ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities | Paper Citation Record

Observation 0ad1fd50-ca3d-45cd-9304-6f5c1a5f1f4f · inbound

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents cites this paper.

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T01:35:51.215921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a301ce5c-2bd5-4879-8d8f-971613a711b6 · inbound

Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents cites this paper.

Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 173

Resolution: unresolved; no resolver link, observed 2026-08-12T20:36:02.129282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b358280-6ffe-4e51-98d5-6d9caa0fc493 · inbound

CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning cites this paper.

CATP-LLM: Empowering Large Language Models for Cost-Aware Tool Planning ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-12T13:19:06.916173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec77af0a-d3e9-43b4-a0e5-ba071b0f6dfe · inbound

Towards Effective GenAI Multi-Agent Collaboration: Design and Evaluation for Enterprise Applications cites this paper.

Towards Effective GenAI Multi-Agent Collaboration: Design and Evaluation for Enterprise Applications ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T20:47:14.563824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9602fd78-0b64-4afa-9e40-bb39925730e3 · inbound

Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions cites this paper.

Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-13T09:02:40.376710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation dedd5286-1cc7-4070-b1ca-b34d47eb14cd · inbound

MARFT: Multi-Agent Reinforcement Fine-Tuning cites this paper.

MARFT: Multi-Agent Reinforcement Fine-Tuning ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-16T11:42:31.292282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b9a74e7-ea75-4326-ad4f-18ce6946824e · inbound

When2Call: When (not) to Call Tools cites this paper.

When2Call: When (not) to Call Tools ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T10:12:48.025171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62e9db9a-bf21-434f-b710-3500d82941f0 · inbound

Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction cites this paper.

Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-15T21:05:35.085270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1873e3ea-ba02-4f5c-a9c5-b8504ac0da62 · inbound

Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challenges cites this paper.

Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challenges ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T20:21:22.209839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbd88b35-1cd6-4f4d-a67a-46f92a7aa064 · inbound

Invisible Tokens, Visible Bills: The Urgent Need to Audit Hidden Operations in Opaque LLM Services cites this paper.

Invisible Tokens, Visible Bills: The Urgent Need to Audit Hidden Operations in Opaque LLM Services ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T14:34:34.819687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55ff60d1-758d-4466-8142-ea7b84b5ab8c · inbound

Large Language Models for Planning: A Comprehensive and Systematic Survey cites this paper.

Large Language Models for Planning: A Comprehensive and Systematic Survey ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 157

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:01.284289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd43e93d-4be5-4004-9d58-f5834c6c6f73 · inbound

CONFETTI: Conversational Function-Calling Evaluation Through Turn-Level Interactions cites this paper.

CONFETTI: Conversational Function-Calling Evaluation Through Turn-Level Interactions ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T11:36:38.571897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f533e183-3092-407c-839d-ffecd6c4733d · inbound

$\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment cites this paper.

$\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T07:52:17.432112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 546c32d9-a530-4dc0-9c0d-1bde942dbe87 · inbound

Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey cites this paper.

Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 129

Resolution: unresolved; no resolver link, observed 2026-08-07T06:00:19.628526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90fb7440-f45f-4f79-b44e-d8638061cfa0 · inbound

Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities cites this paper.

Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 216

Resolution: unresolved; no resolver link, observed 2026-08-06T23:26:54.497019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e5ac1d4-53b1-4a8f-881b-74a20ced8816 · inbound

Teaching a Language Model to Speak the Language of Tools cites this paper.

Teaching a Language Model to Speak the Language of Tools ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:47.975577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c5b7e91-0ef3-44f7-ba03-612cb3886353 · inbound

Apple Intelligence Foundation Language Models: Tech Report 2025 cites this paper.

Apple Intelligence Foundation Language Models: Tech Report 2025 ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T16:26:58.622125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2065dfca-4776-4ec4-b6fd-34ad20d7434b · inbound

Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systems cites this paper.

Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systems ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T15:39:57.418255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17b85ac1-5fe6-4332-a284-bd791f769b3d · inbound

ASPERA: A Simulated Environment to Evaluate Planning for Complex Action Execution cites this paper.

ASPERA: A Simulated Environment to Evaluate Planning for Complex Action Execution ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 4976

Resolution: unresolved; no resolver link, observed 2026-08-06T15:34:30.254612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8985ac9c-af6b-44df-94c6-5f026bf80eae · inbound

Agent Identity Evals: Measuring Agentic Identity cites this paper.

Agent Identity Evals: Measuring Agentic Identity ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T14:57:06.486170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 384f4a7a-5d99-4c71-ad96-646df71eaa06 · inbound

A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence cites this paper.

A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 90

Resolution: verified exact; arxiv_id, observed 2026-05-14T22:23:15.733725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 32adb8cd-f031-49ee-82e3-dc87d140ae16 · inbound

UserBench: An Interactive Gym Environment for User-Centric Agents cites this paper.

UserBench: An Interactive Gym Environment for User-Centric Agents ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T12:09:26.408309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8254a3f-bd8b-4506-bc88-76b597e87b29 · inbound

Hell or High Water: Evaluating Agentic Recovery from External Failures cites this paper.

Hell or High Water: Evaluating Agentic Recovery from External Failures ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T17:35:04.652799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96b63d17-0dd0-4f62-96de-03c8dc107cf8 · inbound

PyTOD: Programmable Task-Oriented Dialogue with Execution Feedback cites this paper.

PyTOD: Programmable Task-Oriented Dialogue with Execution Feedback ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-05T17:57:28.102393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcde5d88-8512-4bb9-bea9-bbb2d01f6287 · inbound

How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on $\tau$-bench cites this paper.

How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on $\tau$-bench ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-05T14:49:00.685400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2acc08f8-df26-4463-b47c-75c18ec09782 · inbound

COMPASS: Benchmarking Constrained Optimization in LLM Agents cites this paper.

COMPASS: Benchmarking Constrained Optimization in LLM Agents ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-18T08:46:07.880209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation cdcb1055-214e-49e5-9335-e7073b300fa1 · inbound

Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory cites this paper.

Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T18:03:37.341452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbc00d68-b687-49dd-93f7-3e8128ef1c4f · inbound

One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents cites this paper.

One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T14:20:31.274272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7671de91-1088-487d-ae66-8bcdfc4e3373 · inbound

Gecko: A Simulation Environment with Stateful Feedback for Refining Agent Tool Calls cites this paper.

Gecko: A Simulation Environment with Stateful Feedback for Refining Agent Tool Calls ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T21:46:33.312636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e99cad8-ad5f-4498-af27-6b33117f8164 · inbound

Mind the Sim2Real Gap in User Simulation for Agentic Tasks cites this paper.

Mind the Sim2Real Gap in User Simulation for Agentic Tasks ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T05:51:29.394088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 303b2907-089e-4a5c-b292-3012610353e9 · inbound

Beyond Benchmark Islands: Toward Representative Trustworthiness Evaluation for Agentic AI cites this paper.

Beyond Benchmark Islands: Toward Representative Trustworthiness Evaluation for Agentic AI ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-22T10:21:23.276299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f512d45f-3c96-4cc1-8cb9-a12791cb8bc4 · inbound

Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills cites this paper.

Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-13T09:29:51.204678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b64fd55d-3560-4fae-b973-1d1382b4c779 · inbound

The A-R Behavioral Space: Execution-Level Profiling of Tool-Using Language Model Agents in Organizational Deployment cites this paper.

The A-R Behavioral Space: Execution-Level Profiling of Tool-Using Language Model Agents in Organizational Deployment ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:41:02.948205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation cb9d7391-7d34-42db-a282-a7f59a02b766 · inbound

The A-R Behavioral Space: Execution-Level Profiling of Tool-Using Language Model Agents in Organizational Deployment cites this paper.

The A-R Behavioral Space: Execution-Level Profiling of Tool-Using Language Model Agents in Organizational Deployment ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-12T21:35:10.173253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9d309d2-bd28-4d6d-b504-e79a0a1ae000 · inbound

Cutscene Agent: An LLM Agent Framework for Automated 3D Cutscene Generation cites this paper.

Cutscene Agent: An LLM Agent Framework for Automated 3D Cutscene Generation ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:41:25.973584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 78643d9a-d7a8-4f1b-9013-46192bceb7f3 · inbound

Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety cites this paper.

Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-05-22T05:51:07.975780Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation bf0365b3-03c4-4603-84ae-bfa4a8c932e4 · inbound

Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety cites this paper.

Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-05-25T06:06:43.057004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 77ad442d-6a89-4507-8670-4154703a5604 · inbound

VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions cites this paper.

VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 51

Resolution: verified exact; arxiv_id, observed 2026-06-29T17:13:44.721016Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5df495e5-804e-45c2-8469-186133156986 · inbound

Designing for Doubt: The Case for Informed Abstention in Autonomous Agents cites this paper.

Designing for Doubt: The Case for Informed Abstention in Autonomous Agents ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-07-01T23:46:23.684356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5fa44723-d6a5-4bca-a7d3-fb6e66293b35 · inbound

Compositional Skill Routing for LLM Agents: Decompose, Retrieve, and Compose cites this paper.

Compositional Skill Routing for LLM Agents: Decompose, Retrieve, and Compose ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-07-03T21:18:59.725697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 91ffc82a-47cf-4552-9eec-f94d765e5ebb · inbound

Beyond Next-Token Prediction: An RLVR Proof of Concept for Tool-Use Agents on Atlassian Workflows cites this paper.

Beyond Next-Token Prediction: An RLVR Proof of Concept for Tool-Use Agents on Atlassian Workflows ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-07-03T20:18:55.533094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 29be73f0-dce0-478d-bf47-45b0d02832d4 · inbound

AppWorld-UL: Benchmarking Diverse Agent-User Interactions for Tool-Use cites this paper.

AppWorld-UL: Benchmarking Diverse Agent-User Interactions for Tool-Use ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-02T07:36:53.348031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63af01f3-1fd4-4326-a9cd-47ddd31efa8f · inbound

Quo Vadis, World Modeling? cites this paper.

Quo Vadis, World Modeling? ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 114

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:06.175548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5eea9802-d3ed-463f-8f49-be91be9f9510 · inbound

Diagnosing Tool-Selection Reasoning in LLM Agents with Canary Tools cites this paper.

Diagnosing Tool-Selection Reasoning in LLM Agents with Canary Tools ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T18:11:39.396840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers