LLM Tool Use

Heavy supervised fine-tuning on a target domain can strongly suppress capabilities that were present in the base model. We study this phenomenon in formal mathematics using Goedel-Prover-V2, an open-source model heavily trained on 1.8 million formal-math examples. After domain specialization, the model almost completely loses its ability to produce valid tool calls, even when explicitly instructed to use tools, dropping from 89.4% function-calling accuracy in the base model to nearly 0%. We ask whether this agentic collapse is permanent or instead reversible. To answer this question, we fine-tune the specialized model on a small amount of Lean-specific tool-use data. Remarkably, as few as 100 agentic traces are sufficient to restore strong tool-calling behavior. Importantly, this recovery is not the result of reward hacking or benchmark-specific optimization: the recovery data is entirely drawn from the Lean setting, where the model uses natural-language queries to search the Mathlib library for relevant theorems and lemmas, yet the regained capability transfers well beyond that domain. In particular, these same 100 Lean-specific traces improve performance on the Berkeley Function Calling Leaderboard from near zero to 83.8%, approaching the base model's 89.4% despite the mismatch in task distribution and protocol. The recovered capability is also practically useful in-domain. On ProofNet, pass@32 improves from 21.51% to 25.81%. Together, these results show that heavy domain supervised fine-tuning can suppress general tool-use ability without permanently erasing it, and that a small amount of domain-specific agentic data can awaken dormant tool-use capabilities.

Computer-Aided Design (CAD) is an expert-level task that relies on long-horizon reasoning and coherent modeling actions. Large Language Models (LLMs) have shown remarkable advancements in enabling language agents to tackle real-world tasks. Notably, there has been no investigation into how tool-using LLMs optimally interact with CAD engines, hindering the emergence of LLM-based agentic text-to-CAD modeling systems. We propose ToolCAD, a novel agentic CAD framework deploying LLMs as tool-using agents for text-to-CAD generation. Furthermore, we introduce an interactive CAD modeling gym to rollout reasoning and tool-augmented interaction trajectories with the CAD engine, incorporating hybrid feedback and human supervision. Meanwhile, an end-to-end post-training strategy is presented to enable the LLM agent to elicit refined CAD Modeling Chain of Thought (CAD-CoT) and evolve into proficient CAD tool-using agents via online curriculum reinforcement learning. Our findings demonstrate ToolCAD fills the gap in adopting and training open-source LLMs for CAD tool-using agents, enabling them to perform comparably to proprietary models, paving the way for more accessible and robust autonomous text-to-CAD modeling systems.

Tool learning has emerged as a promising paradigm for large language models (LLMs) to address real-world challenges. Due to the extensive and irregularly updated number of tools, tool retrieval for selecting the desired tool subset is essential. However, current tool retrieval methods are usually based on academic benchmarks containing overly detailed instructions (e.g., specific API names and parameters), while real-world instructions are more vague. Such a discrepancy would hinder the tool retrieval in real-world applications. In this paper, we first construct a new benchmark, VGToolBench, to simulate human vague instructions. Based on this, we conduct a series of preliminary analyses and find that vague instructions indeed damage the performance of tool retrieval. To this end, we propose a simple-yet-effective Tool Retrieval Bridge (TRB) approach to boost the performance of tool retrieval for vague instructions. The principle of TRB is to introduce a bridge model to rewrite the vague instructions into more specific ones and alleviate the gap between vague instructions and retriever preferences.We conduct extensive experiments under multiple commonly used retrieval settings, and the results show that TRB effectively mitigates the ambiguity of vague instructions while delivering consistent and substantial improvements across all baseline retrievers. For example, with the help of TRB, BM25 achieves a relative improvement of up to 111.51%, i.e., increasing the average NDCG score from 9.73 to 19.59. The source code and models are publicly available at https://github.com/kfchenhn/TRB.

