Paper Citation Record · LEDGER

Scaling Test-time Compute for LLM Agents

As of 10 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 16 inbound Pith citation observations for arXiv:2506.12928.

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

pith.paper-citation-record.v1
2506.12928 v1

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:41:48.421514Z

measured 48 of 48 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 16 of 16 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-08T10:20:42.130163Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-22T06:24:40.465949Z

Reference resolution

32 of 32 outbound references displayed

verified exact0
verified fuzzy3
unresolved29
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ead75c48-fe3f-489f-b8b7-8104120d74c8 · outbound

This paper cites an unresolved cited work.

Scaling Test-time Compute for LLM Agents Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:41:49.377187Z

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 f453d572-e8d7-42f0-b855-03bab1520a0b · outbound

This paper cites TapeAgents: a Holistic Framework for Agent Development and Optimization.

Scaling Test-time Compute for LLM Agents TapeAgents: a Holistic Framework for Agent Development and Optimization

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.283939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16d899cb-5f15-49f7-84dd-93289ab9351c · outbound

This paper cites Beeching, L.

Scaling Test-time Compute for LLM Agents Beeching, L

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:41:49.360522Z

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 5e5c012c-e752-40d3-b687-f9e5a26ffd5c · outbound

This paper cites an unresolved cited work.

Scaling Test-time Compute for LLM Agents Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.293050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f08d72e9-e786-4ef7-ae03-19a4b8ca0356 · outbound

This paper cites an unresolved cited work.

Scaling Test-time Compute for LLM Agents Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:41:49.345844Z

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 959bf115-9cbd-424c-b39b-23232d1d270a · outbound

This paper cites Faria and N.

Scaling Test-time Compute for LLM Agents Faria and N

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.301350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e291ef7-b138-4076-91b6-2f0d96ab0c20 · outbound

This paper cites Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks.

Scaling Test-time Compute for LLM Agents Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.306102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2331d8e-077d-446b-98f9-f65c1da3dc75 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Scaling Test-time Compute for LLM Agents DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.310739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1684e9e7-5946-4bd6-b138-2cc313d9364c · outbound

This paper cites MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework.

Scaling Test-time Compute for LLM Agents MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.319126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ca74235-d0d8-4eae-807c-f11b019e2462 · outbound

This paper cites OpenAI o1 System Card.

Scaling Test-time Compute for LLM Agents OpenAI o1 System Card

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.323210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c63f3175-2472-4843-9ce2-89045992f51e · outbound

This paper cites VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks.

Scaling Test-time Compute for LLM Agents VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.327648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1288602c-0046-48da-bdbc-eaa49d75aa3a · outbound

This paper cites an unresolved cited work.

Scaling Test-time Compute for LLM Agents Unresolved cited work

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.331771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 439ff490-1b63-40a1-866d-b56c2015fab4 · outbound

This paper cites Training Language Models to Self-Correct via Reinforcement Learning.

Scaling Test-time Compute for LLM Agents Training Language Models to Self-Correct via Reinforcement Learning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.335591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21827c23-70e0-4de2-9183-1a3345be1115 · outbound

This paper cites an unresolved cited work.

Scaling Test-time Compute for LLM Agents Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:41:49.330821Z

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 ebd40cb0-8f36-42fb-889f-eaa512995a70 · outbound

This paper cites Search-o1: Agentic Search-Enhanced Large Reasoning Models.

Scaling Test-time Compute for LLM Agents Search-o1: Agentic Search-Enhanced Large Reasoning Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.343427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d691e17-8845-48d9-9b29-8ad550720560 · outbound

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

Scaling Test-time Compute for LLM Agents WebThinker: Empowering Large Reasoning Models with Deep Research Capability

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.347863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb48ef7b-99d4-4531-ab86-8dda35c847a0 · outbound

This paper cites Liang, J.

Scaling Test-time Compute for LLM Agents Liang, J

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.352324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e893122c-ad37-4a27-a137-ea9315d31a5f · outbound

This paper cites Bag of Tricks for Inference-time Computation of LLM Reasoning.

