Paper Citation Record · LEDGER

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning

As of 11 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 4 inbound Pith citation observations for arXiv:2604.09813.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2604.09813 v1

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T17:42:57.596073Z

measured 32 of 32 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-15T10:51:49.150058Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-07-03T06:17:41.457622Z

Reference resolution

28 of 28 outbound references displayed

verified exact20
verified fuzzy2
unresolved0
parse uncertain0
malformed identifier1
metadata mismatch5

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2a48a16c-d056-44fb-abb2-bd30a5ea30d4 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-11T06:15:58.383999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2e1ef6d0-3e73-4dca-b380-23626a4f0f54 · outbound

This paper cites ACEBench: A comprehensive evaluation of LLM tool usage.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning ACEBench: A comprehensive evaluation of LLM tool usage

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T09:21:42.412735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0228cd66-9920-4712-8975-047fea47bd8b · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning Training Verifiers to Solve Math Word Problems

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-11T06:15:58.314264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a12954aa-5646-4123-8c45-5fdc45970949 · outbound

This paper cites DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-11T06:15:58.352308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3b2fdd94-5aee-4d3f-bfab-ed9564a2531c · outbound

This paper cites Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:15:58.434072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3bee09b4-f1f4-4348-9163-07973725b8ee · outbound

This paper cites Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:15:58.424047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation df7b1487-51d2-4972-aa70-6f4f06910a27 · outbound

This paper cites ReTool: Reinforcement Learning for Strategic Tool Use in LLMs.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning ReTool: Reinforcement Learning for Strategic Tool Use in LLMs

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-13T18:42:39.160125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1027fdd9-2fe5-4d0a-8b08-6c6c3423f5e0 · outbound

This paper cites RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T06:15:58.374374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fedd6105-1690-436c-bbcf-1d32489fe748 · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning Measuring Mathematical Problem Solving With the MATH Dataset

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-11T06:15:58.320896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation dc0b1aa1-6763-4ac1-bf84-09758f5a60f2 · outbound

This paper cites LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-11T06:15:58.417191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1299f762-cae7-4419-bd9c-961a4541a2a2 · outbound

This paper cites Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T06:15:58.332777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation aaae4ea5-9845-40fa-ac4a-7087271c8ff9 · outbound

This paper cites WebThinker: Empowering Large Reasoning Models with Deep Research Capability.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning WebThinker: Empowering Large Reasoning Models with Deep Research Capability

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-16T19:14:25.573630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a2fa7022-5196-40be-9c43-36bd6202a94a · outbound

This paper cites ToolACE: Winning the Points of LLM Function Calling.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning ToolACE: Winning the Points of LLM Function Calling

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:15:58.399755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 337a4ddc-e4b1-44d0-823f-65e96345c522 · outbound

This paper cites TOOLVERIFIER: Generalization to New Tools via Self-Verification.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning TOOLVERIFIER: Generalization to New Tools via Self-Verification

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T06:15:58.348335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4f8a772b-a391-49ea-8f66-73147bec2f8c · outbound

This paper cites APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:15:58.440030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 41293427-805d-4b3b-9ba2-ff1f1a2d4cc7 · outbound

This paper cites ToolRL: Reward is All Tool Learning Needs.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning ToolRL: Reward is All Tool Learning Needs

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-14T00:26:48.594660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bb5e4a6c-96e2-418f-b15c-d07f9f1b7fda · outbound

This paper cites ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-11T06:15:58.427470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation af733ace-3d13-47ef-9b86-ef62003310d8 · outbound

This paper cites GPQA: A Graduate-Level Google-Proof Q&A Benchmark.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning GPQA: A Graduate-Level Google-Proof Q&A Benchmark

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-11T06:15:58.430570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 184d6aba-7896-488f-871c-4fccb92e99f3 · outbound

This paper cites MAG-V: A Multi-Agent Framework for Synthetic Data Generation and Verification.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning MAG-V: A Multi-Agent Framework for Synthetic Data Generation and Verification

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T06:15:58.359612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ad2b3bff-3eaf-4f4b-a720-2929b3984cec · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-11T06:15:58.369297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d9078486-3645-49ec-834b-94e382ce929d · outbound

This paper cites Learning to summarize from human feedback.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning Learning to summarize from human feedback

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-18T01:46:18.838660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2956b9cd-8e75-45cf-834e-dd5614a155ee · outbound

This paper cites ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-15T23:03:48.638764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c8f42a8a-04ff-4e18-bd40-d830c11ff778 · outbound

This paper cites Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:15:58.454071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 79092f1e-a2f9-4337-bc51-0762e73a6eab · outbound

This paper cites MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-11T15:51:14.588885Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a3b8105b-edbf-4495-a4e3-724718ddd16d · outbound

This paper cites Qwen2.5 Technical Report.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning Qwen2.5 Technical Report

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-05-11T06:15:58.387819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d058348d-18c5-4724-9f93-7e57fdc6e283 · outbound

This paper cites Tool zero: Training tool- augmented LLMs via pure RL from scratch.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning Tool zero: Training tool- augmented LLMs via pure RL from scratch

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T09:21:42.416492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f7167414-ff93-4c04-9fb4-de6f59864fb9 · outbound

This paper cites Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning

Reference 27

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T06:15:58.363701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 97607fd0-4a28-49a4-a0e6-f3e2e6b5f161 · outbound

This paper cites If none of the functions can be used, point it out.

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning If none of the functions can be used, point it out

Reference 28

Resolution: malformed identifier; raw_fallback, observed 2026-05-17T09:21:42.419917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Pith citing papers

Observation a3dce4b8-7dbf-4055-b5de-780c09e98c4f · inbound

Self-Harness: Harnesses That Improve Themselves cites this paper.

Self-Harness: Harnesses That Improve Themselves Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-07-03T01:37:30.758061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 839dbf13-bc8a-4ab0-8cf5-05b9beee734b · inbound

ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories cites this paper.

ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning

Reference 63

Resolution: verified exact; local_arxiv, observed 2026-07-03T06:17:41.458718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6564216d-952f-4fbc-9e07-2106d0e4b9a4 · inbound

ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories cites this paper.

ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-14T18:06:15.668254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91a0a6a0-d313-4f33-82b8-7b8caf8ad1a1 · inbound

ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories cites this paper.

ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-15T10:51:49.150058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.