Corpus linguistics has traditionally relied on human researchers to formulate hypotheses, construct queries, and interpret results - a process demanding specialized technical skills and considerable time. We propose Agent-Driven Corpus Linguistics, an approach in which a large language model (LLM), connected to a corpus query engine via a structured tool-use interface, takes over the investigative cycle: generating hypotheses, querying the corpus, interpreting results, and refining analysis across multiple rounds. The human researcher sets direction and evaluates final output. Unlike unconstrained LLM generation, every finding is anchored in verifiable corpus evidence. We treat this not as a replacement for the corpus-based/corpus-driven distinction but as a complementary dimension: it concerns who conducts the inquiry, not the epistemological relationship between theory and data. We demonstrate the framework by linking an LLM agent to a CQP-indexed Gutenberg corpus (5 million tokens) via the Model Context Protocol (MCP). Given only "investigate English intensifiers," the agent identified a diachronic relay chain (so+ADJ > very > really), three pathways of semantic change (delexicalization, polarity fixation, metaphorical constraint), and register-sensitive distributions. A controlled baseline experiment shows that corpus grounding contributes quantification and falsifiability that the model cannot produce from training data alone. To test external validity, the agent replicated two published studies on the CLMET corpus (40 million tokens) - Claridge (2025) and De Smet (2013) - with close quantitative agreement. Agent-driven corpus research can thus produce empirically grounded findings at machine speed, lowering the technical barrier for a broader range of researchers.

Large language models (LLMs) have been incorporated into numerous industrial applications. Meanwhile, a vast array of API assets is scattered across various functions in the financial domain. An online financial question-answering system can leverage both LLMs and private APIs to provide timely financial analysis and information. The key is equipping the LLM model with function calling capability tailored to a financial scenario. However, a generic LLM requires customized financial APIs to call and struggles to adapt to the financial domain. Additionally, online user queries are diverse and contain out-of-distribution parameters compared with the required function input parameters, which makes it more difficult for a generic LLM to serve online users. In this paper, we propose a data-driven pipeline to enhance function calling in LLM for our online, deployed financial QA, comprising dataset construction, data augmentation, and model training. Specifically, we construct a dataset based on a previous study and update it periodically, incorporating queries and an augmentation method named AugFC. The addition of user query-related samples will exploit our financial toolset in a data-driven manner, and AugFC explores the possible parameter values to enhance the diversity of our updated dataset. Then, we train an LLM with a two-step method, which enables the use of our financial functions. Extensive experiments on existing offline datasets, as well as the deployment of an online scenario, illustrate the superiority of our pipeline. The related pipeline has been adopted in the financial QA of YuanBao\footnote{https://yuanbao.tencent.com/chat/}, one of the largest chat platforms in China.

Recent advances in large language models have led to strong performance on reasoning and environment-interaction tasks, yet their ability for creative problem-solving remains underexplored. We study this capability through the lens of creative tool use, where a model repurposes available objects by reasoning about their affordances and attributes rather than relying on canonical usage. As a first step, we introduce CreativityBench, a benchmark for evaluating affordance-based creativity in LLMs. To this end, we build a large-scale affordance knowledge base (KB) with 4K entities and 150K+ affordance annotations, explicitly linking objects, parts, attributes, and actionable uses. Building on this KB, we generate 14K grounded tasks that require identifying non-obvious yet physically plausible solutions under constraints. Evaluations across 10 state-of-the-art LLMs, including closed and open-source models, show that models can often select a plausible object, but fail to identify the correct parts, their affordances, and the underlying physical mechanism needed to solve the task, leading to a significant drop in performance. Furthermore, improvements from model scaling quickly saturate, strong general reasoning does not reliably translate to creative affordance discovery, and common inference-time strategies such as Chain-of-Thought yield limited gains. These results suggest that creative tool use remains a major challenge for current models, and that CreativityBench provides a useful testbed for studying this missing dimension of intelligence, with potential implications for planning and reasoning modules in future agents.

Multi-turn tool calling is essential for LLMs to function as autonomous agents, yet synthesizing the training data required for these capabilities remains a fundamental challenge. Existing synthetic data generation pipelines often produce unrealistic dialogues for two reasons: they chain tools that are only superficially compatible rather than aligned with meaningful user tasks, and they generate dialogues in one shot, which often introduces arguments that were neither provided by the user nor produced by prior tool calls. These issues also lead to a severe underrepresentation of multi-step tool interactions. We introduce ToolWeave, a structured framework for synthesizing realistic multi-turn tool-calling dialogues. ToolWeave support realistic multi-step workflows (or tool sequences) by constructing tools with built-in dependencies and filters the workflows based on alignment with user goals. It reduces parameter hallucination by using a fine-grained planning stage that explicitly tracks parameter provenance. As a result, ToolWeave-generated synthetic dialogues contain more multi-step tool interactions (45%) and fewer hallucinations in parameters and tool names. Consequently, LLMs fine-tuned on ToolWeave consistently outperform those fine-tuned on prior datasets across three public benchmarks. Notably, Llama-3.1-70B fine-tuned on ToolWeave achieves 39.75% on BFCL-V3 multi-turn, compared to 23.50% when fine-tuned on SOTA ToolFlow data.

The use of knowledge graphs for grounding agents in real-world Q&A applications has become increasingly common. Answering complex queries often requires multi-hop reasoning and the ability to navigate vast relational structures. Standard approaches rely on prompting techniques that steer large language models to reason over raw graph context, or retrieval-augmented generation pipelines where relevant subgraphs are injected into the context. These, however, face severe limitations with enterprise-scale KGs that cannot fit in even the largest context windows available today. We present GraphWalk, a problem-agnostic, training-free, tool-based framework that allows off-the-shelf LLMs to reason through sequential graph navigation, dramatically increasing performance across different tasks. Unlike task-specific agent frameworks that encode domain knowledge into specialized tools, GraphWalk equips the LLM with a minimal set of orthogonal graph operations sufficient to traverse any graph structure. We evaluate whether models equipped with GraphWalk can compose these operations into correct multi-step reasoning chains, where each tool call represents a verifiable step creating a transparent execution trace. We first demonstrate our approach on maze traversal, a problem non-reasoning models are completely unable to solve, then present results on graphs resembling real-world enterprise knowledge graphs. To isolate structural reasoning from world knowledge, we evaluate on entirely synthetic graphs with random, non-semantic labels. Our benchmark spans 12 query templates from basic retrieval to compound first-order logic queries. Results show that tool-based traversal yields substantial and consistent gains over in-context baselines across all model families tested, with gains becoming more pronounced as scale increases, precisely where in-context approaches fail catastrophically.

Large language models are increasingly being deployed as autonomous agents yet their real world effectiveness depends on reliable tools for information retrieval, computation and external action. Existing studies remain fragmented across tasks, tool types, and training settings, lacking a unified view of how tool-use methods differ and evolve. This paper organizes the literature into three paradigms: prompting as plug-and-play, supervised tool learning and reward-driven tool policy learning, analyzes their methods, strengths and failure modes, reviews the evaluation landscape and highlights key challenges, aiming to address this fragmentation and provide a more structured evolutionary view of agentic tool use.

We present ATLAS-RTC, a runtime control system for autoregressive language models that enforces structured output during decoding. ATLAS-RTC monitors generation at each step, detects drift from output contracts using lightweight signals, and applies targeted interventions such as biasing, masking, and rollback. Unlike post-hoc validation or static constrained decoding, it operates in a closed loop, enabling correction before errors materialize. Across structured generation and tool-calling tasks, ATLAS-RTC improves first-attempt success rates by 20 to 37.8 percentage points, with up to 88% latency reduction in failure-dominated settings. Results show that many failures arise from decoding artifacts rather than task misunderstanding, motivating runtime control as a distinct layer in LLM systems.