Scaling Test-time Compute for LLM Agents Bag of Tricks for Inference-time Computation of LLM Reasoning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.356267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b527d30a-272e-4fb3-9d5c-64ecec4f111a · outbound

This paper cites Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling.

Scaling Test-time Compute for LLM Agents Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.364617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8de97828-6ac3-4f9c-ad77-8a44bb69ece8 · outbound

This paper cites Mialon, C.

Scaling Test-time Compute for LLM Agents Mialon, C

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:41:49.315918Z

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 f4ae9f3d-3792-4c18-b3d9-f7059aff5258 · outbound

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

Scaling Test-time Compute for LLM Agents ToolRL: Reward is All Tool Learning Needs

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.372875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30d0d066-64fe-407f-b1f6-1820f5f7e9c8 · outbound

This paper cites repository.

Scaling Test-time Compute for LLM Agents repository

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:41:49.300615Z

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 7d703542-bcf2-4533-851b-c7559cc76899 · outbound

This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.

Scaling Test-time Compute for LLM Agents Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.380796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84872660-fed1-423e-b193-bf34ebd254ca · outbound

This paper cites an unresolved cited work.

Scaling Test-time Compute for LLM Agents Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.384860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 929e9e6b-b2dc-4f8c-90d0-fff4808e710f · outbound

This paper cites A Comparative Study on Reasoning Patterns of OpenAI's o1 Model.

Scaling Test-time Compute for LLM Agents A Comparative Study on Reasoning Patterns of OpenAI's o1 Model

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.388696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc793ea2-6375-4da3-84d0-54abef17e3a4 · outbound

This paper cites Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models.

Scaling Test-time Compute for LLM Agents Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.397018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bc32b7b-4c2f-49be-a1ba-f3b1bd33099b · outbound

This paper cites OS-Copilot: Towards Generalist Computer Agents with Self-Improvement.

Scaling Test-time Compute for LLM Agents OS-Copilot: Towards Generalist Computer Agents with Self-Improvement

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.400792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97f62b28-d998-499f-aa58-9eb0923c1a72 · outbound

This paper cites Self-rewarding correction for mathematical reasoning.

Scaling Test-time Compute for LLM Agents Self-rewarding correction for mathematical reasoning

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.404875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60284b91-56cd-4e56-bbea-0ef459298217 · outbound

This paper cites WebArena: A Realistic Web Environment for Building Autonomous Agents.

Scaling Test-time Compute for LLM Agents WebArena: A Realistic Web Environment for Building Autonomous Agents

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.409072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d6593bd-d119-42e1-9cf7-7f035bae4949 · outbound

This paper cites RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text.

Scaling Test-time Compute for LLM Agents RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.413118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 524c4b4f-084c-431f-bb09-1a10a6336551 · outbound

This paper cites Agents: An Open-source Framework for Autonomous Language Agents.

Scaling Test-time Compute for LLM Agents Agents: An Open-source Framework for Autonomous Language Agents

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.417200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 752036d6-2d75-4ae0-8470-afc36563930b · outbound

This paper cites Symbolic Learning Enables Self-Evolving Agents.

Scaling Test-time Compute for LLM Agents Symbolic Learning Enables Self-Evolving Agents

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T00:41:48.421514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation c74b1a72-ace6-4ffb-8732-1be03af50989 · inbound

SSRL: Self-Search Reinforcement Learning cites this paper.

SSRL: Self-Search Reinforcement Learning Scaling Test-time Compute for LLM Agents

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-05T20:17:13.855017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bc80da3-53d8-4761-b32d-2fd4cf67c913 · inbound

Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL cites this paper.

Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL Scaling Test-time Compute for LLM Agents

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-05T23:57:37.738674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3642bd2-4c47-4b87-893b-f479cf8520fd · inbound

Evaluation-driven Scaling for Scientific Discovery cites this paper.

Evaluation-driven Scaling for Scientific Discovery Scaling Test-time Compute for LLM Agents

Reference 176

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:26:05.399233Z

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 782feeaa-f415-49e3-a1e3-c9b58861e895 · inbound

Inference-Time Budget Control for LLM Search Agents cites this paper.

