Paper Citation Record · LEDGER

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks

As of 11 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 0 inbound Pith citation observations for arXiv:2607.22724.

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

pith.paper-citation-record.v1
2607.22724 v1

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T11:55:00.149522Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

42 of 42 outbound references displayed

verified exact0
verified fuzzy0
unresolved41
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 735f858a-003b-4482-bfb6-99bf523fe866 · outbound

This paper cites GPT-4 Technical Report.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:56.943572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 153f6762-c155-4940-a48f-5abfbc6c7910 · outbound

This paper cites Back to basics: Revisiting reinforce-style optimization for learning from human feedback in llms.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Back to basics: Revisiting reinforce-style optimization for learning from human feedback in llms

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:57.024936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76b916fa-ceae-4a1f-8c33-6bc7d40bfe1e · outbound

This paper cites XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:57.104603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1c681c6-96d6-4772-8643-d084061965fb · outbound

This paper cites Progra: Progress-aware reinforcement learning for multi-turn function calling.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Progra: Progress-aware reinforcement learning for multi-turn function calling

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:57.183813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9d9387e-8aa1-4762-8e92-2eabf8b75da1 · outbound

This paper cites Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:57.260816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f39d3ef5-e163-4ba1-8e85-655eb5f7fe63 · outbound

This paper cites Proximity-based multi-turn optimization: Practical credit assignment for llm agent training.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Proximity-based multi-turn optimization: Practical credit assignment for llm agent training

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:57.347969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b5ce984-ba5e-45cd-9070-d08ec0e81ae5 · outbound

This paper cites Towards efficient online tuning of VLM agents via counterfactual soft reinforcement learning.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Towards efficient online tuning of VLM agents via counterfactual soft reinforcement learning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:57.387214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2aecaa62-a666-492c-9d25-c4c1980a138c · outbound

This paper cites Group-in-group policy optimization for llm agent training.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Group-in-group policy optimization for llm agent training

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:57.408564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29d00fd5-e39d-4257-bf65-eec4519cf6a8 · outbound

This paper cites Multimodal web navigation with instruction-finetuned foundation models.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Multimodal web navigation with instruction-finetuned foundation models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:57.449494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b74b658-d362-43e5-8bd8-2e99cd0f9c94 · outbound

This paper cites Navigating the digital world as humans do: Universal visual grounding for GUI agents.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Navigating the digital world as humans do: Universal visual grounding for GUI agents

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:57.482108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e70a9ec2-8237-4ecc-b7f4-4c2831afcfe5 · outbound

This paper cites Hierarchy-of-groups policy optimization for long-horizon agentic tasks.arXiv preprint arXiv:2602.22817, 2026.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Hierarchy-of-groups policy optimization for long-horizon agentic tasks.arXiv preprint arXiv:2602.22817, 2026

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:57.550878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3066127f-4654-4345-9d09-bfd39d4d3d11 · outbound

This paper cites Buy 4 reinforce samples, get a baseline for free! InICLR 2019 Workshop, 2019.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Buy 4 reinforce samples, get a baseline for free! InICLR 2019 Workshop, 2019

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:57.627348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bec2e20-02f0-4da2-b05f-5ebdf58e5339 · outbound

This paper cites No prompt left behind: Exploiting zero-variance prompts in llm reinforcement learning via entropy-guided advantage shaping.arXiv preprint arXiv:2509.21880, 2025.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks No prompt left behind: Exploiting zero-variance prompts in llm reinforcement learning via entropy-guided advantage shaping.arXiv preprint arXiv:2509.21880, 2025

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:57.697039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba852e80-66cd-4988-bddb-7dbc2b450f2d · outbound

This paper cites Salt: Step-level advantage assignment for long-horizon agents via trajectory graph.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Salt: Step-level advantage assignment for long-horizon agents via trajectory graph

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:57.763485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bb46914-ba17-471c-8a21-b66cb2d554d0 · outbound

This paper cites Embodied agent interface: Benchmarking LLMs for embodied decision making.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Embodied agent interface: Benchmarking LLMs for embodied decision making

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:57.849466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b694f3a2-2a2b-40ea-ae60-66a4cd8aaa80 · outbound

This paper cites Agentic reinforcement learning with implicit step rewards.arXiv preprint arXiv:2509.19199, 2025.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Agentic reinforcement learning with implicit step rewards.arXiv preprint arXiv:2509.19199, 2025

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:58.026598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f170e07-8301-4bc9-a2e3-116956eb6366 · outbound

This paper cites Understanding R1-Zero-Like Training: A Critical Perspective.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Understanding R1-Zero-Like Training: A Critical Perspective

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:58.149883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ef6eb7f-41df-451c-bf4e-00675be94ffe · outbound

This paper cites TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimization.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimization

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:58.217966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0ed8ad7-bd09-4dbd-9a3b-bcb972e39b69 · outbound

This paper cites Ngrpo: Negative-enhanced group relative policy optimization.arXiv preprint arXiv:2509.18851, 2025.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Ngrpo: Negative-enhanced group relative policy optimization.arXiv preprint arXiv:2509.18851, 2025

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:58.321856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab76c4dc-079a-47a8-ae20-a36978d09223 · outbound

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

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks ToolRL: Reward is All Tool Learning Needs

