Tool-Use Evaluation

While LLM agents demonstrate strong reasoning abilities in compact and well-defined scenarios, they struggle to maintain robustness and effectiveness when faced with large-scale, diverse, and dynamic real-world environments that demand seamless tool integration. To address this gap, we introduce ToolVerse, a comprehensive framework that scales up agentic RL environments and enables agents to perform complex long-horizon reasoning in Tool-Integrated Reasoning (TIR) tasks. First, ToolVerse automatically builds the massive executable agent training environments from nearly 400 real-world Model Context Protocols (MCPs) that contain about 4500 tools. Second, we propose a task design strategy based on a tool dependency graph, utilizing Dynamic Unlocking Sampling Algorithm to generate long-horizon tasks, and produce GUST (Graph Unlocking Sampling Tasks) dataset. Third, to alleviate the credit assigment problem in long-horizon agentic RL, we propose a fine-grained Turn-Aware Relative Advantage algorithm. We conduct extensive Agentic RL training using ToolVerse and evaluate our framework on serveral agentic benchmarks. Experimental results demonstrate that our framework significantly strengthens LLMs' capabilities in long-horizon tool use, achieving a marked performance boost and showcasing robust reasoning within dynamic environments.

As Model Context Protocol (MCP) servers emerge as the core infrastructure for connecting LLMs with external tools, existing benchmarks leverage real-world MCP servers to evaluate LLM agents' tool-using capabilities. However, these benchmarks overlook the continuous evolution of tool interfaces and functionalities within MCP servers, resulting in flawed assessments that fail to capture the agent's adaptability in changing tool landscapes. To bridge this gap, we introduce \textbf{MCPEvol-Bench}, a novel benchmark for evaluating the task-solving capabilities of LLM agents under dynamic toolset evolution. Inspired by large-scale empirical study, we propose 11 mutation operators to simulate realistic tool evolution within 123 MCP servers. We benchmark 12 state-of-the-art LLMs on multiple versions of MCP servers, revealing that even frontier models struggle to adapt to evolving tools. For instance, GPT-5.4 and Claude-Sonnet-4-6 exhibit performance declines of 13.7% and 14.4% in evolved MCP servers, respectively, accompanied by substantial increases in planning and reasoning errors. These findings highlight the vulnerability of LLM-driven workflows, establishing MCPEvol-Bench as a standard for evaluating agent adaptability in dynamic tool environments.

Trustworthy deployment of LLM-based agents in software systems requires evaluating how they perform on application-specific workflows, with enough granularity to localize where they succeed and fail. Yet existing agent evaluation mechanisms are limited: benchmarks have low construct validity for application-specific workflows and environments, and replica evaluation environments are expensive and prone to drift. We propose Copy-on-Write (CoW) Scoring, a framework that evaluates agent operations directly within application environments using a PostgreSQL-level Copy-on-Write mechanism to isolate agent writes. CoW Scoring produces session- and operation-level scores that highlight where agents' database write operations succeed and fail in a given application environment, enabling inexpensive evaluation and iteration on agent harnesses and tool surfaces. We demonstrate the framework on Plane, an open-source project-management platform, where analysis surfaced specific issues in the tool surface, and corresponding fixes produced measurable improvements on affected models. Python library: https://github.com/trail-ml/agent-cow-python

We introduce MM-ToolSandBox, a benchmark and evaluation framework for visually grounded tool-calling agents. The framework provides a stateful execution environment spanning 500+ tools across 16 application domains, supporting multi-image, multi-turn tasks where agents must ground progressively arriving visual inputs into executable tool calls while handling realistic conversational phenomena (goal revisions, error corrections, state mutations). An automated scenario generation pipeline produces diverse, visually grounded scenarios through information-flow-guided planning and multi-stage quality filtering, yielding 258 human-verified nominal scenarios and 50 variants targeting interactive UI applications. Evaluating 12 state-of-the-art models, from 4B open-weight to frontier proprietary systems, shows that current models still lack robust visual tool-calling capability: even the best model achieves below 50% success rate. Our failure analysis further reveals that visual precision, not only planning, is a primary bottleneck for capable models: 53% of failures stem from incorrect information extraction from images despite otherwise correct task workflows. A planning-to-precision crossover emerges with scale: smaller models fail at deciding what to do, while larger models fail at perceiving what they see, suggesting fundamentally different research directions for improving models at different capability levels. The framework and the benchmark are publicly available at https://github.com/apple/ml-mmtoolsandbox

