Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction | Paper Citation Record

Observation 09d97e4f-ced6-45d7-b2c7-f740760deaba · outbound

This paper cites Many-shot in-context learning.Advances in Neural Information Processing Systems, 37:76930–76966, 2024.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Many-shot in-context learning.Advances in Neural Information Processing Systems, 37:76930–76966, 2024

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:31.971243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cd93409-239c-459f-aabe-a81841f4d6e6 · outbound

This paper cites AutoMix: Automatically Mixing Language Models.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction AutoMix: Automatically Mixing Language Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.022958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b72f677-7202-4924-9558-e84a1d72653a · outbound

This paper cites GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.077850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a557d41f-20aa-4b00-817f-a22960f39aba · outbound

This paper cites InProceedings of the 62nd Annual Meeting of the Association for Computational Linguis- tics (Volume 1: Long Papers), pages 12248–12267, 2024.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction InProceedings of the 62nd Annual Meeting of the Association for Computational Linguis- tics (Volume 1: Long Papers), pages 12248–12267, 2024

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.137007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 189ba2c5-240b-47dd-8b9b-3248219af6b5 · outbound

This paper cites Self-RAG: Learning to retrieve, generate, and critique through self-reflection.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Self-RAG: Learning to retrieve, generate, and critique through self-reflection

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.140785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80c5210e-e431-49a4-bc98-06596e564ebc · outbound

This paper cites Program Synthesis with Large Language Models.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Program Synthesis with Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.144679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9a07f0d-e26c-4c80-aaa5-58032f277c49 · outbound

This paper cites Digirl: Train- ingin-the-wilddevice-controlagentswithautonomous reinforcement learning.Advances in Neural Informa- tion Processing Systems, 37:12461–12495, 2024.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Digirl: Train- ingin-the-wilddevice-controlagentswithautonomous reinforcement learning.Advances in Neural Informa- tion Processing Systems, 37:12461–12495, 2024

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.148827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32950d6a-7f69-4603-b4ed-89caaa41b9e3 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Constitutional AI: Harmlessness from AI Feedback

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.153242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47acc963-bb6c-4f64-9f31-3004eb87f8b5 · outbound

This paper cites Longbench: A bilingual, multitask benchmark for long context understanding.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Longbench: A bilingual, multitask benchmark for long context understanding

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.157190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cbd9b77-0cb8-445d-be94-2dc0f90a379c · outbound

This paper cites CodeT: Code Generation with Generated Tests.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction CodeT: Code Generation with Generated Tests

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.160580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d078e36f-47f6-44cb-a93b-60be7de38413 · outbound

This paper cites FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.164506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68ecc026-c855-4dd6-b247-1378d728b4e4 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Evaluating Large Language Models Trained on Code

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.168031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c874b937-257f-4ef4-bd2f-47a0a4774bc9 · outbound

This paper cites Teaching large language models to self-debug.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Teaching large language models to self-debug

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.171640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b073000-76d2-40ae-9712-a8f8872eb97f · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Training Verifiers to Solve Math Word Problems

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.175234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f48e516-0c7c-4e28-bc03-41dc99ab008b · outbound

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

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.179467Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2fb1888-51f0-48fd-8924-dfa3ddd58756 · outbound

This paper cites Precise zero-shot dense retrieval without rel- evance labels.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Precise zero-shot dense retrieval without rel- evance labels

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.182753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96df189d-b461-4611-9233-1430c2a4a05d · outbound

This paper cites REALM: Retrieval- augmented language model pre-training.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction REALM: Retrieval- augmented language model pre-training

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.186272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af93ce11-40a2-4316-929a-f29a1c26016b · outbound

This paper cites Measuring massive multitask language under- standing.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Measuring massive multitask language under- standing

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.189460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd1acf69-ee37-487d-823e-9bc27a45faca · outbound

This paper cites MetaGPT: Meta programming for a multi-agent col- laborative framework.International Conference on Learning Representations, 2024.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction MetaGPT: Meta programming for a multi-agent col- laborative framework.International Conference on Learning Representations, 2024

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.193279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa226199-b19d-48e6-add2-59c7a12eb9c0 · outbound

This paper cites RULER: What's the Real Context Size of Your Long-Context Language Models?.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction RULER: What's the Real Context Size of Your Long-Context Language Models?

