The Bitter Lesson of Tool Calling

Tool use transforms LLMs into agents that act beyond their training data, and for code-capable models, programmatic tool calling extends this further by replacing rigid JSON calls with scripts that chain and parallelize naturally. However, a systematic evaluation of tools as code on an established benchmark across current and prior model generations under real-world task conditions has not been conducted. In this work, we empirically compare programmatic tool calling (PTC) to native JSON tool calling across 14 language models on BFCL v4. In the programmatic tool calling paradigm, tools are exposed as typed Python stubs that the model invokes through code, with execution and results handled in a single agent turn. Programmatic tool calling matches or exceeds native JSON tool calling in 11 of 14 models on BFCL v4, with the GPT-5.6 family achieving a 10.6% improvement over the JSON tool calling baseline. Further, it matches or outperforms baseline in 13 of 14 models under parallel fan-out, and holds stable under context rot conditions where baseline degrades 2.3% on average. Our results demonstrate that programmatic tool calling is a viable and robust alternative to JSON tool calling, with performance tracking model capability across release generations.

Do You Need a Frontier Model as a Citation Verifier? Benchmarking Rubric LLMs for Deep-Research Source Attribution

Reinforcement learning increasingly relies on an LLM judge to score each rubric criterion, and that judge acts as the reward model during training. Before such a signal can be trusted, we need to know how capable the judge must be and how biased it is. We study this calibration question for citation quality in deep-research systems, where a search-grounded LLM must support each claim it writes with a cited source. Citation quality is a structured rubric task in which each attribution-citation pair is judged along two dimensions that require an LLM, source relevance and factual support. On an adversarial long-form benchmark, we score 8 off-the-shelf LLM judges from 3 model families against gold labels over 1,248 rubric decisions, all of which were human-reviewed and 378 of which were hard cases adjudicated from judge disagreements. Cheaper judges remain competitive across both dimensions, with GPT-5-mini attaining the strongest source-relevance pass-class F1 at 0.908 ($κ$=0.636), while on factual support the judges are statistically indistinguishable (overlapping confidence intervals), so no single model dominates. At comparable F1, the judges still differ substantially in pass-rate drift, false positive rate, and false negative rate. Scalar F1 obscures this directional bias, yet it is exactly what a downstream reinforcement learning loop would reinforce. Calibrating the judge is therefore a prerequisite for using citation rubrics as reward signals, and our results show that this calibration does not require the most expensive available model.

Recursive Agent Harnesses

Recursive language models (RLMs) showed that recursion over model calls is an effective strategy for long-context reasoning, and production coding agents have begun to write code that spawns subagents at scale, most recently in Anthropic's dynamic workflows. We name and study the pattern between these two lines of work, where the recursive unit is a full agent harness with filesystem tools, code execution, and planning rather than a model call with no tools. We call this the Recursive Agent Harness (RAH) and frame it as harness recursion, the code-first extension to the model recursion of RLMs. A parent agent generates and runs an executable script that spawns subagent harnesses in parallel for fine-grained workloads and uses structured function calls for small subtasks. We provide a controlled evaluation on long-context reasoning. With the backbone held fixed at GPT-5 to match the published Codex and RLM baselines, RAH improves the Codex coding-agent baseline from 71.75% to 81.36% on Oolong-Synthetic (199 samples, 13 context-length buckets up to 4M tokens), a gain attributable to the harness rather than the model. With a stronger backbone, Claude Sonnet 4.5, the same design reaches 89.77%.

Is Grep All You Need? How Agent Harnesses Reshape Agentic Search

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.

Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents

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.

Agentic Jackal: Live Execution and Semantic Value Grounding for Text-to-JQL

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.

Chronos: Temporal-Aware Conversational Agents with Structured Event Retrieval for Long-Term Memory

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.

Don't Break the Cache: An Evaluation of Prompt Caching for Long-Horizon Agentic Tasks

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 DeepResearchBench, 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 45-80% 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. Our analysis reveals nuanced variations in caching behavior across providers, and we provide practical guidance for implementing prompt caching in production agentic systems.

ScaleMCP: Dynamic and Auto-Synchronizing Model Context Protocol Tools for LLM Agents

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.

Graph RAG-Tool Fusion

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 na\"ive RAG on ToolLinkOS and ToolSandbox benchmarks, respectively (mAP@10). ToolLinkOS dataset is available at https://github.com/EliasLumer/Graph-RAG-Tool-Fusion-ToolLinkOS