Tool calling is central to modern language model agents, but aggregate benchmark scores often hide where tool use fails. A model that never calls a needed tool and a model that calls the tool but ignores the result can look similar under final task accuracy. We introduce ToolFailBench, a diagnostic benchmark for measuring tool-use failures across 1,000 tasks in finance, medicine, law, cybersecurity, and real estate. Tool-required tasks return values the model wouldn't guess, forcing it to trust the tool while control tasks attach the same tools but should be answered directly. We label each trace with Tool-Skip, Result-Ignore, Output-Fabrication, and Unnecessary-Tool-Use, using a rule classifier and two LLM judges aggregated by majority vote. Across 19 headline models, the best reaches 86.33% Clean Tool-Use Rate, showing that faithful tool use is not saturated. More importantly, models with similar aggregate scores fail in different ways: most stay disciplined on no-tool controls, while Llama-3.1 models show an Always-Call pattern, and at the same parameter scale Llama-3.1-70B and Qwen2.5-72B differ by 89 percentage points on control-task accuracy. Tool-use evaluation should measure not only whether agents call tools, but whether they use tool outputs correctly and avoid tools when none is needed.

Large language model agents are increasingly connected to scientific software, yet it remains unclear when tool access makes scientific computation more reliable rather than merely more complex. We introduce PHREEQC-MCQ-200, a benchmark for evaluating tool-augmented agents on deterministic aqueous-geochemistry simulations. The benchmark contains 200 multiple-choice questions derived from 21 validated PHREEQC scenarios, requiring agents to construct simulator inputs, execute PHREEQC, inspect structured outputs, and commit to final answers. Across multiple frontier and mid-tier model families, simulator access substantially improves aggregate accuracy, confirming that grounded execution is necessary for many scientific-computation tasks. However, the gains are not monotonic: tool-augmented agents also lose items they answered correctly without tools, revealing regressions that average accuracy alone hides. We further show that output-access protocol matters. A table-of-contents interface can reduce token cost while preserving or improving accuracy for stronger models, but it degrades performance for mid-tier models that cannot reliably navigate structured simulator outputs. PHREEQC-MCQ-200 therefore frames scientific tool use as an end-to-end diagnostic problem rather than a simple tool-calling capability. We argue that evaluations of scientific agents should report not only accuracy, but also item-level retention, output-access sensitivity, trajectory failures, and where the computation chain breaks.

Large language models (LLMs) have increasingly moved from standalone text generation systems to agents that invoke external tools, access environments, and execute multi-step tasks. However, conventional function-calling benchmarks mainly evaluate task completion and API correctness, while privacy evaluation benchmarks typically focus on final responses or privacy judgments. Neither perspective captures purpose-bound information flow across an executed multi-tool trajectory. Motivated by this limitation in current agent evaluation, ToolPrivacyBench audits whether task-private atoms are routed only to authorized tools and downstream sinks, thereby evaluating both task completion and privacy over-disclosure during tool use. The benchmark contains 2,150 cases, including 1,150 fully synthetic privacy-sensitive business workflows and 1,000 cases adapted from existing multi-tool and function-calling benchmarks. Each case is represented by a policy knowledge base. After an agent executes against mock business backends, the evaluator compares recorded tool arguments and backend audit logs with this policy knowledge base. The evaluation covers nine widely used agents to characterize purpose-bound privacy over-disclosure. The results show that successful tool execution does not imply appropriate privacy disclosure: an agent may complete a task while transmitting unnecessary private information through intermediate tool calls. ToolPrivacyBench therefore formalizes a need-to-know disclosure boundary, under which each tool should receive only the information necessary for its stated purpose, and uses trajectory-level auditing to identify privacy over-disclosure in multi-tool workflows.

