and executable JQL queries, Jackal exposes the limitations of current state-of-the-art LLMs and sets a new, execution-based challenge for future research in Jira enterprise data.