LLMs have become deeply embedded in knowledge work, raising concerns about growing dependency and the potential undermining of human skills. To investigate the pervasiveness of LLMs in work practices, we conducted a four-day diary study with frequent LLM users (N=10), observing how knowledge workers responded to a temporary withdrawal of LLMs. Our findings show how LLM withdrawal disrupted participants' workflows by identifying gaps in task execution, how self-directed work led participants to reclaim professional values, and how everyday practices revealed the extent to which LLM use had become inescapably normative. Conceptualizing LLMs as infrastructural to contemporary knowledge work, this research contributes empirical insights into the often invisible role of LLMs and proposes value-driven appropriation as an approach to supporting professional values in the current LLM-pervasive work environment.

Graphic design is a creative and innovative process that plays a crucial role in applications such as e-commerce and advertising. However, developing an automated design system that can faithfully translate user intentions into editable design files remains an open challenge. Although recent studies have leveraged powerful text-to-image models and MLLMs to assist graphic design, they typically simplify professional workflows, resulting in limited flexibility and intuitiveness. To address these limitations, we propose PSDesigner, an automated graphic design system that emulates the creative workflow of human designers. Building upon multiple specialized components, PSDesigner collects theme-related assets based on user instructions, and autonomously infers and executes tool calls to manipulate design files, such as integrating new assets or refining inferior elements. To endow the system with strong tool-use capabilities, we construct a design dataset, CreativePSD, which contains a large amount of high-quality PSD design files annotated with operation traces across a wide range of design scenarios and artistic styles, enabling models to learn expert design procedures. Extensive experiments demonstrate that PSDesigner outperforms existing methods across diverse graphic design tasks, empowering non-specialists to conveniently create production-quality designs.

Large language models and autonomous agents are increasingly explored for EDA automation, but many existing integrations still rely on script-level or request-level interactions, which makes it difficult to preserve tool state and support iterative optimization in real production-oriented environments. In this work, we present FluxEDA, a unified and stateful infrastructure substrate for agentic EDA. FluxEDA introduces a managed gateway-based execution interface with structured request and response handling. It also maintains persistent backend instances. Together, these features allow upper-layer agents and programmable clients to interact with heterogeneous EDA tools through preserved runtime state, rather than through isolated shell invocations. We evaluate the framework using two representative commercial backend case studies: automated post-route timing ECO and standard-cell sub-library optimization. The results show that FluxEDA can support multi-step analysis and optimization over real tool contexts, including state reuse, rollback, and coordinated iterative execution. These findings suggest that a stateful and governed infrastructure layer is a practical foundation for agent-assisted EDA automation.

This paper introduces FinMCP-Bench, a novel benchmark for evaluating large language models (LLMs) in solving real-world financial problems through tool invocation of financial model context protocols. FinMCP-Bench contains 613 samples spanning 10 main scenarios and 33 sub-scenarios, featuring both real and synthetic user queries to ensure diversity and authenticity. It incorporates 65 real financial MCPs and three types of samples, single tool, multi-tool, and multi-turn, allowing evaluation of models across different levels of task complexity. Using this benchmark, we systematically assess a range of mainstream LLMs and propose metrics that explicitly measure tool invocation accuracy and reasoning capabilities. FinMCP-Bench provides a standardized, practical, and challenging testbed for advancing research on financial LLM agents.

Tool-use capabilities are vital for Large Language Models (LLMs) in finance, a domain characterized by massive investment targets and data-intensive inquiries. However, existing data synthesis methods typically rely on a reverse synthesis paradigm, generating user queries from pre-sampled tools. This approach inevitably introduces artificial explicitness, yielding queries that fail to capture the implicit, event-driven nature of real-world needs. Moreover, its reliance on static tool sets overlooks the dynamic retrieval process required to navigate massive tool spaces. To address these challenges, we introduce FinToolSyn, a forward synthesis framework designed to generate high-quality financial dialogues. Progressing from persona instruction and atomic tool synthesis to dynamic retrieval dialogue generation, our pipeline constructs a repository of 43,066 tools and synthesizes over 148k dialogue instances, incorporating dynamic retrieval to emulate the noisy candidate sets typical of massive tool spaces. We also establish a dedicated benchmark to evaluate tool-calling capabilities in realistic financial scenarios. Extensive experiments demonstrate that models trained on FinToolSyn achieve a 21.06% improvement, providing a robust foundation for tool learning in financial scenarios.