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.196910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e841e3bc-1a57-44dc-959a-0d6ebac2a071 · outbound

This paper cites SEAL: Synergistic Co-Evolution of Agents and Learning Environments.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction SEAL: Synergistic Co-Evolution of Agents and Learning Environments

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-08-16T00:33:34.206650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 51eb4269-139a-4e06-b618-13f06e4d30c0 · outbound

This paper cites Leveraging pas- sage retrieval with generative models for open domain question answering.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Leveraging pas- sage retrieval with generative models for open domain question answering

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.204786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 002df34c-bb15-4c7b-84a3-eed606ef1358 · outbound

This paper cites Atlas: Few-shot Learning with Retrieval Augmented Language Models.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Atlas: Few-shot Learning with Retrieval Augmented Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.208555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1426c6e-e4a0-4500-87fd-c8064ca820d1 · outbound

This paper cites Adaptive-rag: Learning to adapt retrieval-augmented large language models through question complexity.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Adaptive-rag: Learning to adapt retrieval-augmented large language models through question complexity

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.228347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75256c16-6b1b-4bf2-9c60-344eb5af9e3c · outbound

This paper cites Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik Narasimhan.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik Narasimhan

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.288079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f22a8f96-6674-4744-90b3-77beeff398b5 · outbound

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

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.416509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d91ba6c-99f5-49aa-a9cb-63cd2ee6690a · outbound

This paper cites Densepassageretrievalforopen-domain question answering.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Densepassageretrievalforopen-domain question answering

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.467329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 620349e2-6004-4fe6-a454-7177b30781fe · outbound

This paper cites DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.474145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6be8f683-fa64-4f16-92c4-505ba26e9f0c · outbound

This paper cites Decomposedprompting: Amodular approach for solving complex tasks.International Conference on Learning Representations, 2023.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Decomposedprompting: Amodular approach for solving complex tasks.International Conference on Learning Representations, 2023

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.478752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ae42f66-aeb2-46db-9777-42c899ab93d3 · outbound

This paper cites Language models can solve computer tasks.Advances in Neural Information Processing Systems, 36:39648– 39677, 2023.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Language models can solve computer tasks.Advances in Neural Information Processing Systems, 36:39648– 39677, 2023

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.481838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8515de51-d582-453a-bb2f-e1e49c602329 · outbound

This paper cites Large language modelsare zero-shotreasoners.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Large language modelsare zero-shotreasoners

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.484935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b40e6beb-36f6-425f-bd6f-e4328a11da63 · outbound

This paper cites RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.488403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08a108b0-374a-4483-a78c-86ff582a0635 · outbound

This paper cites Retrieval-augmented generation for knowledge- intensive nlp tasks.Advances in neural information processing systems, 33:9459–9474, 2020.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Retrieval-augmented generation for knowledge- intensive nlp tasks.Advances in neural information processing systems, 33:9459–9474, 2020

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.492546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5211ec49-0bb9-4d1e-bded-90916a296193 · outbound

This paper cites CAMEL: Communicative agents for mind exploration of large language model society.Advances in Neu- ral Information Processing Systems, 36:51991–52008, 2023.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction CAMEL: Communicative agents for mind exploration of large language model society.Advances in Neu- ral Information Processing Systems, 36:51991–52008, 2023

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:35.581738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ffa740c5-05f8-4e55-b9c9-ffb58f9373f5 · outbound

This paper cites LooGLE: Can Long-Context Language Models Understand Long Contexts?.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction LooGLE: Can Long-Context Language Models Understand Long Contexts?

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.498179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48ae8444-11cf-4995-945a-6bdd9cbe490f · outbound

This paper cites API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.555235Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7339dda7-b780-4ef4-9a17-47c79564b0b5 · outbound

This paper cites Rethinking the role of entropy in optimizing tool-use behaviors for large language model agents.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Rethinking the role of entropy in optimizing tool-use behaviors for large language model agents

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:35.571104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 82d101be-2327-4503-97b4-9f1b2144bb32 · outbound

This paper cites ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.695930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c273b47-1aa3-4ddb-a50d-f7eb068852f8 · outbound

This paper cites Holisticevaluationoflanguagemodels.InTransactions on Machine Learning Research, 2023.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Holisticevaluationoflanguagemodels.InTransactions on Machine Learning Research, 2023

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:35.499331Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 02fa0e63-0548-47d8-86b0-1d655b8ffab3 · outbound

This paper cites Let’s verify step by step.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Let’s verify step by step

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:35.399743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b560e841-de80-490f-b16d-3224831a7d2e · outbound

This paper cites Toxicchat: Unveiling hidden challenges of toxicity detection in real-world user-ai conversation.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Toxicchat: Unveiling hidden challenges of toxicity detection in real-world user-ai conversation

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:35.390237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 86a963b1-50dd-4db6-a4a5-f74944028721 · outbound

