Paper Citation Record · LEDGER

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents

As of 6 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 1 inbound Pith citation observation for arXiv:2607.01120.

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

pith.paper-citation-record.v1
2607.01120 v2

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-03T18:47:46.719344Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T09:49:31.023088Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

38 of 38 outbound references displayed

verified exact20
verified fuzzy18
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e1c90530-8511-499e-a8b0-d26b7a6805f1 · outbound

This paper cites Openclaw: The ai that actually does things, 2026.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents Openclaw: The ai that actually does things, 2026

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-07-05T03:30:39.196295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1b3b92dd-efc9-48a8-b07c-4b4fe1ddfee2 · outbound

This paper cites OpenClaw-RL: Train Any Agent Simply by Talking.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents OpenClaw-RL: Train Any Agent Simply by Talking

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-07-03T18:48:49.543357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 967125cd-f96c-4e9c-b929-22c36418c295 · outbound

This paper cites Metaclaw: Just talk–an agent that meta-learns and evolves in the wild.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents Metaclaw: Just talk–an agent that meta-learns and evolves in the wild

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-07-03T18:48:49.564921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 04c9d290-5979-48eb-9048-d581db4657d6 · outbound

This paper cites SkillClaw: Let Skills Evolve Collectively with Agentic Evolver.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents SkillClaw: Let Skills Evolve Collectively with Agentic Evolver

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-07-03T18:48:49.546339Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2fe8fb89-55af-4473-881c-7459d52f566f · outbound

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

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents Reflexion: Language agents with verbal reinforcement learning

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-07-05T03:30:39.206472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d6e51a11-f1ef-438b-b3f4-2e2e0894cdd5 · outbound

This paper cites Memento-skills: Let agents design agents.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents Memento-skills: Let agents design agents

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-07-03T18:48:49.535633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ae361a64-5409-4815-89ff-015f892e6109 · outbound

This paper cites Agentic context engineering: Evolving contexts for self-improving language models.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents Agentic context engineering: Evolving contexts for self-improving language models

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-07-05T03:30:39.208651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation dca7b9d2-8929-46f6-8200-13b76856f345 · outbound

This paper cites Areal: A large-scale asynchronous reinforcement learning system for language reasoning.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents Areal: A large-scale asynchronous reinforcement learning system for language reasoning

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-07-05T03:30:39.208460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b1e742bc-aef7-445d-8132-a304f92dcdbd · outbound

This paper cites A Survey of Reinforcement Learning for Large Reasoning Models.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents A Survey of Reinforcement Learning for Large Reasoning Models

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-07-03T18:48:49.532549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation efe2340e-a09f-4d24-ac53-05179d597600 · outbound

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

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents Training language models to follow instructions with human feedback

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-07-05T03:30:39.218276Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8df964e6-5775-4b93-897b-8a6b9c73b844 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents Constitutional AI: Harmlessness from AI Feedback

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-07-03T18:48:49.527409Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 96ec482e-174a-4b88-b947-04ac42f8395d · outbound

This paper cites Proximal Policy Optimization Algorithms.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents Proximal Policy Optimization Algorithms

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-07-03T18:48:49.529749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 06eec497-5edc-48f7-81a0-5663b9d3136a · outbound

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

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents Direct preference optimization: Your language model is secretly a reward model.Advances in neural information processing systems, 36:53728–53741

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-07-05T03:30:39.210686Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b7e9d4cf-9adc-4873-9c94-9cb7193c9153 · outbound

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

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-07-03T18:48:49.540942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 76af6b6d-0be3-4282-b302-959eb43ce550 · outbound

This paper cites The Landscape of Agentic Reinforcement Learning for LLMs: A Survey.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-07-03T18:48:49.516258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4b4ace6b-a685-4d6c-878a-839beb201afc · outbound

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

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents ReAct: Synergizing Reasoning and Acting in Language Models

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-07-03T18:48:49.519138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e6c8c4c1-7b6f-4ead-a109-8ba3a0fb3888 · outbound

This paper cites TextGrad: Automatic "Differentiation" via Text.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents TextGrad: Automatic "Differentiation" via Text

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-07-03T18:48:49.521976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7311449a-4606-4d17-8358-8fec45566b0d · outbound

This paper cites Unlocking long-horizon agentic search with large-scale end-to-end rl.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents Unlocking long-horizon agentic search with large-scale end-to-end rl

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-07-05T03:30:39.187826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 06870b1d-8722-4fea-8bb3-1141e75b3305 · outbound

This paper cites ReaL: Efficient RLHF Training of Large Language Models with Parameter Reallocation.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents ReaL: Efficient RLHF Training of Large Language Models with Parameter Reallocation

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-07-03T18:48:49.538132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7dcf6429-605c-42ca-925d-cafe84bc77f9 · outbound