Tool use enables large language models (LLMs) to access external information, invoke software systems, and act in digital environments beyond what can be solved from model parameters alone. Early research mainly studied whether a model could select and execute a correct single tool call. As agent systems evolve, however, the central problem has shifted from isolated invocation to multi-tool orchestration over long trajectories with intermediate state, execution feedback, changing environments, and practical constraints such as safety, cost, and verifiability. We comprehensively review recent progress in multi-tool LLM agents and analyzes the state of the art in this rapidly developing area. First, we unify task formulations and distinguish single-call tool use from long-horizon orchestration. Then, we organize the literature around six core dimensions: inference-time planning and execution, training and trajectory construction, safety and control, efficiency under resource constraints, capability completeness in open environments, and benchmark design and evaluation. We further summarize representative applications in software engineering, enterprise workflows, graphical user interfaces, and mobile systems. Finally, we discuss major challenges and outline future directions for building reliable, scalable, and verifiable multi-tool agents.

Tool-using large language model (LLM) agents often face a fundamental tension between answer quality and execution cost. Fixed workflows are stable but inflexible, while free-form multi-step reasoning methods such as ReAct may improve task performance at the expense of excessive tool calls, longer trajectories, higher token consumption, and increased latency. In this paper, we study agent orchestration as an explicit decision problem rather than leaving it entirely to prompt-level behavior. We propose a utility-guided orchestration policy that selects among actions such as respond, retrieve, tool call, verify, and stop by balancing estimated gain, step cost, uncertainty, and redundancy. Our goal is not to claim universally best task performance, but to provide a controllable and analyzable policy framework for studying quality-cost trade-offs in tool-using LLM agents. Experiments across direct answering, threshold control, fixed workflows, ReAct, and several policy variants show that explicit orchestration signals substantially affect agent behavior. Additional analyses on cost definitions, workflow fairness, and redundancy control further demonstrate that lightweight utility design can provide a defensible and practical mechanism for agent control.

Large Language Models (LLMs) with tool-calling capabilities have demonstrated remarkable potential in executing complex tasks through external tool integration. The Model Context Protocol (MCP) has emerged as a standardized framework for connecting LLMs to diverse toolsets, with individual MCP servers potentially exposing dozens to hundreds of tools. However, current implementations face a critical scalability challenge: providing all available tools to the LLM context results in substantial token overhead, increased costs, reduced accuracy, and context window constraints. We present a semantic tool discovery architecture that addresses these challenges through vector-based retrieval. Our approach indexes MCP tools using dense embeddings that capture semantic relationships between tool capabilities and user intent, dynamically selecting only the most relevant tools (typically 3-5) rather than exposing the entire tool catalog (50-100+). Experimental results demonstrate a 99.6% reduction in tool-related token consumption with a hit rate of 97.1% at K=3 and an MRR of 0.91 on a benchmark of 140 queries across 121 tools from 5 MCP servers, with sub-100ms retrieval latency. Contributions include: (1) a semantic indexing framework for MCP tools, (2) a dynamic tool selection algorithm based on query-tool similarity, (3) comprehensive evaluation demonstrating significant efficiency and accuracy improvements, and (4) extensibility to multi-agent and cross-organizational tool discovery.

