Paper Citation Record · LEDGER

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks

As of 19 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 7 inbound Pith citation observations for arXiv:2508.13143.

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

pith.paper-citation-record.v1
2508.13143 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T17:19:51.873664Z

measured 40 of 40 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-08T10:20:42.058799Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-25T04:26:38.042285Z

Reference resolution

33 of 33 outbound references displayed

verified exact0
verified fuzzy18
unresolved15
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0b859add-951e-47b5-b3ed-7250b0ba4d21 · outbound

This paper cites TaskWeaver: A Code-First Agent Framework.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks TaskWeaver: A Code-First Agent Framework

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T17:19:51.742803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 132a18b8-c8d5-446d-8c7e-351c836e48fd · outbound

This paper cites Autogen: Enabling next-gen LLM applications via multi- agent conversations,.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks Autogen: Enabling next-gen LLM applications via multi- agent conversations,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:19:52.280593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation df860d48-b452-4c3b-b986-be57d8f0f674 · outbound

This paper cites CodeAgent: Enhancing code generation with tool-integrated agent systems for real-world repo-level coding challenges,.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks CodeAgent: Enhancing code generation with tool-integrated agent systems for real-world repo-level coding challenges,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:19:52.267893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0f70a63c-72a9-4a61-b1e6-faecf997c16d · outbound

This paper cites Executable code actions elicit better llm agents,.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks Executable code actions elicit better llm agents,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:19:52.254063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation afcf02cd-bb57-4233-9f3c-22867bfca568 · outbound

This paper cites Solving challenging math word problems using gpt-4 code interpreter with code-based self-verification,.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks Solving challenging math word problems using gpt-4 code interpreter with code-based self-verification,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:19:52.240211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 39966860-d1b3-41e3-8f0c-2b3f2a872f0f · outbound

This paper cites CIBench: Evaluating Your LLMs with a Code Interpreter Plugin.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks CIBench: Evaluating Your LLMs with a Code Interpreter Plugin

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T17:19:51.764153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 486df829-a9a7-4ac3-86c5-19c55f4e3f19 · outbound

This paper cites Data Dialogue with ChatGPT: Using Code Interpreter to Simulate and Analyse Experimental Data.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks Data Dialogue with ChatGPT: Using Code Interpreter to Simulate and Analyse Experimental Data

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T17:19:51.769010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d996104-93ca-42f6-b079-926f71cb59ed · outbound

This paper cites Webpilot: A versatile and autonomous multi-agent system for web task execution with strategic exploration,.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks Webpilot: A versatile and autonomous multi-agent system for web task execution with strategic exploration,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:19:52.226686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 14af42c9-f294-4aa1-831f-833ed575c4d7 · outbound

This paper cites Redcode: Risky code execution and generation benchmark for code agents,.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks Redcode: Risky code execution and generation benchmark for code agents,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T17:19:51.777304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a87fecc5-a8d4-48ce-9b1d-9ea05a7f7655 · outbound

This paper cites Large Language Model-Based Agents for Software Engineering: A Survey.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks Large Language Model-Based Agents for Software Engineering: A Survey

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T17:19:51.781158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b941e0d-4dcd-4cab-ade5-e2ec7ef6ca3a · outbound

This paper cites Llm-based multi-agent systems for software engineering: Literature review, vision, and the road ahead,.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks Llm-based multi-agent systems for software engineering: Literature review, vision, and the road ahead,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:19:52.204562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation dd9554a4-7dff-4c04-9c3b-8ce2ecf791b5 · outbound

This paper cites Demystifying llm-based software engineering agents,.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks Demystifying llm-based software engineering agents,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:19:52.190809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ce0f2418-a4a7-4b4e-82a8-97aa0fd538cc · outbound

This paper cites Self-collaboration code generation via chatgpt,.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks Self-collaboration code generation via chatgpt,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T17:19:51.793365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e1fd98c-f23d-4115-8467-c2e54db0ca76 · outbound

This paper cites MARE: Multi-Agents Collaboration Framework for Requirements Engineering.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks MARE: Multi-Agents Collaboration Framework for Requirements Engineering

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T17:19:51.797921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8e0a342-7230-4f28-8ffd-4977df7b8829 · outbound

This paper cites Requirements are all you need: From requirements to code with llms,.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks Requirements are all you need: From requirements to code with llms,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T17:19:51.802907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8aa8365b-eb61-46c8-b6ee-a451620c4b9c · outbound

This paper cites MarsCode Agent: AI-native Automated Bug Fixing.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks MarsCode Agent: AI-native Automated Bug Fixing

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T17:19:51.806704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a663a997-2139-4c4d-9187-c37c3ddafd7d · outbound

This paper cites Cycle: Learning to self- refine the code generation,.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks Cycle: Learning to self- refine the code generation,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:19:52.161275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 77cc3a4a-abcc-43ff-81c5-a79ed0233ee2 · outbound

This paper cites Self-planning code generation with large language models,.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks Self-planning code generation with large language models,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T17:19:51.814865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb548101-a0d1-40d0-ae6f-ac13b1f5dbb3 · outbound