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:58.370351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e39b4dfb-3766-4988-bd8f-80d31b93802a · outbound

This paper cites RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:58.489272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6c5daa6-733f-4db9-b1b4-450f2e84d886 · outbound

This paper cites Toolformer: Language models can teach themselves to use tools.Advances in Neural Information Processing Systems, 36:68539–68551, 2023.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Toolformer: Language models can teach themselves to use tools.Advances in Neural Information Processing Systems, 36:68539–68551, 2023

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:58.558728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb84fd38-1f30-4ad0-b912-50e749c4a27f · outbound

This paper cites Proximal Policy Optimization Algorithms.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Proximal Policy Optimization Algorithms

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:58.628083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd73ad1f-60b7-4a24-9f29-5a0e76208184 · outbound

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

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:58.733456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1464195-bee3-40ab-a24e-ce74a2e37d8e · outbound

This paper cites Reflexion: Language agents with verbal reinforcement learning.Advances in Neural Information Processing Systems, 36, 2024.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Reflexion: Language agents with verbal reinforcement learning.Advances in Neural Information Processing Systems, 36, 2024

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:58.902231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d56febe0-c7b2-4e16-a94f-834d91a6effd · outbound

This paper cites ALFWorld: Aligning text and embodied environments for interactive learning.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks ALFWorld: Aligning text and embodied environments for interactive learning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:58.960233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1add1d35-3663-46e3-8b31-dd1718c77724 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Gemini: A Family of Highly Capable Multimodal Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:59.062582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12cecd86-58dc-47f0-a82d-cf3ee377e031 · outbound

This paper cites Kimi k1.5: Scaling Reinforcement Learning with LLMs.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:59.123594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77f84b04-9d40-491f-9927-52328a607635 · outbound

This paper cites Voyager: An open-ended embodied agent with large language models.Transactions on Machine Learning Research, 2024.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Voyager: An open-ended embodied agent with large language models.Transactions on Machine Learning Research, 2024

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:59.187480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c3f1976-d2f5-4aa9-8e5e-ea3e347b890e · outbound

This paper cites Information gain-based policy optimization: A simple and effective approach for multi-turn llm agents.arXiv preprint arXiv:2510.14967, 2025.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Information gain-based policy optimization: A simple and effective approach for multi-turn llm agents.arXiv preprint arXiv:2510.14967, 2025

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:59.299303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69741546-e41a-4506-a1df-59b33b37d407 · outbound

This paper cites SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:59.427547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8aa4bd78-cbee-4d74-a401-bcde75c7ef8e · outbound

This paper cites Mobile-Agent-v2: Mobile device operation assistant with effective navigation via multi-agent collaboration.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Mobile-Agent-v2: Mobile device operation assistant with effective navigation via multi-agent collaboration

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:59.487844Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6f8b6a3-ab00-49c3-9543-10dd64968821 · outbound

This paper cites SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:59.568773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ede04870-efde-46f5-84f5-1c473f846b00 · outbound

This paper cites Agentprm: Process reward models for llm agents via step-wise promise and progress.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Agentprm: Process reward models for llm agents via step-wise promise and progress

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:59.658025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16f0f686-765a-471b-bf93-1715f5ea85ce · outbound

This paper cites Watch every step! llm agent learning via iterative step-level process refinement.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Watch every step! llm agent learning via iterative step-level process refinement

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:59.719592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 051548c4-99fd-47c1-af84-d6ed190263df · outbound

This paper cites Qwen3 Technical Report.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Qwen3 Technical Report

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:59.787781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 388bfc90-99b3-45cb-9700-2c87a312a1fe · outbound

This paper cites WebShop: Towards scalable real-world web interaction with grounded language agents.Advances in Neural Information Processing Systems, 35:20744–20757, 2022.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks WebShop: Towards scalable real-world web interaction with grounded language agents.Advances in Neural Information Processing Systems, 35:20744–20757, 2022

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:59.916475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c24956e-6f6d-4016-b592-9e6a32c08b93 · outbound

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

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks ReAct: Synergizing Reasoning and Acting in Language Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-01T11:54:59.962766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ce797b9-649e-4872-ab75-2f4d50c414a2 · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-01T11:55:00.025273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7c6c403-0bc4-426d-9a67-637a11b4e003 · outbound

This paper cites Reinforcement world model learning for llm-based agents.arXiv preprint arXiv:2602.05842, 2026.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Reinforcement world model learning for llm-based agents.arXiv preprint arXiv:2602.05842, 2026

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-01T11:55:00.080830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89303a57-3d4e-45c8-8f9d-684a626ada19 · outbound

This paper cites Scaf-grpo: Scaffolded group relative policy optimization for enhancing llm reasoning.arXiv preprint arXiv:2510.19807, 2025.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks Scaf-grpo: Scaffolded group relative policy optimization for enhancing llm reasoning.arXiv preprint arXiv:2510.19807, 2025

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-01T11:55:00.117534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7081ea75-5803-4eca-ad0f-75a2a6116586 · outbound

This paper cites put a cool tomato on the countertop.

Progress-conditioned Group Policy Optimization for Long-Horizon Agentic Tasks put a cool tomato on the countertop

Reference 43

Resolution: malformed identifier; no resolver link, observed 2026-08-01T11:55:00.149522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.