Inference-Time Budget Control for LLM Search Agents Scaling Test-time Compute for LLM Agents

Reference 80

Resolution: malformed identifier; arxiv_id, observed 2026-05-11T19:31:07.932732Z

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 4aea3837-ef7b-40e2-a7d4-23fcc92696ec · inbound

A Communication-Theoretic Framework for LLM Agents: Cost-Aware Adaptive Reliability cites this paper.

A Communication-Theoretic Framework for LLM Agents: Cost-Aware Adaptive Reliability Scaling Test-time Compute for LLM Agents

Reference 66

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T03:06:19.459616Z

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 aece34da-0f04-4b99-9b93-dce8ded68d13 · inbound

The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck cites this paper.

The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck Scaling Test-time Compute for LLM Agents

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-13T01:32:02.859506Z

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 02bd3d7b-4e54-42c7-bf88-5668d8ebdc51 · inbound

Self-Pruned Key-Value Attention: Learning When to Write by Predicting Future Utility cites this paper.

Self-Pruned Key-Value Attention: Learning When to Write by Predicting Future Utility Scaling Test-time Compute for LLM Agents

Reference 66

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T05:39:47.911666Z

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 5640f2b7-5067-48bb-87a6-90f722a0c543 · inbound

TClone: Low-Latency Forking of Live GUI Environments for Computer-Use Agents cites this paper.

TClone: Low-Latency Forking of Live GUI Environments for Computer-Use Agents Scaling Test-time Compute for LLM Agents

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-19T22:57:50.188959Z

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 cd3253b7-eea2-4e30-9d1b-8a9bfee353ef · inbound

ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling cites this paper.

ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling Scaling Test-time Compute for LLM Agents

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-22T05:54:38.586904Z

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 9847c3d3-f2bf-4878-bfff-f2fbe9fefaa5 · inbound

IdleSpec: Exploiting Idle Time via Speculative Planning for LLM Agents cites this paper.

IdleSpec: Exploiting Idle Time via Speculative Planning for LLM Agents Scaling Test-time Compute for LLM Agents

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-22T06:24:40.468558Z

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 9e91e587-47b1-422f-9eaf-0e96bb217707 · inbound

CurveShift: Is Agent Progress Scalar? Separating Level from Shape cites this paper.

CurveShift: Is Agent Progress Scalar? Separating Level from Shape Scaling Test-time Compute for LLM Agents

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T00:43:21.854604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7921223b-3ee0-4633-9e0a-af2fe5e9b1f8 · inbound

Cognitive Demand Steering for Adaptive Meta-Reasoning in Large Language Models cites this paper.

Cognitive Demand Steering for Adaptive Meta-Reasoning in Large Language Models Scaling Test-time Compute for LLM Agents

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T00:24:22.837114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41ae6c14-ffbc-4112-9389-4ca2b5dde8ee · inbound

CRISP: Critical Step Perception for Training Efficient Deep Search Agents cites this paper.

CRISP: Critical Step Perception for Training Efficient Deep Search Agents Scaling Test-time Compute for LLM Agents

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T19:21:37.747063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e883c10c-9899-4482-8c63-faedb87f389e · inbound

CRISP: Critical Step Perception for Training Efficient Deep Search Agents cites this paper.

CRISP: Critical Step Perception for Training Efficient Deep Search Agents Scaling Test-time Compute for LLM Agents

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T00:13:41.203958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddbf3e45-f320-4df8-b7ba-3f42e3441114 · inbound

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds cites this paper.

Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds Scaling Test-time Compute for LLM Agents

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-05T04:26:29.391821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e914543-90f7-4f96-bbdc-5af9c64d2bb7 · inbound

SkillTV-Bench: Benchmarking How Well Judges Perform on Skill-Augmented Agentic Execution cites this paper.

SkillTV-Bench: Benchmarking How Well Judges Perform on Skill-Augmented Agentic Execution Scaling Test-time Compute for LLM Agents

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-08T10:20:42.130163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.