Tag: Tool Use

Shilin Yan, Jintao Tong, Hongwei Xue, Xiaojun Tang, Yangyang Wang, Kunyu Shi · Apr 9, 2026 · Citations: 0

• The advent of agentic multimodal models has empowered systems to actively interact with external environments.
• Extensive evaluations demonstrate that our resulting model, Metis, reduces tool invocations by orders of magnitude while simultaneously elevating reasoning accuracy.

Hanyang Wang, Mingxuan Zhu · Apr 8, 2026 · Citations: 0

• Across five model configurations, two families, and three benchmarks, we find that 52--88% of chain-of-thought tokens are produced after the answer is recoverable from a partial prefix.

Yuanfu Sun, Kang Li, Dongzhe Fan, Jiajin Liu, Qiaoyu Tan · Apr 7, 2026 · Citations: 0

• To bridge this gap, we introduce Agentic Graph Learning (AGL), a paradigm that reframes graph learning as an interleaved process of topology-aware navigation and LLM-based inference.
• Specifically, we propose AgentGL, the first reinforcement learning (RL)-driven framework for AGL.

Guan-Ting Lin, Chen Chen, Zhehuai Chen, Hung-yi Lee · Apr 6, 2026 · Citations: 0

• We introduce Full-Duplex-Bench-v3 (FDB-v3), a benchmark for evaluating spoken language models under naturalistic speech conditions and multi-step tool use.
• Unlike prior work, our dataset consists entirely of real human audio annotated for five disfluency categories, paired with scenarios requiring chained API calls across four task domains.

Xuan Qi · Apr 2, 2026 · Citations: 0

• Chain-of-thought (CoT) reasoning is widely assumed to improve agent performance, but the relationship between reasoning length and accuracy in structured tool-use settings remains poorly understood.
• We present a systematic study of CoT budget effects on function-calling agents, sweeping six token budgets (0--512) across 200 tasks from the Berkeley Function Calling Leaderboard v3 Multiple benchmark.

Zhe Yang, Shulin Tian, Kairui Hu, Shuai Liu, Hoang-Nhat Nguyen, Yichi Zhang · Apr 1, 2026 · Citations: 0

• We present HippoCamp, a new benchmark designed to evaluate agents' capabilities on multimodal file management.
• We evaluate a wide range of state-of-the-art multimodal large language models (MLLMs) and agentic methods on HippoCamp.

Davide Di Gioia · Mar 31, 2026 · Citations: 0

• Autonomous tool-using agents in networked environments must decide which information source to query and when to stop querying and act.
• Without principled bounds on information-acquisition costs, unconstrained agents exhibit systematic failure modes: excessive tool use under congestion, prolonged deliberation under time decay, and brittle behavior under ambiguous evidence.

Lara Russell-Lasalandra, Hudson Golino, Luis Eduardo Garrido, Alexander P. Christensen · Mar 30, 2026 · Citations: 0

• Psychological scale development has traditionally required extensive expert involvement, iterative revision, and large-scale pilot testing before psychometric evaluation can begin.
• The `AIGENIE` R package implements the AI-GENIE framework (Automatic Item Generation with Network-Integrated Evaluation), which integrates large language model (LLM) text generation with network psychometric methods to automate the early…

Jie Zhu, Yimin Tian, Boyang Li, Kehao Wu, Zhongzhi Liang, Junhui Li · Mar 26, 2026 · Citations: 0

• 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.
• Using this benchmark, we systematically assess a range of mainstream LLMs and propose metrics that explicitly measure tool invocation accuracy and reasoning capabilities.

Chinmay Soni, Shivam Chourasia, Gaurav Kumar, Hitesh Kapoor · Mar 25, 2026 · Citations: 0

Yuhao Chen, Yi Xu, Xinyun Ding, Xiang Fang, Shuochen Liu, Luxi Lin · Mar 25, 2026 · Citations: 0

• With the growing demand for intelligent in-vehicle experiences, vehicle-based agents are evolving from simple assistants to long-term companions.
• To address this gap, we introduce VehicleMemBench, a multi-user long-context memory benchmark built on an executable in-vehicle simulation environment.