LLM-powered agents execute tasks through a sequential loop of model generation and tool execution. Today's serving systems serialize this loop, leaving tool latency exposed on the task critical path. This paper presents PASTE, a tool-aware agent-serving system that predicts concrete future tool invocations from recurring agent patterns and executes them speculatively while the LLM is still generating. PASTE isolates speculative results until confirmed by the LLM and jointly schedules tool execution and returning LLM sessions to avoid shifting bottlenecks to the GPU. Across deep research, coding, and scientific-agent workloads, PASTE reduces average task completion time by 43.5% and lowers observed tool latency by 1.8x.

The evolving LLM landscape requires capabilities beyond simple text generation, prioritizing multi-step reasoning, long-context understanding, and agentic workflows. This shift challenges existing models in enterprise environments, especially in Korean-language and domain-specific scenarios where scaling is insufficient. We introduce Mi:dm K 2.5 Pro, a 32B parameter flagship LLM designed to address enterprise-grade complexity through reasoning-focused optimization. Our methodology builds a robust data foundation via a quality-centric curation pipeline utilizing abstract syntax tree (AST) analysis for code, gap-filling synthesis for mathematics, and an LLM-based quality evaluator. Pre-training scales the model via layer-predictor-based Depth Upscaling (DuS) and a progressive strategy supporting a 128K token context window. Post-training introduces a specialized multi-stage pipeline, including Reasoning SFT, model merging, and asynchronous reinforcement learning (RL), to develop complex problem-solving skills. "Fusion Training" then rebalances these capabilities with conversational fluency, consistent response styling, and reliable tool-use. The evaluations show that Mi:dm K 2.5 Pro achieves competitive performance against leading global and domestic models. In addition, it sets state-of-the-art results on Korean-specific benchmarks, showcasing deep linguistic and cultural understanding. Finally, Responsible AI evaluations validate safety against attacks, ensuring a secure profile for deployment with a balance of harmlessness and responsiveness.

Tool-augmented large language models (LLMs) must tightly couple multi-step reasoning with external actions, yet existing benchmarks often confound this interplay with complex environment dynamics, memorized knowledge or dataset contamination. In this paper, we introduce ZebraArena, a procedurally generated diagnostic environment for studying reasoning-action coupling in tool-augmented LLMs, with controllable difficulty and a knowledge-minimal design, which limits gains from memorization or dataset contamination. Each task in ZebraArena requires a set of critical information which is available only through targeted tool use, yielding an interpretable interface between external information acquisition and deductive reasoning. This design provides deterministic evaluation via unique solutions, and a theoretical optimal query count for measuring efficient tool use. We show that ZebraArena requires a combination of in-depth reasoning and accurate external tool calling, which remains a challenge as frontier reasoning models such as GPT-5 and Gemini 2.5 Pro only achieves 60% accuracy on the hard instances. We also observe a persistent gaps between theoretical optimality and practical tool usage. For example, GPT-5 uses 70-270% more tool calls than the theoretical optimum. We highlight the key findings in our evaluation, and hope ZebraArena stimulates further research on the interplay between internal reasoning and external action.

Solving problems through tool use under explicit constraints constitutes a highly challenging yet unavoidable scenario for large language models (LLMs), requiring capabilities such as function calling, instruction following, and self-refinement. However, progress has been hindered by the absence of dedicated evaluations. To address this, we introduce CCTU, a benchmark for evaluating LLM tool use under complex constraints. CCTU is grounded in a taxonomy of 12 constraint categories spanning four dimensions (i.e., resource, behavior, toolset, and response). The benchmark comprises 200 carefully curated and challenging test cases across diverse tool-use scenarios, each involving an average of seven constraint types and an average prompt length exceeding 4,700 tokens. To enable reliable evaluation, we develop an executable constraint validation module that performs step-level validation and enforces compliance during multi-turn interactions between models and their environments. We evaluate nine state-of-the-art LLMs in both thinking and non-thinking modes. Results indicate that when strict adherence to all constraints is required, no model achieves a task completion rate above 20%. Further analysis reveals that models violate constraints in over 50% of cases, particularly in the resource and response dimensions. Moreover, LLMs demonstrate limited capacity for self-refinement even after receiving detailed feedback on constraint violations, highlighting a critical bottleneck in the development of robust tool-use agents. To facilitate future research, we release the data and code.

The growth of online platforms and user content requires strong content moderation systems that can handle complex inputs from various media types. While large language models (LLMs) are effective, their high computational cost and latency present significant challenges for scalable deployment. To address this, we introduce Tool-MCoT, a small language model (SLM) fine-tuned for content safety moderation leveraging external framework. By training our model on tool-augmented chain-of-thought data generated by LLM, we demonstrate that the SLM can learn to effectively utilize these tools to improve its reasoning and decision-making. Our experiments show that the fine-tuned SLM achieves significant performance gains. Furthermore, we show that the model can learn to use these tools selectively, achieving a balance between moderation accuracy and inference efficiency by calling tools only when necessary.

Large language models (LLMs) are increasingly integrated into design and development workflows, yet decisions about their use are rarely binary or purely technical. We report findings from a constructivist grounded theory study based on interviews with 33 designers and developers across three large technology organisations. Rather than evaluating LLMs solely by capability, participants reasoned about the role an LLM could occupy within a workflow and how that role would interact with existing structures of responsibility and organisational accountability. When LLMs were framed as tools under clear human control, their use was typically acceptable and could be integrated within existing governance structures. When framed as teammates with shared or ambiguous agency, practitioners expressed hesitation, particularly when responsibility for outcomes could not be clearly justified. At the same time, participants also described productive teammate configurations in which LLMs supported collaborative reasoning while remaining embedded within explicit oversight structures. We identify tool and teammate framings as recurring ways in which designers and developers position LLMs relative to human work and present an analytic rubric describing how role framing shapes decision authority, accountability ownership, oversight strategies, and organisational acceptability. By foregrounding design-time reasoning, this work reframes To LLM or Not to LLM as a sociotechnical positioning problem that emerges during system design rather than during post-deployment evaluation.

Semantic routers in LLM inference gateways select tools in the critical request path, where every millisecond of added latency compounds across millions of requests. We propose Outcome-Aware Tool Selection (OATS), which interpolates tool embeddings toward the centroid of queries where they historically succeed -- an offline process that adds no parameters, latency, or GPU cost at serving time. On MetaTool (199tools, 4,287queries), this improves NDCG@5 from 0.869 to 0.940; on ToolBench (2,413~APIs), from 0.834 to 0.848. We also evaluate two learned extensions: a 2,625-parameter MLP re-ranker and a 197K-parameter contrastive adapter. The MLP re-ranker hurts or matches baseline when outcome data is sparse relative to the tool set; the contrastive adapter provides comparable gains on MetaTool (NDCG@5: 0.931). All methods are evaluated on the same held-out 30% test split. The practical takeaway is to start with the zero-cost refinement and add learned components only when data density warrants it. All mechanisms run within single-digit millisecond CPU budgets.

Tool use has become central to modern LLM agents, yet interface design is rarely isolated as an experimental variable. This paper studies whether schema based tool contracts and structured validation diagnostics improve reliability under strict interaction budgets. We evaluate three conditions that preserve identical tool semantics and information content: free form documentation, JSON Schema specifications, and JSON Schema with structured diagnostics. We implement a deterministic software engineering sandbox with logs, metrics, configurations, and repository tasks, and evaluate a fully crossed pilot with one open local model, three seeds, three interface conditions, and four budgets. We report end task success, interface misuse, execution failures, semantic misuse, recovery behavior, and overhead. In this pilot, success remains zero across conditions, while schema conditions reduce interface misuse but not semantic misuse. The evidence supports a precise interpretation that interface formalization improves contract adherence, but semantic action quality and timeout sensitive tasks remain dominant bottlenecks under constrained local inference.