This paper cites Liu, Kevin Lin, John Hewitt, Ashwin Paran- jape, Michele Bevilacqua, Fabio Petroni, and Percy Liang.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Liu, Kevin Lin, John Hewitt, Ashwin Paran- jape, Michele Bevilacqua, Fabio Petroni, and Percy Liang

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:35.379798Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d224acb1-c0af-4393-9c86-7685f3ca1f9b · outbound

This paper cites Agentbench: Evaluating llms as agents.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Agentbench: Evaluating llms as agents

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:35.369200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c12d4d46-ca23-48da-b358-38ff6cbbf340 · outbound

This paper cites AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.781745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa9fc889-98e2-46f7-a0f0-14f1e6633a05 · outbound

This paper cites Finer: Finan- cial numeric entity recognition for xbrl tagging.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Finer: Finan- cial numeric entity recognition for xbrl tagging

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:35.359186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 8e82d994-dcbb-4bea-9c43-bb0db391b830 · outbound

This paper cites Self- refine: Iterative refinement with self-feedback.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Self- refine: Iterative refinement with self-feedback

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:35.348917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0d30f7b4-3722-4297-8b49-91ede3b6da8c · outbound

This paper cites Lever: Learning to verify language-to-code genera- tion with execution.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Lever: Learning to verify language-to-code genera- tion with execution

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:35.338188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2dba78d6-0612-4f7a-b24f-bc3841774a86 · outbound

This paper cites Optimizing instructions and demon- strations for multi-stage language model programs.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Optimizing instructions and demon- strations for multi-stage language model programs

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:35.287312Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b4ceec2c-27ba-43fe-a8f3-3a57918d247e · outbound

This paper cites Training language models to follow instructions with human feedback.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Training language models to follow instructions with human feedback

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.932441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a935459-b786-4a8a-8438-c2408fe2c0c1 · outbound

This paper cites Understanding and miti- gatingoverrefusalinllmsfromanunveilingperspective of safety decision boundary.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Understanding and miti- gatingoverrefusalinllmsfromanunveilingperspective of safety decision boundary

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:35.205605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9613c332-f4ba-43a0-8f25-58e6c8b3ad20 · outbound

This paper cites Optimal Transport for LLM Reward Modeling from Noisy Preference.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Optimal Transport for LLM Reward Modeling from Noisy Preference

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-08-16T00:33:34.071641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 51a50405-d900-4128-ac77-8a3e5d0687de · outbound

This paper cites ART: Automatic multi-step reasoning and tool-use for large language models.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction ART: Automatic multi-step reasoning and tool-use for large language models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.944284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 724498f6-bcc6-4194-b5e7-ebd3be301342 · outbound

This paper cites Generative Agents: Interactive Simulacra of Human Behavior.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Generative Agents: Interactive Simulacra of Human Behavior

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.949504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7aecd48e-25eb-439e-b06b-123a90b728ba · outbound

This paper cites Gorilla: Large language model connected with massive apis.Advances in Neural Information Processing Systems, 37:126544–126565, 2024.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Gorilla: Large language model connected with massive apis.Advances in Neural Information Processing Systems, 37:126544–126565, 2024

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.952720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7ca47cf-09ef-4cbe-8e99-15c781a63853 · outbound

This paper cites Webrl: Training llm web agents via self- evolving online curriculum reinforcement learning.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Webrl: Training llm web agents via self- evolving online curriculum reinforcement learning

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:35.128534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 926f485e-c26d-47d7-8e51-ae9a50e2d937 · outbound

This paper cites Toolllm: Facilitating large language modelstomaster16000+real-worldapis.InThe twelfth international conference on learning representations, 2023.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Toolllm: Facilitating large language modelstomaster16000+real-worldapis.InThe twelfth international conference on learning representations, 2023

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:35.094626Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 53834e41-48b2-4bb5-9a3e-10e333d704a2 · outbound

This paper cites Qwen3.5: Towards native multimodal agents, February 2026.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Qwen3.5: Towards native multimodal agents, February 2026

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:32.963369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 843c4dc3-8dc5-4edd-8626-97b439ac488f · outbound

This paper cites Qwen3.6-27B: Flagship-level coding in a 27B dense model, April 2026.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Qwen3.6-27B: Flagship-level coding in a 27B dense model, April 2026

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:35.078721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5979b046-04a3-4fda-a452-1aae76c2bd1f · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.Advances in neural infor- mation processing systems, 36:53728–53741, 2023.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Direct preference optimization: Your language model is secretly a reward model.Advances in neural infor- mation processing systems, 36:53728–53741, 2023