Haoyuan Xu, Chang Li, Xinyan Ma, Xianhao Ou, Zihan Zhang, Tao He · Mar 24, 2026 · Citations: 0

• 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…
• We comprehensively review recent progress in multi-tool LLM agents and analyzes the state of the art in this rapidly developing area.

Tianyi Li, Zixuan Wang, Guidong Lei, Xiaodong Li, Hui Li · Mar 23, 2026 · Citations: 0

• To address this, we present AgenticRec, a ranking-oriented agentic recommendation framework that optimizes the entire decision-making trajectory (including intermediate reasoning, tool invocation, and final ranking list generation) under…
• Third, we introduce Progressive Preference Refinement (PPR) to resolve fine-grained preference ambiguities.

Hussein Jawad, Nicolas J-B Brunel · Mar 14, 2026 · Citations: 0

• Large Language Model (LLM) agents increasingly use external tools for complex tasks and rely on embedding-based retrieval to select a small top-k subset for reasoning.
• We provide theoretical analysis of retrieval saturation and show on standard benchmarks that ToolFlood achieves up to a 95% attack success rate with a low injection rate (1% in ToolBench).

Guanyu Jiang, Zhaochen Su, Xiaoye Qu, Yi R. Fung · Mar 12, 2026 · Citations: 0

• Multimodal agents can now tackle complex reasoning tasks with diverse tools, yet they still suffer from inefficient tool use and inflexible orchestration in open-ended settings.
• To this end, we propose XSkill, a dual-stream framework for continual learning from experience and skills in multimodal agents.

Thiago Laitz, Thales Sales Almeida, Hugo Abonizio, Roseval Malaquias Junior, Giovana Kerche Bonás, Marcos Piau · Mar 10, 2026 · Citations: 0

• 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…
• 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…

Qianyu Yang, Yang Liu, Jiaqi Li, Jun Bai, Hao Chen, Kaiyuan Chen · Mar 9, 2026 · Citations: 0

• To this end, we introduce \OneMillion-Bench \OneMillion-Bench, a benchmark of 400 expert-curated tasks spanning Law, Finance, Industry, Healthcare, and Natural Science, built to evaluate agents across economically consequential scenarios.
• We adopt a rubric-based evaluation protocol scoring factual accuracy, logical coherence, practical feasibility, and professional compliance, focused on expert-level problems to ensure meaningful differentiation across agents.

Nicholas Kluge Corrêa, Aniket Sen, Shiza Fatimah, Sophia Falk, Lennard Landgraf, Julia Kastner · Mar 3, 2026 · Citations: 0

• Following our previous works, we now extend our dataset, GigaVerbo-v2, to a new degree of quality and scale, while also introducing a new synthetic dataset, GigaVerbo-v2 Synth, aimed at filling missing gaps in GigaVerbo-v2, and two…
• Through extensive ablation studies, we design both pretraining and continual pretraining recipes for the Tucano 2 suite (Base, Instruct, and Think), which achieve state-of-the-art performance on several Portuguese-language modeling…

Bo-Wei Chen, Chung-Chi Chen, An-Zi Yen · Feb 25, 2026 · Citations: 0

• Experiments on the Massive Multitask Language Understanding (MMLU) benchmark show that our approach achieves accuracy comparable to the largest model while reducing computational costs by 20\% to 40\%.

Debjit Paul, Daniel Murphy, Milan Gritta, Ronald Cardenas, Victor Prokhorov, Lena Sophia Bolliger · Feb 24, 2026 · Citations: 0

• To address this, we introduce DEEPSYNTH, a novel benchmark designed to evaluate agents on realistic, time-consuming problems that combine information gathering, synthesis, and structured reasoning to produce insights.
• When evaluated on DEEPSYNTH, 11 state-of-the-art LLMs and deep research agents achieve a maximum F1 score of 8.97 and 17.5 on the LLM-judge metric, underscoring the difficulty of the benchmark.