Paper Citation Record · LEDGER

Exploring Expert Failures Improves LLM Agent Tuning

As of 18 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 2 inbound Pith citation observations for arXiv:2504.13145.

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

pith.paper-citation-record.v1
2504.13145 v2

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T12:18:49.217321Z

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-14T04:35:18.372917Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T14:37:49.973211Z

Reference resolution

25 of 25 outbound references displayed

verified exact1
verified fuzzy1
unresolved23
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 249b3db7-8aff-4e77-b34a-f77a8c814a26 · outbound

This paper cites GPT-4 Technical Report.

Exploring Expert Failures Improves LLM Agent Tuning GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T12:18:48.351840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0d3ecae-0ccb-4ac0-9a07-f0eaa1188143 · outbound

This paper cites Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models.

Exploring Expert Failures Improves LLM Agent Tuning Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T12:18:48.456453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84cfe1d2-0b4d-4f22-8fa9-e6bc399ca847 · outbound

This paper cites ATLaS: Agent Tuning via Learning Critical Steps.

Exploring Expert Failures Improves LLM Agent Tuning ATLaS: Agent Tuning via Learning Critical Steps

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T12:18:48.461379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72cc724b-ec18-4e01-8074-87fae4431a62 · outbound

This paper cites Contextual Markov Decision Processes.

Exploring Expert Failures Improves LLM Agent Tuning Contextual Markov Decision Processes

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T12:18:48.505040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc2a8a1b-8fc2-475e-bf22-77fb5cbf60a5 · outbound

This paper cites Inner Monologue: Embodied Reasoning through Planning with Language Models.

Exploring Expert Failures Improves LLM Agent Tuning Inner Monologue: Embodied Reasoning through Planning with Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T12:18:48.636400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44a0e70f-1438-40bc-8e6c-d88f0b49fba0 · outbound

This paper cites Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories.

Exploring Expert Failures Improves LLM Agent Tuning Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-08-16T12:18:49.545440Z

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 8a194436-aeff-4e10-bc78-a7631828a1d7 · outbound

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

Exploring Expert Failures Improves LLM Agent Tuning AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T12:18:48.647661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b03e05ab-cc8b-4679-b438-1eb760f011d3 · outbound

This paper cites AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents.

Exploring Expert Failures Improves LLM Agent Tuning AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T12:18:48.652037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c65e9a6-bc17-4964-b91e-9929624fb5c5 · outbound

This paper cites Let's reward step by step: Step-Level reward model as the Navigators for Reasoning.

Exploring Expert Failures Improves LLM Agent Tuning Let's reward step by step: Step-Level reward model as the Navigators for Reasoning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T12:18:48.731690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0734153d-3925-46e4-9365-2bd38a29105a · outbound

This paper cites Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

Exploring Expert Failures Improves LLM Agent Tuning Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T12:18:48.806241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44660778-45d2-4f54-9d0c-b38c82ffa363 · outbound

This paper cites Co-Reyes, Rishabh Agarwal, Ankesh Anand, Piyush Patil, Peter J.

Exploring Expert Failures Improves LLM Agent Tuning Co-Reyes, Rishabh Agarwal, Ankesh Anand, Piyush Patil, Peter J

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:18:49.744493Z

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 76c7a648-bc90-4e61-a3c0-e7323f7616ec · outbound

This paper cites AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories.

Exploring Expert Failures Improves LLM Agent Tuning AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T12:18:48.816530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d39c7cb4-c684-413d-937d-243cf74acd92 · outbound

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

Exploring Expert Failures Improves LLM Agent Tuning Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T12:18:48.822368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28eeec0e-a312-48d7-88fc-48956ab785d8 · outbound

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

Exploring Expert Failures Improves LLM Agent Tuning Voyager: An Open-Ended Embodied Agent with Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T12:18:48.932683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 592ad90b-a4d2-4c0a-a807-e590420720b9 · outbound

This paper cites Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement.

Exploring Expert Failures Improves LLM Agent Tuning Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T12:18:49.043336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c99db4df-5e29-4fb1-8941-6487d8232cc0 · outbound

This paper cites Scaling Relationship on Learning Mathematical Reasoning with Large Language Models.

Exploring Expert Failures Improves LLM Agent Tuning Scaling Relationship on Learning Mathematical Reasoning with Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T12:18:49.048092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0395c9fb-f92f-411d-9e33-5911a80ef306 · outbound

This paper cites AgentTuning: Enabling Generalized Agent Abilities for LLMs.

Exploring Expert Failures Improves LLM Agent Tuning AgentTuning: Enabling Generalized Agent Abilities for LLMs

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T12:18:49.053848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 038236ee-fc72-4ba4-8dc0-6b827899e086 · outbound

This paper cites AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning.

Exploring Expert Failures Improves LLM Agent Tuning AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T12:18:49.121774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21a63a2a-87fe-4779-8e77-355d2a965055 · outbound

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

Exploring Expert Failures Improves LLM Agent Tuning WebArena: A Realistic Web Environment for Building Autonomous Agents

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-16T12:18:49.217321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebf6be87-6040-4376-b23e-04bfd0ca8bc8 · outbound

This paper cites From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning.

Exploring Expert Failures Improves LLM Agent Tuning From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning

Reference 2006

Resolution: unresolved; no resolver link, observed 2026-08-16T12:18:48.467217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72ea9de0-b53f-46ba-a609-7c688668cfed · outbound

This paper cites GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinements.

Exploring Expert Failures Improves LLM Agent Tuning GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinements

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-16T12:18:48.585351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83a868b4-051e-4786-b2b0-982c031b2ea0 · outbound

This paper cites Multi-step Problem Solving Through a Verifier: An Empirical Analysis on Model-induced Process Supervision.

Exploring Expert Failures Improves LLM Agent Tuning Multi-step Problem Solving Through a Verifier: An Empirical Analysis on Model-induced Process Supervision

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-16T12:18:49.037721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5dd1a83-41b9-4a2f-97c9-555ac768a72b · outbound

This paper cites FireAct: Toward Language Agent Fine-tuning.

Exploring Expert Failures Improves LLM Agent Tuning FireAct: Toward Language Agent Fine-tuning

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-16T12:18:48.450541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98cd6fc3-0cdb-4b1e-9952-546dc8930ff9 · outbound

This paper cites ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent.

Exploring Expert Failures Improves LLM Agent Tuning ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-16T12:18:48.417057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64679209-0df5-4952-8128-8e06271f7c27 · outbound

This paper cites Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations.

Exploring Expert Failures Improves LLM Agent Tuning Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-16T12:18:49.032082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 58e481f7-a907-4cbb-9051-e260b61b71d4 · inbound

ProgRM: Build Better GUI Agents with Progress Rewards cites this paper.

ProgRM: Build Better GUI Agents with Progress Rewards Exploring Expert Failures Improves LLM Agent Tuning

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:37:50.068075Z

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 ac2fa8c3-3207-4f37-aa2d-4f7a74718ad6 · inbound

FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents cites this paper.

FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents Exploring Expert Failures Improves LLM Agent Tuning

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-14T04:35:18.372917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.