architecture · first seen 4 Oct 2026
tool-using agents
Also: agent loop, AI agent tools, agent tool loop, tool-use agents, agentic tool use, agentic perception, LLM agent tool use
LLM-based agents that invoke external tools or functions to complete tasks.
Mentions per week
PapersCodeDiscussion
Rank 142 on 3 Nov 2026 · 25 mentions in 28 days · 25 independent groups · papers → code · first seen 4 weeks ago · acceleration -0.29
Earliest sources
- Rethinking Tool Design for Agentic RCA: A Controlled Empirical StudyPapers · 4 Oct 2026 · Yu Luo, Rongchen Gao, Zhenhui Zhou, Changchang Liu, Yuliang You, Yongqian Sun, S…
- UndoBench: Separating Task Competence from Recovery Capability in Tool-Using AI AgentsPapers · 4 Oct 2026 · Dolly Sah, Tanmay Sah, Harshul Jain, Tanya Sah
- Judged Useless, Queried Anyway: Tool-Using Agents Rarely Turn Their Own Evidence Judgments into Stopping DecisionsPapers · 5 Oct 2026 · Chubin Zhang, Zhenglin Wan, Xingrui Yu, Jingxuan Wu, Yaxin Zhou, Ivor Tsang, Bo…
- amadeuskeeler/agent-tool-loop-guideCode · 5 Oct 2026 · amadeuskeeler · 42 stars
- From Evidence to Action: How Tool-Using Agents FailPapers · 6 Oct 2026 · Hongzhan Lin, Shidong Cao, Ziyang Luo, Wenhao Chai, Mong-Li Lee, Wynne Hsu
- When the Governor Becomes the Disturbance: Control-Generated Disturbance and Cost-Aware Backoff in Governed Tool-Using AgentsPapers · 6 Oct 2026 · Veronique Ziegler
Latest sources
- Think2Listen: Evidence-Centric Learning For Agentic Audio Understanding With LALMSPapers · 16 Nov 2026 · Jin Wang, Liang Lin, Kaiwen Luo, Weiliu Wang, Yuxuan Li, Zengxin Han, Gan Zhang,…
- ToolGraph as a Q-Function for Test-Time Scaling of Tool-Use AgentsPapers · 16 Nov 2026 · Ke Shen, Ankita Bhaumik, Li Dong, Shengjie Liu, Shuzhen Li, Naveed Ahmed Janveka…
- ARCHER: From Rationale Imitation to Executable Reasoning in Small Language ModelsPapers · 13 Nov 2026 · Dhruv Dixit, Khushi Patel, Congcong Xu, Min Song
- When Safety Becomes an Attack Surface: Manipulating Abstention in Tool-Using AI AgentsPapers · 11 Nov 2026 · Charles Xiao
- ABLingss/awesome-agent-loopsCode · 5 Nov 2026 · ABLingss · 108 stars
- SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt InjectionPapers · 4 Nov 2026 · Woosang Lim, Yeseul Chang, Jaewoo Lee
- CompSkill: Compiling Execution Experience for Skill RetrievalPapers · 31 Oct 2026 · Qi Shen, Ziyue Zhu, Yongqing Jiang, Zhen Xia, Li Shengjie, Shuai Zhao, Bo Cheng,…
- Fidelity Collapses with Table Size, Not Turn Count: Delivery Architecture in a Deployed Tool-Using AgentPapers · 30 Oct 2026 · Tung Thanh Hoang
- PhysAg3D: Bridging 3D Generative and Agentic Models for High-Fidelity and Physically-Interactive AssetsPapers · 29 Oct 2026 · Bi'an Du, Fanpeng Meng, Jiemin Fang, Chen Yang, Pufan Li, Daizong Liu, Qi Tian,…
- Efficient Agentic Audio-Visual Question Answering through Toolset Pruning and Modality ConsolidationPapers · 28 Oct 2026 · Yi Wang, Tianzi Wang, Peter Bell
- Scaling Laws for Tool-Use Agents via Controllable Environment SynthesisPapers · 27 Oct 2026 · Andrew Szot, Samira Abnar, Omar Attia, Abbas Kazerouni, Michael Kirchhof, Cheng-…
- Context Is a Pipeline, Not a Window: Information Attrition in LLM Agent HarnessesPapers · 26 Oct 2026 · Yuvraj Sehgal, Mahsa Panahandeh, Naser Ezzati-Jivan