This paper cites Optimizing {RLHF} training for large language models with stage fusion.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents Optimizing {RLHF} training for large language models with stage fusion

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-07-05T03:30:39.204090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9487bfb8-2fb1-45b3-a0a8-28adfd9e3a54 · outbound

This paper cites G-Core: A Simple, Scalable and Balanced RLHF Trainer.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents G-Core: A Simple, Scalable and Balanced RLHF Trainer

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-07-03T18:48:49.524813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 79e78776-42d1-406d-8f8c-808815f3e29f · outbound

This paper cites Hybridflow: A flexible and efficient rlhf framework.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents Hybridflow: A flexible and efficient rlhf framework

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-07-05T03:30:39.212609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 082f5c95-f61d-4dd9-8c06-0462846c29b6 · outbound

This paper cites StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-07-03T18:48:49.509444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 17173bbf-93a2-485d-9c69-c7d3c3888201 · outbound

This paper cites AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-07-03T18:48:49.549581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7c103216-7fca-42f0-8da6-95001fddfca1 · outbound

This paper cites Introducing the Model Context Protocol.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents Introducing the Model Context Protocol

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-07-05T03:30:39.197808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 07fc8c61-7a8c-402a-a713-6ed78e051e15 · outbound

This paper cites Agent2agent (a2a) protocol.https://a2a-protocol.org/, 2025.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents Agent2agent (a2a) protocol.https://a2a-protocol.org/, 2025

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-07-05T03:30:39.194269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 79ec63d6-1e71-4b4b-b3e7-b1c6f0664c4b · outbound

This paper cites A Survey of AI Agent Protocols.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents A Survey of AI Agent Protocols

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-07-03T18:48:49.556107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation aad236f2-dc72-4606-960e-cccab34bc2f6 · outbound

This paper cites D4RL: Datasets for Deep Data-Driven Reinforcement Learning.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents D4RL: Datasets for Deep Data-Driven Reinforcement Learning

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-07-03T18:48:49.553561Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9092a0e7-8054-4066-95f6-fc2fc0a351e6 · outbound

This paper cites RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learning.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learning

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-07-03T18:48:49.559274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3aa93142-cd4f-4de2-8eb6-38292f3c8ac6 · outbound

This paper cites Agent data protocol: Unifying datasets for diverse, effective fine-tuning of llm agents.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents Agent data protocol: Unifying datasets for diverse, effective fine-tuning of llm agents

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-07-03T18:48:49.561726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c8bf950d-8111-425e-9de1-2afa6e8be718 · outbound

This paper cites LangChain: The agent engineering platform.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents LangChain: The agent engineering platform

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-07-05T03:30:39.206668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2db5f868-cab5-4c31-865f-3fed96a8be40 · outbound

This paper cites LangGraph: Build resilient language agents as graphs.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents LangGraph: Build resilient language agents as graphs

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-07-05T03:30:39.216644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 41e9af60-311a-4abb-8ce8-1c387b0e3477 · outbound

This paper cites CrewAI: Framework for orchestrating role-playing, autonomous AI agents.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents CrewAI: Framework for orchestrating role-playing, autonomous AI agents

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-07-05T03:30:39.191761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation eeafd810-b69f-4294-8a62-ab7eb4ff6b8c · outbound

This paper cites OpenAI Agents SDK: A lightweight, powerful framework for multi-agent workflows.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents OpenAI Agents SDK: A lightweight, powerful framework for multi-agent workflows

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-07-05T03:30:39.201810Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 639b0062-83c4-4c49-a225-30d408f222ee · outbound

This paper cites Claude Agent SDK.https://github.com/anthropics/claude-agent-sdk-python, 2025.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents Claude Agent SDK.https://github.com/anthropics/claude-agent-sdk-python, 2025

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-07-05T03:30:39.210562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 73883c96-3a86-45eb-b16f-3cc6483ff40b · outbound

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

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents Agentprm: Process reward models for llm agents via step-wise promise and progress

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-07-05T03:30:39.214498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e4742587-7e2f-4d8b-99c3-607576e104d8 · outbound

This paper cites Rlanything: Forge environment, policy, and reward model in completely dynamic rl system.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents Rlanything: Forge environment, policy, and reward model in completely dynamic rl system

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-07-03T18:48:49.512855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5e8abccd-d426-4fc2-8f39-021a16556997 · outbound

This paper cites Hermes agent: The self-improving ai agent built by nous research.

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents Hermes agent: The self-improving ai agent built by nous research

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-07-05T03:30:39.216467Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Pith citing papers

Observation 6a869fb7-4c00-430a-973c-afe7325b5047 · inbound

Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning cites this paper.

Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-01T09:49:31.023088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.