This paper cites Swt-bench: Testing and validating real-world bug-fixes with code agents,.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks Swt-bench: Testing and validating real-world bug-fixes with code agents,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:19:52.139286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 19c2dbed-31a0-4942-8cb4-d552127c0739 · outbound

This paper cites Make llm a testing expert: Bringing human-like interaction to mobile gui testing via functionality-aware decisions,.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks Make llm a testing expert: Bringing human-like interaction to mobile gui testing via functionality-aware decisions,

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:19:52.125785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ee73889a-f54e-4a17-98a3-e39bdf63c076 · outbound

This paper cites Chatunitest: A framework for llm-based test generation,.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks Chatunitest: A framework for llm-based test generation,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T17:19:51.826907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 101b8ae6-0b90-46f8-8abb-0bd5abac6f65 · outbound

This paper cites Infiagent-dabench: evaluating agents on data analysis tasks,.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks Infiagent-dabench: evaluating agents on data analysis tasks,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:19:52.105708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1c8d51f8-b7b9-4cb0-8bcb-21fae86dae5c · outbound

This paper cites Super: Evaluating agents on setting up and executing tasks from research repositories,.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks Super: Evaluating agents on setting up and executing tasks from research repositories,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:19:52.090688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 8035ecc3-05f8-4840-80d8-4e59ce525bda · outbound

This paper cites $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T17:19:51.838765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67b0c347-4043-43bd-93f1-c234ef6e3ed8 · outbound

This paper cites MetaGPT: Meta programming for a multi-agent collaborative framework,.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks MetaGPT: Meta programming for a multi-agent collaborative framework,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:19:52.076511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f1841ab7-e1a5-4eef-847d-9777b13c8713 · outbound

This paper cites an unresolved cited work.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T17:19:51.847048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aefe7158-e617-416e-b9d5-0b0c094368f4 · outbound

This paper cites Gpt-4o mini,.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks Gpt-4o mini,

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:19:52.054404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation bcbf1272-6d2c-4349-a632-fba873876dbe · outbound

This paper cites Multi- stage large language model pipelines can outperform gpt-4o in relevance assessment,.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks Multi- stage large language model pipelines can outperform gpt-4o in relevance assessment,

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:19:52.040811Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c05875ca-3556-4be6-84bc-910169701c21 · outbound

This paper cites React: Synergizing reasoning and acting in language models,.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks React: Synergizing reasoning and acting in language models,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T17:19:51.858815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b248f53f-df27-4f4c-ada2-e3c60889f4e2 · outbound

This paper cites Reasoning with language model is planning with world model,.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks Reasoning with language model is planning with world model,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:19:52.018133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation dcb32af2-a2bf-4939-9385-17f973d52429 · outbound

This paper cites Automated program repair via conversation: Fixing 162 out of 337 bugs for $0.42 each using chatgpt,.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks Automated program repair via conversation: Fixing 162 out of 337 bugs for $0.42 each using chatgpt,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T17:19:51.866296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa93284e-e4c2-4e8a-af87-22e013d59cee · outbound

This paper cites Perfcodegen: Improving performance of llm generated code with execution feedback,.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks Perfcodegen: Improving performance of llm generated code with execution feedback,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:19:51.997652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2a697131-4fe8-467d-8137-8d622e8c72e4 · outbound

This paper cites Self-edit: Fault-aware code editor for code generation,.

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks Self-edit: Fault-aware code editor for code generation,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T17:19:51.984781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Pith citing papers

Observation d0b511dc-7e95-42fe-896e-5aaf32b7ae16 · inbound

Characterizing Faults in Agentic AI: A Taxonomy of Types, Symptoms, and Root Causes cites this paper.

Characterizing Faults in Agentic AI: A Taxonomy of Types, Symptoms, and Root Causes Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-15T14:46:08.247213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 01ff125c-8a27-4781-b121-41c694677c4c · inbound

Profile-Then-Reason: Bounded Semantic Complexity for Tool-Augmented Language Agents cites this paper.

Profile-Then-Reason: Bounded Semantic Complexity for Tool-Augmented Language Agents Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:03:01.282736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation add86010-c736-43ab-9f90-8bea8dd87bdc · inbound

When Agents Look the Same: Quantifying Distillation-Induced Similarity in Tool-Use Behaviors cites this paper.

When Agents Look the Same: Quantifying Distillation-Induced Similarity in Tool-Use Behaviors Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T14:16:17.896521Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b9206f08-eb4b-4ef2-aa0c-c5c37f9572a0 · inbound

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

Inference-Time Budget Control for LLM Search Agents Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-11T19:31:07.777341Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f9c724bb-3eab-4df4-83d3-c6aa3bf6de69 · inbound

When Planning Fails Despite Correct Execution: On Epistemic Calibration for LLM-Based Multi-Agent Systems cites this paper.

When Planning Fails Despite Correct Execution: On Epistemic Calibration for LLM-Based Multi-Agent Systems Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-25T04:26:38.045622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 85e33e3a-a616-403b-80f7-eba747086055 · inbound

Failure as a Process: An Anatomy of CLI Coding Agent Trajectories cites this paper.

Failure as a Process: An Anatomy of CLI Coding Agent Trajectories Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-13T02:31:04.773248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a4d8dca-9e04-46be-bc1c-95eef9990c49 · 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 Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-08T10:20:42.058799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.