Exact-match retrieval recall is often used as a proxy for whether a retriever supplies useful policy context to a downstream decision model. We test this proxy for pre-action policy classification in $τ$-bench using Qwen2.5-3B/7B classifiers. Under gold-policy conditioning, a compact structured state improves macro-F1 over raw trajectories by $0.20$ after tuning at 3B, with the same ordering at 7B under shared hyperparameters. We then replace the benchmark-designated governing rule with the top-ranked benchmark assertion retrieved from decision-time context. Although the exact governing rule is retrieved at rank 1 for only $7\%$ of airline states, the primary 3B classifier obtains macro-F1 $0.58$ with retrieved assertions versus $0.60$ with the gold rule ($Δ=-0.02$, task-cluster 95% CI $[-0.23,+0.21]$); random non-gold and no-assertion controls score $0.32$ and $0.21$. We do not detect a macro-F1 difference between retrieved assertions and the gold rule in this configuration, although the interval remains too wide to establish non-inferiority. The same qualitative pattern appears with a second retriever and at 7B, while varying across fine-tuning configurations. These results show that exact-match recovery of the benchmark-designated rule can underestimate the downstream utility of retrieved benchmark assertions in this setting. Retrieval should therefore be evaluated inside the classification loop rather than by exact-match recall alone.

Before letting an agent operate over real context, can you prove it used the right evidence? GroundEval turns that question into a deterministic test of what the agent searched, fetched, cited, and was permitted to access. In one case study, two frontier LLM judges scored a plausible agent response 0.85 and higher. But the trace told a different story: the agent had never retrieved the artifact its answer depended on, yielding a GroundEval score of 0.000. We introduce GroundEval, a judge-free framework for evaluating agents against grounded, time-bounded, and access-controlled evidence. GroundEval uses a domain configuration to generate questions, lets the agent choose how to answer, and then scores both the final answer and the recorded trajectory that produced it. The benchmark targets three failures that LLM-as-judge evaluation struggles to detect: whether an agent checked before claiming absence, reasoned only from evidence available to the actor at the relevant time, and used the correct causal mechanism rather than a plausible one. These correspond to three tracks: Silence, Perspective, and Counterfactual. GroundEval exposes when plausible answers rest on invalid evidence paths, and produces structured per-question diagnostics that pair tool activity with the agent's turn-level narration, making each score inspectable rather than merely reported. Our case studies suggest this failure mode is common rather than exceptional, one that final-answer and judge-based evaluation cannot detect by construction.

Tool-augmented agents are typically evaluated by their gains under reliable external feedback. Yet these gains leave open a key counterfactual: when feedback is unreliable, would the agent be better off receiving no task evidence? We study this question with a controlled matched-loop comparison that fixes the agent loop, prompt, action space, and decoding, while varying only the returned observation: faithful, misleading, or absent. Across question answering and fact verification, persistent misleading feedback produces a value inversion: agents that benefit from clean tools can perform worse than the matched no-feedback fallback. On HotpotQA, Qwen2.5-7B reaches 44.8 F1 with clean retrieval and 22.3 F1 with no feedback, but drops to 4.7 F1 under shuffled retrieval. The inversion persists under stronger clean retrieval and locally plausible distractors, but weakens when later clean evidence can repair the trajectory. Early trajectory signals predict many failures, yet simple repairs remain fallback-limited: rejecting bad evidence helps only when the exposed fallback is reliable. These results show that clean-tool gains can overstate tool value, and that matched no-feedback fallback controls are necessary for evaluating tool-augmented agents.

As LLM-based shopping agents enter production, existing benchmarks fail to capture how a shopper's requirements arrive: stated implicitly in the query, recorded in a profile, or revealed only when the right question is asked. Benchmarks that expose full intent upfront and grade only the final choice can neither pose this long-horizon challenge nor explain which requirement an agent missed. To address this gap, we introduce EComAgentBench, a benchmark of 662 tasks grounded in real Amazon products and reviews. Each task scatters these requirements across a visible query, a tool-gated profile, and scripted clarification; an agent must uncover hidden intent, verify candidates against attributes and review evidence, and commit to a single product within 100 tool calls. Moreover, typed, source-tagged rubrics grade every task, attributing each failure to a requirement and its source. Construction is automated yet reliable, with every answer fixed in code before any text is generated and every sample validated. Our evaluation of seven models reveals that even the strongest attains only 57.1% overall accuracy, and rubric satisfaction degrades from visible to hidden sources. Overall, we believe EComAgentBench will serve as a reproducible foundation for moving shopping agents from single-query search toward dependable assistance over long horizons.