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:35.068292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 98de1b21-8a3c-443d-86eb-1b51b29ff57b · outbound

This paper cites Tool- former: Language models can teach themselves to use tools.Advances in neural information processing systems, 36:68539–68551, 2023.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Tool- former: Language models can teach themselves to use tools.Advances in neural information processing systems, 36:68539–68551, 2023

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:35.056321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6c3a2dc9-614e-4199-b5ce-391f0d27dc1a · outbound

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

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:33.080607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66175715-5efd-44f8-b949-db35c5e00be9 · outbound

This paper cites HuggingGPT: Solvingaitaskswithchatgptanditsfriendsinhugging face.Advances in Neural Information Processing Systems, 36:38154–38180, 2023.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction HuggingGPT: Solvingaitaskswithchatgptanditsfriendsinhugging face.Advances in Neural Information Processing Systems, 36:38154–38180, 2023

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:34.944393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 76a573c4-808a-4277-b3aa-fdc10cefd3f6 · outbound

This paper cites Chi, Nathanael Schärli, andDennyZhou.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Chi, Nathanael Schärli, andDennyZhou

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:34.896116Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation bac1e0a3-91ec-4b3c-b897-c8d5004b4344 · outbound

This paper cites Reflexion: Language agents with verbal reinforcement learning.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Reflexion: Language agents with verbal reinforcement learning

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:33.091708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e47806f5-7490-4a44-b27e-aedce987065a · outbound

This paper cites ALFWorld: Aligning Text and Embodied Environments for Interactive Learning.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction ALFWorld: Aligning Text and Embodied Environments for Interactive Learning

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:33.095593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24c2a113-bd2e-4d10-874d-acd65cf0e319 · outbound

This paper cites Beyond the imitation game: Quantifying and extrapolating the capabilities of lan- guage models.Transactions on Machine Learning Research, 2023.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Beyond the imitation game: Quantifying and extrapolating the capabilities of lan- guage models.Transactions on Machine Learning Research, 2023

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:34.880215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 7f3c1aee-d14e-4347-83bb-b07b6977ca5f · outbound

This paper cites Cognitive Architectures for Language Agents.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Cognitive Architectures for Language Agents

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:33.103535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d41055d-f86f-4679-b786-b1159d401579 · outbound

This paper cites Challenging big-bench tasks and whether chain-of-thought can solve them.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Challenging big-bench tasks and whether chain-of-thought can solve them

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:34.870263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3b250c3d-05f6-4c53-8346-29ba93471cb1 · outbound

This paper cites Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:33.224105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26f07466-fff7-4e29-85ae-6ab6f60cf66a · outbound

This paper cites Eliminating Reasoning via Inferring with Planning: A New Framework to Guide LLMs' Non-linear Thinking.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Eliminating Reasoning via Inferring with Planning: A New Framework to Guide LLMs' Non-linear Thinking

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:33.228103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c547dd5e-94a3-4c2a-9a6e-fa6183c73134 · outbound

This paper cites Canllmslearnfromprevious mistakes? investigating llms’ errors to boost for rea- soning.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Canllmslearnfromprevious mistakes? investigating llms’ errors to boost for rea- soning

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:34.860646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 578b6c1e-9374-4af1-9efb-6502704c0d7f · outbound

This paper cites Optimizing Language Model's Reasoning Abilities with Weak Supervision.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Optimizing Language Model's Reasoning Abilities with Weak Supervision

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:33.235031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2789af54-40cf-46f6-ae27-64ea6b5d4cb1 · outbound

This paper cites Appworld: A controllable world of apps and people for benchmarking interactive coding agents.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Appworld: A controllable world of apps and people for benchmarking interactive coding agents

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:34.850747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 32516c05-0ee4-47f5-922e-0d1c91c624a6 · outbound

This paper cites FinLoRA: Benchmarking LoRA Methods for Fine-Tuning LLMs on Financial Datasets.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction FinLoRA: Benchmarking LoRA Methods for Fine-Tuning LLMs on Financial Datasets

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:33.242741Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58f28120-81b0-4846-b256-acf8819992f7 · outbound

This paper cites Voyager: An Open-Ended Embodied Agent with Large Language Models.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Voyager: An Open-Ended Embodied Agent with Large Language Models

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:33.285570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e92c1da4-0770-4dba-bcf1-7c5d81521fe3 · outbound

This paper cites REFLEX: Reflective evolution from LLM experience.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction REFLEX: Reflective evolution from LLM experience

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:34.840862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4e5eadef-055e-4428-8a26-08917106bcd0 · outbound

