Paper Citation Record · LEDGER

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents

As of 13 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 1 inbound Pith citation observation for arXiv:2605.18882.

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

pith.paper-citation-record.v1
2605.18882 v1

Coverage vector

measured 23 of 23 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-20T16:07:43.528608Z

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-30T20:47:41.031108Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

23 of 23 outbound references displayed

verified exact6
verified fuzzy15
unresolved0
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d921b53f-bf3a-45d3-bf0b-7bad0978ac5f · outbound

This paper cites OpenAI GPT-5 System Card.

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents OpenAI GPT-5 System Card

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-20T16:08:33.508171Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6a1b3530-5557-4466-851f-a6d62cdd6a3e · outbound

This paper cites Claude opus 4.6 system card.

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents Claude opus 4.6 system card

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T16:08:33.771591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5a185384-4537-4877-87f4-e73203053c7c · outbound

This paper cites Gemma 4 model card.

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents Gemma 4 model card

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T16:08:33.775188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 43b0c87f-5449-402e-a6b4-c603ce08da22 · outbound

This paper cites Qwen3.5: Accelerating productivity with native multimodal agents, February 2026.

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents Qwen3.5: Accelerating productivity with native multimodal agents, February 2026

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T16:08:33.767756Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4c8db2f8-ba6d-4f6e-83c8-54f34dd91cc6 · outbound

This paper cites Toolformer: Language models can teach themselves to use tools.

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents Toolformer: Language models can teach themselves to use tools

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T16:08:33.769747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 684f90c4-a597-472c-819d-156289a82fa1 · outbound

This paper cites Toolllm: Facilitating large language models to master 16000+ real-world APIs.

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents Toolllm: Facilitating large language models to master 16000+ real-world APIs

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T16:08:33.773440Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c67fc59c-7419-4b8d-b05d-8e6e3c141b1d · outbound

This paper cites Gorilla: Large Language Model Connected with Massive APIs.

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents Gorilla: Large Language Model Connected with Massive APIs

Reference 7

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T16:08:33.505281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation db14b60a-f078-4bef-acb8-6d1e8532f835 · outbound

This paper cites AFlow: Automating agentic workflow generation.

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents AFlow: Automating agentic workflow generation

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T16:08:33.759231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1597226d-03dd-4382-b9e0-a37bb249d553 · outbound

This paper cites Gemma 3 Technical Report.

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents Gemma 3 Technical Report

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-20T16:08:33.499401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e724c0f1-8fb1-45f2-bb59-73a22cd504d1 · outbound

This paper cites Ministral 3.

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents Ministral 3

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-20T16:08:33.496308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c4c96279-aab1-4a1f-bd8c-080c4aa91e75 · outbound

This paper cites When2call: When (not) to call tools.

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents When2call: When (not) to call tools

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T16:08:33.752586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation baa9ec18-277d-42c9-a003-b5da9911b47d · outbound

This paper cites Sparse autoencoders find highly interpretable features in language models.

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents Sparse autoencoders find highly interpretable features in language models

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T16:08:33.754662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 00955fc6-024d-4716-84da-21f9b969be71 · outbound

This paper cites Scaling and evaluating sparse autoencoders.

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents Scaling and evaluating sparse autoencoders

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T16:08:33.757005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c5daa985-6fc4-404b-b295-7a3f7601d3d4 · outbound

This paper cites Daniel Freeman, Theodore R.

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents Daniel Freeman, Theodore R

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T16:08:33.761411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f8041432-c8c9-4637-a961-42f3a0bdb675 · outbound

This paper cites MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning.

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-20T16:08:33.490050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c801592e-9562-4ad0-983e-d264963a0778 · outbound

This paper cites Narasimhan, and Yuan Cao.

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents Narasimhan, and Yuan Cao

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T16:08:33.748347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f25e3e7f-6857-4333-95be-8295ce093fa2 · outbound

This paper cites Agentbench: Evaluating llms as agents.

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents Agentbench: Evaluating llms as agents

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T16:08:33.765341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b592b5ba-50d9-42fe-bb3a-eaa412b11a82 · outbound

This paper cites Patil, Huanzhi Mao, Fanjia Yan, Charlie Cheng-Jie Ji, Vishnu Suresh, Ion Stoica, and Joseph E.

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents Patil, Huanzhi Mao, Fanjia Yan, Charlie Cheng-Jie Ji, Vishnu Suresh, Ion Stoica, and Joseph E

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T16:08:33.746414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e45c8cc3-02ac-4ad7-bb77-c34ccc5abefa · outbound

This paper cites Michaud, Stephen Casper, Max Tegmark, David Bau, Eric Todd, Atticus Geiger, Mor Geva, Jesse Hoogland, Daniel Murfet, and Tom McGrath.

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents Michaud, Stephen Casper, Max Tegmark, David Bau, Eric Todd, Atticus Geiger, Mor Geva, Jesse Hoogland, Daniel Murfet, and Tom McGrath

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T16:08:33.744433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b62257e4-3ace-4be4-84d6-90ba8cef42ac · outbound

This paper cites Towards monosemanticity: Decomposing language models with dictionary learning.Transformer Circuits Thread.

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents Towards monosemanticity: Decomposing language models with dictionary learning.Transformer Circuits Thread

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T16:08:33.750529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 40369072-b782-4c3e-832c-05e852df4b37 · outbound

This paper cites Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders.

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-20T16:08:33.493338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1151a622-023f-45f5-af30-1c7efcc6847f · outbound

This paper cites The Pile: An 800GB Dataset of Diverse Text for Language Modeling.

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-20T16:08:33.502236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c7c18536-15b2-42de-91cf-eba9b63f844f · outbound

This paper cites classification.

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents classification

Reference 23

Resolution: malformed identifier; raw_fallback, observed 2026-05-20T16:08:33.763415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Pith citing papers

Observation e261a5e2-b4cf-49a9-90cb-084e58e5188f · inbound

Do LLMs Know Their Vulnerable Scenarios? cites this paper.

Do LLMs Know Their Vulnerable Scenarios? To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-30T20:47:41.031108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.