Tool-augmented large language model agents increasingly operate over large tool libraries, but existing evaluations often focus on whether a model can call a tool correctly rather than how the visible tool menu shapes reliability, efficiency, and safety-relevant risk exposure. We introduce ToolMenuBench, a benchmark for evaluating tool-menu construction in multi-step LLM agents. ToolMenuBench varies tool-menu size, distractor type, state-dependent task structure, and risk exposure, and reports both filter-level and downstream agent metrics, including visible-tool count, risky-tool exposure, task success, wrong-tool calls, premature actions, and token usage. In a controlled evaluation across seven model backends, three tool-menu sizes, six filtering methods, and seven evaluation settings, CMTF improves task success from 32.1% under all-tools exposure to 85.7%, while reducing average token usage by roughly 98%. Causal minimal tool filtering achieves the strongest overall tradeoff, reducing visible tools, wrong-tool calls, premature actions, and risky-tool exposure relative to unfiltered exposure, lexical filtering, state-aware filtering, and broader causal-path baselines. ToolMenuBench provides a reusable evaluation framework for studying the agent-interface problem: which tools should be visible, when they should be visible, and under what cost or risk constraints.

Tool-augmented large language model agents increasingly rely on external APIs, but standard tool schemas describe how to call a tool, not when the tool is causally appropriate or what task state it produces. Causal tool filtering addresses this gap by using lightweight contracts that specify each tool's preconditions, effects, risk level, and cost. However, manually writing and maintaining such contracts does not scale to large or changing tool ecosystems. We introduce Contract2Tool, a framework for inferring tool contracts from metadata, schemas, documentation, and execution traces. Contract2Tool converts observable tool evidence into normalized symbolic contracts that can be evaluated intrinsically and deployed inside downstream causal tool filtering. We evaluate learned contracts against gold preconditions, effects, and risk labels, and measure their downstream utility on multi-step agent tasks. Our results show that hybrid documentation-and-trace evidence produces contracts accurate enough to preserve most of the reliability and efficiency benefits of gold contracts. Learned-contract CMTF achieves 0.980 downstream success, close to 0.990 for gold-contract CMTF, while reducing visible tools from 100 to 1 and reducing average token usage from 26,172 to 2,528 relative to all-tools exposure. These results suggest that learned contracts can provide a scalable contract layer between tool schemas and reliable agent execution.

Large language model agents increasingly rely on external tools, but larger tool menus can reduce reliability and efficiency by increasing wrong-tool calls, premature actions, and token cost. Existing tool-selection methods often optimize semantic relevance, exposing tools whose names or descriptions match the user request. We argue that relevance is insufficient: a tool may be related to the task while still being unnecessary or premature at the current step. We propose Causal Minimal Tool Filtering (CMTF), a training-free method that selects tools by causal sufficiency. CMTF uses lightweight precondition-effect contracts to expose only the minimal next-step tool frontier needed to advance from the current state toward the user goal. Across multi-step tool-use tasks, we compare CMTF with all-tools exposure, keyword retrieval, state-aware filtering, and causal-path ablations, measuring task success, wrong-tool calls, premature actions, tool exposure, and token cost. In the main benchmark with 102 tasks, 100 tools, four LLM backends, and 2448 task-method-model runs, CMTF matches the strongest causal baseline in aggregate success while reducing visible tools from 100 to one per step and reducing token usage by about 90% relative to all-tools exposure.

When an AI agent calls an API and hits a validation error, it needs more than what went wrong -- it needs what to do next. A self-reflective API returns, on validation failure, a machine-readable recovery_feedback.suggestions[] payload sufficient for the agent to repair the request and retry without external reasoning. On a leak-audited pilot ($N{=}30$ per cell, 3 LLMs, 10 adversarial tasks), structured suggestions lift task-completion rate by $+36.7$--$40.0$pp over plain-English diagnoses on Anthropic models (Fisher's exact $p \le 0.0022$), at $1.8$--$2.2\times$ better per-success token efficiency. The lift is not significant on gpt-4o-mini ($p{=}0.435$); a second-domain replication on a billing API confirms the pattern. The comparison only holds after auditing two undocumented classes of answer leakage in LLM benchmarks. We shipaudit_prompt_leakage.py as reusable CI infrastructure. Code and data: https://github.com/arquicanedo/self-reflective-apis.

Despite great advances in tool-use capabilities of large language models (LLMs), existing evaluation benchmarks struggle to fully align with real-world scenarios. Such benchmarks mostly rely on simulated idealized user assumptions and lacks experience-oriented evaluation. These limitations fail to account for the ambiguity, uncooperative behaviors, and shifting intentions characteristic of real-world users. To fill this gap, we propose RUT-Bench, a dedicated benchmark designed to assess LLMs under diverse Real-world User Tool calling scenarios. RUT-Bench supports high-fidelity simulations covering both ideal rational patterns and heterogeneous non-ideal behaviors across single-turn and multi-turn dialogues. We conduct comprehensive evaluations on 19 widely adopted open-source and proprietary LLMs using our benchmark. Experimental results reveal that no tested LLMs achieve an overall success rate above 40%, and nearly all of them experience noticeable performance drops when facing more complicated non-ideal user inputs. Our code and data is available at https://github.com/Miaow-Lab/RUT-Bench.