This paper cites AtlasVA: Self-Evolving Visual Skill Memory for Teacher-Free VLM Agents.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction AtlasVA: Self-Evolving Visual Skill Memory for Teacher-Free VLM Agents

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:33.435925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 896cc7b9-c227-48b8-b059-40c9543f532e · outbound

This paper cites Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:33.490521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88ca43e4-4628-4468-b315-fa7325705753 · outbound

This paper cites BPO: Towards balanced preference optimization between knowledge breadth and depth in alignment.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction BPO: Towards balanced preference optimization between knowledge breadth and depth in alignment

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:34.830847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 088094cc-c51b-4956-9ecf-7f9145f63a4d · outbound

This paper cites OpenHands: An Open Platform for AI Software Developers as Generalist Agents.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction OpenHands: An Open Platform for AI Software Developers as Generalist Agents

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:33.498815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ae4ec73-b70d-4cfd-90d6-ffd9223b2f86 · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:33.503441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82300874-c092-48f0-9e21-94999a2fcfed · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Chain-of-thought prompting elicits reasoning in large language models

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:34.814090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9e6b5135-869a-43ef-8e63-a87a5a065628 · outbound

This paper cites Generating sequences by learning to self- correct.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Generating sequences by learning to self- correct

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:34.661793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 189255af-02e9-4150-b435-18a40aa37400 · outbound

This paper cites Autogen: Enabling next-genllmapplicationsviamulti-agentconversations.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Autogen: Enabling next-genllmapplicationsviamulti-agentconversations

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:34.558483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 80b0ac03-dfb2-4ef9-a65b-af2f0ad7feb6 · outbound

This paper cites Agentless: Demystifying LLM-based Software Engineering Agents.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Agentless: Demystifying LLM-based Software Engineering Agents

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:33.515805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcc01372-0216-406d-b5a0-4c595510e4f1 · outbound

This paper cites Understanding conflicts in multi- objective alignment through reward consistency.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Understanding conflicts in multi- objective alignment through reward consistency

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:34.545677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation cc1f9429-1855-4ebc-88aa-e9db5d0afafa · outbound

This paper cites Corrective Retrieval Augmented Generation.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Corrective Retrieval Augmented Generation

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:33.522211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e443eff3-8741-4a37-9111-932790c0bef7 · outbound

This paper cites SWE-agent: Agent-computer interfaces enable automatedsoftwareengineering.InAdvances in Neural Information Processing Systems, volume 37, 2024.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction SWE-agent: Agent-computer interfaces enable automatedsoftwareengineering.InAdvances in Neural Information Processing Systems, volume 37, 2024

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:34.533251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2ea8998c-607c-4368-8d9e-2f37126e16fc · outbound

This paper cites How is llm reasoning distracted by irrelevant context? an analysis using a controlled benchmark.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction How is llm reasoning distracted by irrelevant context? an analysis using a controlled benchmark

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:34.523071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0d040aec-434f-4b5a-a34a-b9441f54389d · outbound

This paper cites ReAct: Synergizing Reasoning and Acting in Language Models.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction ReAct: Synergizing Reasoning and Acting in Language Models

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:33.588385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34d85fb8-9456-4f94-bf2e-1fd169af05e9 · outbound

This paper cites Griffiths, Yuan Cao, and Karthik Narasimhan.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Griffiths, Yuan Cao, and Karthik Narasimhan

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:34.511755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1aa9ee3c-da5e-4dc4-8dc7-733ba2c82a06 · outbound

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

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:33.645802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e72c3e34-d083-45f0-a36b-91aad86262f4 · outbound

This paper cites an unresolved cited work.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Unresolved cited work

Reference 93

Resolution: unresolved; raw_fallback, observed 2026-08-16T00:33:34.502260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3f749eb0-d9a9-4aae-be9c-94aebded2811 · outbound

This paper cites Agenticcon- text engineering: Evolving contexts for self-improving language models.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Agenticcon- text engineering: Evolving contexts for self-improving language models

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:34.492208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 49112e5b-16e2-488a-b499-b839b9e8c802 · outbound

This paper cites Debug like a human: A large language model debugger via verifying runtime execution step-by-step.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Debug like a human: A large language model debugger via verifying runtime execution step-by-step

Reference 95

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:34.481415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 089374cc-2037-440c-a863-59c4f7bc4ff1 · outbound

This paper cites Least-to- most prompting enables complex reasoning in large language models.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction Least-to- most prompting enables complex reasoning in large language models

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T00:33:34.384144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a6063bd7-fd89-4283-bd7b-34fe3c9f1b14 · outbound

This paper cites ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL.

Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-16T00:33:33.662364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers