Paper Citation Record · LEDGER

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use

As of 19 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 5 inbound Pith citation observations for arXiv:2412.15495.

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

pith.paper-citation-record.v1
2412.15495 v2

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T11:26:49.109273Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T16:08:41.926916Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T14:37:03.249565Z

Reference resolution

37 of 37 outbound references displayed

verified exact1
verified fuzzy1
unresolved35
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 40f9f706-b5fe-44bd-b4b8-d6375482a58a · outbound

This paper cites online" 'onlinestring :=.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use online" 'onlinestring :=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:48.954889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20cd0117-114b-43f5-ae38-14672b563ccd · outbound

This paper cites write newline.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:48.959958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb3a244e-2477-4a8f-8789-961ac0e973ed · outbound

This paper cites Qwen Technical Report.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use Qwen Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:48.964552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75c57adf-e12a-4894-8b5b-b3ab4e0d13f5 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use Evaluating Large Language Models Trained on Code

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:48.969776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71b5185a-0378-4881-bc48-391914ed4b9b · outbound

This paper cites How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:48.974404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a15d9d7b-7dc9-4f6a-9eea-3aec7068fb50 · outbound

This paper cites T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:48.978958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68b89d42-14aa-4e27-9315-0feb08f7d57c · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use Training Verifiers to Solve Math Word Problems

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:48.983771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 917e097f-8365-4866-a660-5ef042c87a9b · outbound

This paper cites an unresolved cited work.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-11T11:26:49.512165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 42e46a9a-dd6e-4171-94f6-709c11ff616e · outbound

This paper cites ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:48.992291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation deab990d-ac6d-4dca-9d1e-20e7549b180b · outbound

This paper cites an unresolved cited work.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:48.996460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fd7ce65-5d8f-47a4-892b-6280f15961dc · outbound

This paper cites an unresolved cited work.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use Unresolved cited work

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:49.000262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45318174-4410-4123-bee3-2fa07cf87a0d · outbound

This paper cites an unresolved cited work.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use Unresolved cited work

Reference 12

Resolution: verified exact; doi, observed 2026-08-11T11:26:49.339134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 92db2a13-33c1-447c-a444-6152481574ea · outbound

This paper cites GPT-4 Technical Report.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use GPT-4 Technical Report

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:49.009537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 224e8d7b-0e89-4d3a-8904-1524300a1df3 · outbound

This paper cites Patil, Tianjun Zhang, Xin Wang, and Joseph E.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use Patil, Tianjun Zhang, Xin Wang, and Joseph E

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:26:49.486796Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ba58f312-46ec-4ca8-bc86-ce2c319a0448 · outbound

This paper cites Tool Learning with Foundation Models.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use Tool Learning with Foundation Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:49.018363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 492161b4-d8f7-4be9-bd4a-032e27062901 · outbound

This paper cites an unresolved cited work.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-11T11:26:49.475306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f64bc921-057e-4fc1-afbe-478da8ca5ac4 · outbound

This paper cites an unresolved cited work.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:49.026660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 633b6cc9-25a2-41be-9163-5895524193e8 · outbound

This paper cites Code Llama: Open Foundation Models for Code.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use Code Llama: Open Foundation Models for Code

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:49.030476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f7b246b-8b93-472a-bcbb-13386e07d033 · outbound

This paper cites Proximal Policy Optimization Algorithms.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use Proximal Policy Optimization Algorithms

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:49.034831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8edc89e2-0d54-4ee4-a728-abea66a9faac · outbound

This paper cites RestGPT: Connecting Large Language Models with Real-World RESTful APIs.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use RestGPT: Connecting Large Language Models with Real-World RESTful APIs

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:49.039636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 132a8249-faad-4d51-bc6e-c586fcaed279 · outbound

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

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:49.044046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aee82c11-7bd2-4641-8436-47b86bcef5c1 · outbound

This paper cites an unresolved cited work.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-11T11:26:49.463743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 33fddb24-2143-443c-b932-e9b29c8c0729 · outbound

This paper cites an unresolved cited work.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:49.052121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07382bcf-ecc9-4fa1-a46b-e43292de3969 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:49.056141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df62379b-7222-4eae-b9de-c17ba9e4dd4c · outbound

This paper cites Knowledge Mechanisms in Large Language Models: A Survey and Perspective.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use Knowledge Mechanisms in Large Language Models: A Survey and Perspective

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:49.059983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 041ac1e6-97b1-48e2-aefe-d219decd1e5a · outbound

This paper cites Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmark.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmark

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:49.064264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b8e9ef9-9b1d-416c-a810-b6c816c4d066 · outbound

This paper cites The Rise and Potential of Large Language Model Based Agents: A Survey.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use The Rise and Potential of Large Language Model Based Agents: A Survey

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:49.068541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 594f2d83-0660-463a-8ac2-bd91d08f8e77 · outbound

This paper cites Qwen2 Technical Report.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use Qwen2 Technical Report

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:49.072942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be708d5a-c7ba-4060-9e98-9f246c8a2ca5 · outbound

This paper cites Qwen2.5 Technical Report.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use Qwen2.5 Technical Report

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:49.077294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82590aca-53ed-41cf-83c3-daf77fba946f · outbound

This paper cites an unresolved cited work.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:49.081455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57690675-afcc-4630-a36a-1ab6b5d68223 · outbound

This paper cites A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:49.085472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 880068f6-1844-4321-a6bf-871083ef8a69 · outbound

This paper cites an unresolved cited work.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-11T11:26:49.445254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 79a0e127-2ca9-4cea-a192-436d659d97a3 · outbound

This paper cites an unresolved cited work.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:49.093127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f0ff889-a5d2-4ba4-91d6-e9ebe8bbb1d2 · outbound

This paper cites an unresolved cited work.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-11T11:26:49.432429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation be40c297-d447-476a-bc59-8848e72445ab · outbound

This paper cites 60 Data Points are Sufficient to Fine-Tune LLMs for Question-Answering.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use 60 Data Points are Sufficient to Fine-Tune LLMs for Question-Answering

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:49.100716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42a7830e-51b2-450a-86d8-edfcd9e63d53 · outbound

This paper cites ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:49.105197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e421fdc-8bce-4645-b0e4-d561f2a9d50a · outbound

This paper cites ToolChain: Efficient Action Space Navigation in Large Language Models with A Search.

TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T11:26:49.109273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 890ce412-71a4-481c-9df1-802ba3eac1d4 · inbound

MulDimIF: A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models cites this paper.

MulDimIF: A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-22T15:46:45.174141Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation be99b73b-b1c7-4786-afd4-c5af248cafcf · inbound

AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning cites this paper.

AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-15T16:08:41.926916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 311788f4-fc26-473c-8f9d-75f2fc0e58d5 · inbound

Failure Makes the Agent Stronger: Enhancing Accuracy through Structured Reflection for Reliable Tool Interactions cites this paper.

Failure Makes the Agent Stronger: Enhancing Accuracy through Structured Reflection for Reliable Tool Interactions TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T15:01:31.388765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ac3db9b8-6648-40f0-8b87-65646d0ba322 · inbound

When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents cites this paper.

When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use

Reference 49

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T05:52:22.060134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7a37d445-5a20-4989-8bb3-735b81527a6e · inbound

WebMCP Tool Surface Poisoning: Runtime Manipulation Attacks on LLM Agents cites this paper.

WebMCP Tool Surface Poisoning: Runtime Manipulation Attacks on LLM Agents TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use

Reference 23

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T14:37:03.251077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.