Tool-augmented multimodal agents show strong benchmark gains, often taken as evidence that agents have learned to use tools. We argue that this interpretation can be premature: a tool-call trace alone does not show whether the tool supplied answer-critical information. We study two representative ``thinking with images'' agents, Thyme and DeepEyesV2, across real-world understanding, OCR, chart understanding, and mathematical reasoning. Each agent is compared with its Tool-Free counterpart and with a Pure-Text Reasoner trained from the same source pool without tool-calling trajectories. Tool access yields little consistent aggregate improvement, does not reliably reduce generated-token cost, and leaves only a small tool-only solved set: 93% of DeepEyesV2's tool-solved problems and 96% of Thyme's are also solved by at least one non-tool setting. Mechanism ablations further show that the full tool-use loop does not consistently outperform either the tool-call format or the returned execution result alone. In the settings we study, the analyzed agents appear to learn tool-calling patterns more reliably than tool-contributed capabilities, suggesting that evaluation should distinguish tool availability from whether tools actually expand what agents can solve.

Tool-calling is a central component of modern large language model (LLM) agents, equipping them with skills beyond their parametric knowledge. This paper studies tool-calling along two complementary axes: effectiveness, i.e., how this capability is measured, and efficiency, i.e., how it is learned. On effectiveness, we systematically analyze tool-calling evaluation pipelines and show that results can be highly sensitive to seemingly minor, often undocumented implementation choices including the random seed, system prompt, multi-turn template construction, and how prior interaction/reasoning history is carried forward. These choices can lead to substantial differences in reported performance, especially in multi-turn settings where without rigorous standardization, leaderboard rankings are unreliable. On efficiency, we examine standard reinforcement learning (RL) for tool-calling and identify two sources of computational waste: (i) during rollouts, many prompts produce no learning signal, and (ii) during policy updates, optimization incurs high computational cost. Guided by these findings, we introduce two techniques that accelerate RL-based tool-calling training, achieving substantial wall-clock speedup without degrading performance.

As agent capabilities advance, existing benchmarks, such as $τ^2$-Bench, are becoming increasingly saturated. Yet constructing new benchmark tasks remains complex, costly, and labor-intensive. Moreover, the standard approach, in which scenarios are first written in natural language and then mapped to tool sequences, captures only a narrow subset of the tool-use patterns agents exercise. In this paper, we address these problems by reversing the task construction process. We propose TASTE: Task Synthesis from Tool Sequence Evolution, an automatic method that generates challenging tasks with broader tool-use coverage. TASTE utilizes an Adaptive Contrastive $n$-gram model trained on LLM-judged validity signals. This enables sampling valid tool sequences that cover a vast range of tool combinations. TASTE then selects representative sequences from the pool via clustering, instantiates them into complete benchmark tasks, and refines them through iterative difficulty evolution. Using TASTE, we construct $τ^c$-Bench, a challenging extension of the three domains of $τ^2$-Bench. We evaluate $11$ agent/user LLM pairs and find that models nearly saturating $τ^2$-Bench suffer severe performance drops on our tasks (e.g., Gemini-3-Flash falls from $0.82\!-\!0.94$ to $0.28\!-\!0.61$). Beyond increasing difficulty, our generated tasks more than double the number of unique tool combinations agents must execute. Our results suggest high scores on existing benchmarks often reflect saturation rather than robust task-solving ability. By automating the generation of difficult, high-coverage benchmarks, TASTE enables continuous, scalable evaluation of future agents.