Tool-calling empowers Large Language Models (LLMs) to interact with external environments. However, current methods often struggle to handle massive and noisy candidate tools in long-context tool-calling tasks, limiting their real-world application. To this end, we propose Tool-DC, a Divide-and-Conquer framework for boosting tool-calling performance of LLMs. The core of Tool-DC is to reduce the reasoning difficulty and make full use of self-reflection ability of LLMs via a "Try-Check-Retry" paradigm. Specifically, Tool-DC involves two variants: 1) the training-free Tool-DC (TF), which is plug-and-play and flexible; 2) the training-based Tool-DC (TB), which is more inference-efficient. Extensive experiments show that both Tool-DC methods outperform their counterparts by a clear margin. Tool-DC (TF) brings up to +25.10% average gains against the baseline on BFCL and ACEBench benchmarks, while Tool-DC (TB) enables Qwen2.5-7B to achieve comparable or even better performance than proprietary LLMs, e.g., OpenAI o3 and Claude-Haiku-4.5.

Recent work synthesizes agentic tasks for post-training tool-using LLMs, yet robust generalization under shifts in tasks and toolsets remains an open challenge. We trace this brittleness to insufficient diversity in synthesized tasks. Scaling diversity is difficult because training requires tasks to remain executable and verifiable, while generalization demands coverage of diverse tool types, toolset combinations, and heterogeneous tool-use patterns. We propose DIVE, an evidence-driven recipe that inverts synthesis order, executing diverse, real-world tools first and reverse-deriving tasks strictly entailed by the resulting traces, thereby providing grounding by construction. DIVE scales structural diversity along two controllable axes, tool-pool coverage and per-task toolset variety, and an Evidence Collection--Task Derivation loop further induces rich multi-step tool-use patterns across 373 tools in five domains. Training Qwen3-8B on DIVE data (48k SFT + 3.2k RL) improves by +22 average points across 9 OOD benchmarks and outperforms the strongest 8B baseline by +68. Remarkably, controlled scaling analysis reveals that diversity scaling consistently outperforms quantity scaling for OOD generalization, even with 4x less data.

This technical report presents Sabiá-4 and Sabiazinho-4, a new generation of Portuguese language models with a focus on Brazilian Portuguese language. The models were developed through a four-stage training pipeline: continued pre-training on Portuguese and Brazilian legal corpora, long-context extension to 128K tokens, supervised fine-tuning on instruction data spanning chat, code, legal tasks, and function calling, and preference alignment. We evaluate the models on six benchmark categories: conversational capabilities in Brazilian Portuguese, knowledge of Brazilian legislation, long-context understanding, instruction following, standardized exams, and agentic capabilities including tool use and web navigation. Results show that Sabiá-4 and Sabiazinho-4 achieve a favorable cost-performance trade-off compared to other models, positioning them in the upper-left region of the pricing-accuracy chart. The models show improvements over previous generations in legal document drafting, multi-turn dialogue quality, and agentic task completion.

Large Language Model (LLM) has exhibited strong reasoning ability in text-based contexts across various domains, yet the limitation of context window poses challenges for the model on long-range inference tasks and necessitates a memory storage system. While many current storage approaches have been proposed with episodic notes and graph representations of memory, retrieval methods still primarily rely on predefined workflows or static similarity top-k over embeddings. To address this inflexibility, we introduced a novel tool-augmented autonomous memory retrieval framework (TA-Mem), which contains: (1) a memory extraction LLM agent which is prompted to adaptively chuck an input into sub-context based on semantic correlation, and extract information into structured notes, (2) a multi-indexed memory database designed for different types of query methods including both key-based lookup and similarity-based retrieval, (3) a tool-augmented memory retrieval agent which explores the memory autonomously by selecting appropriate tools provided by the database based on the user input, and decides whether to proceed to the next iteration or finalizing the response after reasoning on the fetched memories. The TA-Mem is evaluated on the LoCoMo dataset, achieving significant performance improvements over existing baseline approaches. In addition, an analysis of tool use across different question types also demonstrates the adaptivity of the proposed method.