Large language model (LLM)-based agents have shown strong capabilities in using external tools to solve complex tasks. However, existing evaluations often overlook the temporal dimension of tool use, especially the impact of tool response latency, and are usually limited to single-task settings. In real-world applications, multiple tasks often need to be executed concurrently, and overall efficiency depends on whether an agent can use idle time while waiting for tool responses. We refer to this capability as asynchronous tool calling. To evaluate it, we propose AsyncTool, a benchmark for assessing LLM-based agents in interactive multi-task tool-use environments with delayed tool feedback. AsyncTool presents multiple heterogeneous tasks simultaneously and simulates realistic tool response latency during execution. Using a hybrid data evolution strategy, we construct a diverse asynchronous multitasking dataset that covers multiple scenarios and tool-use patterns. We evaluate models at the step, sub-task, and task levels, and introduce efficiency-oriented metrics to measure task coordination and completion efficiency. Extensive experiments show that delayed tool feedback poses substantial challenges to current agents and leads to clear performance degradation. Models that better coordinate task switching, dependency tracking, and state maintenance achieve stronger performance on AsyncTool. Our analysis identifies key failure modes of current tool-using agents and provides practical insights for designing future systems with stronger temporal reasoning and coordination capabilities.

We test the standard RLVR tool-use recipe -- GRPO on Qwen2.5-7B-Instruct -- on a deliberately minimal knowledge-graph tool API: four Freebase navigation verbs over Complex WebQuestions. Under a self-verifiable retrieval reward, the policy's tool-grounded answer rate climbs from $3.8\%$ to $9.6\%$ over 250 steps, then collapses to $0\%$ within a single 50-step window -- a \emph{peak-then-collapse} pattern replicated across four seeds. Across seven reward designs, we find four recurring failure modes: adding denser or more targeted proxy rewards shifts the failure mode rather than eliminating it. We argue that a key difference from Python interpreters, web search, and JSON APIs is interface feedback: their failures often leak natural-language signal the model saw in pretraining. A Python traceback names the failing line; an empty Freebase result \texttt{[]} does not. Stripping away that surface exposes a degradation regime that same-family reward redesigns do not fix. A direct oracle ablation rules out relation selection: injecting gold relations at every retrieval call lifts exact-match accuracy by only $+0.20$~pp, and $95.4\%$ of retrieval-dependent errors are retrieval-composition failures rather than answer-extraction failures. As a mitigation, one-iteration self-distillation reaches $40.0\%$ EM at 7B and is capacity-invariant: doubling capacity to 14B improves EM by only $0.25$~pp, and initialization barely matters -- the ceiling appears interface-bound within the 7B--14B range tested.

Before an LLM agent can use a tool, a retrieval system must decide which candidate tools to show to the agent. How long should that shortlist be? Show too many tools and the model struggles to choose. Show too few and the correct tool may not appear. Most systems apply a fixed shortlist size to every query, but no standard metric exists to evaluate whether that size was appropriate. We treat the number of tools shown to an LLM agent as the object of evaluation and we apply Bits-over-Random (BoR), a chance-corrected metric that asks whether success at a given depth is better than what random selection would achieve at that same depth. We evaluate BoR across three tool-selection benchmarks, multiple scorers, and registries ranging from 20 to 3,251 tools. We then turn the same principle into a reinforcement learning (RL) reward for choosing tool shortlist depth per query. The RL agent is deliberately simple, serving as a probe of the metric rather than a proposed system. As the shortlist grows, random chance of including the correct tool rises, so the reward naturally decreases, reducing the need for an engineered depth penalty. On BFCL (370 tools), the learned policy nearly matches the coverage of showing 50 tools ($90.3\%$ vs $90.8\%$) while presenting only 7 on average. On ToolBench (3,251 tools), a fixed shortlist of 5 tools achieves higher aggregate coverage ($64.7\%$ vs $61.9\%$) but finds nothing on hard queries (correct tool ranked 6th-20th). The BoR agent finds $16.7\%$ on those same queries by searching deeper. Downstream validation with Claude Sonnet 4.6 indicates that shorter adaptive lists also improve the LLM's ability to select the right tool: $93.1\%$ versus $87.1\%$ when always shown 5 tools, widening to $76.8\%$ vs $60.9\%$ on medium-difficulty queries where the correct tool is present but not ranked first.

Today, tool-calling agents are commonly evaluated or tested on static datasets of execution traces, including input commands, agent responses, and associated tool calls. However, internal production datasets are often insufficient or unusable for testing; for example, they may contain sensitive or proprietary data, or they may be too sparse to support comprehensive testing (especially pre-deployment). In these settings, practitioners are increasingly replacing or augmenting real datasets with synthetic ones for evaluation purposes. A key challenge is quantifying the relation between these synthetic datasets and the real data. We introduce SynAE, an evaluation framework for assessing how well synthetic benchmarks for multi-turn, tool-calling agents replicate and augment the characteristics of real data trajectories. SynAE assesses the validity, fidelity, and diversity of synthetic data across four metric categories: (i) task instructions and intermediate responses, (ii) tool calls, (iii) final outputs, and (iv) downstream evaluation. We evaluate SynAE using recent agent benchmarks and test common synthetic data failure modes via realistic and controlled generation schemes. SynAE detects fine-grained variations in data validity, fidelity and diversity, and shows that no single metric is sufficient to fully characterize synthetic data quality, motivating a multi-axis evaluation of synthetic data for agent testing. A demo of SynAE is available at https://synae-2026-synae-demo.static.hf.space/index.html, with code at https://github.com/wsqwsq/SynAE.

Tool-using agents are increasingly expected to operate across realistic professional workflows, where they must interpret multimodal inputs, coordinate external tools, inspect intermediate artifacts, and revise their actions before producing a final result. Existing benchmarks, however, often evaluate tool use, computer use, and multimodal reasoning in isolation, leaving a gap between benchmark settings and end-to-end omni-modal tool use in the real world. To address this gap, we introduce MM-ToolBench, a benchmark and evaluation harness for task-oriented omni-modal tool use. MM-ToolBench contains 100 executable tasks from two macro task families, Customer Service and Intelligent Creation, covering 20 subcategory slices and supported by 27 MCP servers with 324 tools. The central design of MM-ToolBench is closed-loop multimodal verification: agents must execute tools, inspect rendered or transformed artifacts, and self-correct when outputs fail task-specific requirements. To make such evaluation scalable and verifiable, MM-ToolBench couples MCP-based execution with task-specific grounded evaluators and a semi-automated construction pipeline for scenario discovery, task instantiation, evaluator synthesis, and human audit. Experiments on 15 contemporary agentic models show that MM-ToolBench remains highly challenging: Claude Opus 4.6, commonly regarded as one of the strongest coding-agent models, achieves only 32.0% task success, far below the 94.0% human benchmark. We envision MM-ToolBench as a practical foundation for evaluating and advancing next-generation omni-modal tool-using agents through closed-loop multimodal verification.

LLM recommendation agents increasingly produce structured recommendation reports: sets of items accompanied by natural-language justifications. Yet existing evaluations often reduce this setting to reranking small shortlisted candidate sets or judge reports mainly by semantic plausibility. We introduce Recommendation Atlas (Agentic Tool-Level Assessment for Shopping), or RecoAtlas, a benchmark and toolkit for evaluating shopping agents with behavior-grounded metrics. RecoAtlas complements held-out interaction metrics with learned utility proxies for relevance, complementarity, and diversity derived from interaction data, while separately measuring semantic coherence and explanation quality. Its controlled tool environment exposes agents to either semantic, behavior-aligned, or faulty tools, enabling diagnosis of whether performance gains arise from stronger reasoning, better signals, or more effective tool-use policies. Across controlled experiments, we show that RecoAtlas exhibits key properties of a meaningful benchmark for agentic systems: performance scales with model capacity and test-time compute, improves with stronger and better-aligned tools, degrades under noisy or misaligned signals, and reveals that semantic plausibility does not necessarily capture behavior-grounded utility. RecoAtlas provides a foundation for developing and evaluating shopping assistants that optimize not only for plausible recommendations, but also for coherent, behaviorally grounded recommendation sets.

Closed-loop tool-using agents are increasingly evaluated in executable web, code, and micro-task environments, but benchmark reports often conflate workloads, action-generating drivers, and the evidence admitted for systems-facing claims. We present an executable benchmarking suite that makes these objects explicit under a shared evidence-admission contract. The suite connects WebArena Verified, a SWE-Gym slice with SWE-bench-compatible verification, and MiniWoB++ through common workload adapters, task manifests, event schemas, replay/freeze policy, declared drivers, and reporting pipelines. In the canonical release, the gate separates paper-facing evidence from preflight, fixture, smoke, and diagnostic rows while preserving non-admitted artifacts for audit and onboarding. The admitted evidence records latency, invalid-action behavior, patch-generation cost, verifier metadata, replay bindings, and provenance under one auditable contract. The gate is decision-relevant rather than merely clerical: in a separate WebArena Verified controller study, clean-baseline and medium live-stressed evaluation select different fixed controller variants under the same workload and admission contract. The release is scoped as a benchmarking suite and admitted evidence, not a new agent policy, model leaderboard, backend comparison, or autonomous SWE-bench solver.

Tool-integrated reasoning has emerged as a promising paradigm for enhancing large language models with external computation, retrieval, and execution capabilities. However, the field still lacks a high-quality and unified evaluation benchmark, and existing TIR evaluations remain limited in dataset quality, task diversity, diagnostic comprehensiveness, and evaluation efficiency. In this work, we introduce TIDE-Bench, a holistic and efficient benchmark for evaluating TIR methods, featuring three key advantages. First, it provides diverse task settings, combining widely used mathematical reasoning and knowledge-intensive QA tasks with two newly designed tasks, namely the tool-grounded experimental design task and the dynamic interactive task, to probe models' abilities in complex tool invocation and multi-tool coordination. Second, TIDE-Bench adopts a comprehensive yet task-aware evaluation protocol, jointly measuring final answer quality, process reliability, tool-use efficiency, and inference cost across heterogeneous task settings. Third, TIDE-Bench constructs high-quality and discriminative evaluation sets by filtering low-discrimination instances from existing datasets, substantially reducing evaluation cost while focusing on more challenging samples. Extensive experiments on multiple foundation models and TIR methods reveal persistent bottlenecks in tool grounding, offering insights for future TIR research.

This paper introduces tool efficiency, a new quantitative metric to evaluate the rate of useful tool calls in an LLM agent trajectory. To ensure that tool efficiency is well-defined, we also introduce marginal tool utility, a new quantitative metric defined per tool call indicating whether a tool is useful or whether it can be safely removed from the tool suite without affecting accuracy while increasing tool efficiency; in this paper, we determine the sign of marginal tool utility for each tool call in a trajectory using LLM-as-a-Judge. While much prior work has been done to develop techniques that improve tool use by LLMs and design evaluation methods measuring efficiency indirectly using accuracy as a proxy, our work is centered on measuring efficiency directly via the quantitative metric proposed in this paper in post hoc trajectory analyses. It is our intention that this work contributes to the frontier of LLM evaluation research as a springboard for future benchmark designs and agent harness engineering (specifically with regards to creating lean tool suites) that optimize for metrics that complement but are distinct from accuracy.

A semantic gap separates how users describe tasks from how tools are documented. As API ecosystems scale to tens of thousands of endpoints, static retrieval from the initial query alone cannot bridge this gap: the agent's understanding of what it needs evolves during execution, but its tool set does not. We identify this retrieval interface, not planning, as the binding constraint on end-to-end agent performance, and introduce FitText, a training-free framework that makes retrieval dynamic by embedding it directly in the agent's reasoning loop. FitText treats retrieval as test-time evolution of hypotheses: the agent generates natural-language pseudo-tool descriptions (revisable beliefs about the tool it needs), refines them iteratively using retrieval feedback, and explores diverse alternatives through stochastic generation. Memetic Retrieval adds evolutionary selection pressure over candidate descriptions, guided by a tool memory that avoids redundant search. On ToolRet (three domains), FitText's reformulation strategies improve NDCG@5 by 2.7 to 10.6 points over static query retrieval across all base models; on StableToolBench (16,464 APIs) with GPT-5.4-mini, Memetic reaches an 84.3% pooled pass rate, a 26.7-point absolute gain over static query retrieval.

Agentic AI architectures augment LLMs with external tools, unlocking strong capabilities. However, tool use is not always beneficial; some calls may be redundant or even harmful. Effective tool use, therefore, hinges on a core LLM decision: whether to call or not call a tool when performing a task. This decision is particularly challenging for web search tools, where the benefits of external information depend on the model's internal knowledge and its ability to integrate potentially noisy tool responses. We introduce a principled framework inspired by decision-making theory to evaluate web search tool-use decisions along three key factors: necessity, utility, and affordability. Our analysis combines two complementary lenses: a normative perspective that infers true need and utility from an optimal allocation of tool calls, and a descriptive perspective that infers the model's self-perceived need and utility from their observed behaviors. We evaluate six open and one closed-source frontier models under two harnesses, one conditioning on only the current turn and its search results, the other on the full execution traces, across four web-search tools and three tasks. In every setting, we find that a model's perceived need and utility are frequently misaligned with the true need and utility. Building on this framework, we train lightweight estimators of need and utility from the models' hidden states. These estimators drive simple controllers that improve decision quality and yield stronger task performance than the self-perceived baseline for most of the open-source models.