Paper Citation Record · LEDGER

Agent Safety Alignment via Reinforcement Learning

As of 21 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 5 inbound Pith citation observations for arXiv:2507.08270.

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

pith.paper-citation-record.v1
2507.08270 v1

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:29:36.837135Z

measured 35 of 35 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T19:23:23.093260Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T02:16:26.560954Z

Reference resolution

30 of 30 outbound references displayed

verified exact0
verified fuzzy13
unresolved16
parse uncertain1
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 180d6887-487a-4761-b359-a24be9ab44c2 · outbound

This paper cites Narasimhan, and Yuan Cao.

Agent Safety Alignment via Reinforcement Learning Narasimhan, and Yuan Cao

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:29:39.278568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9b8cfb93-2cd6-414b-bca4-c1d04723b526 · outbound

This paper cites AutoGPT: An open-source autonomous agent framework.

Agent Safety Alignment via Reinforcement Learning AutoGPT: An open-source autonomous agent framework

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:29:39.040807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 8c747e8a-2736-4a40-863c-48cef5300cb1 · outbound

This paper cites BabyAGI: Experimental self-building autonomous agent.

Agent Safety Alignment via Reinforcement Learning BabyAGI: Experimental self-building autonomous agent

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:29:38.892749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 30daa421-c6f6-4f62-871b-9fbce1301e31 · outbound

This paper cites AgentGPT: Configure and deploy autonomous ai agents.

Agent Safety Alignment via Reinforcement Learning AgentGPT: Configure and deploy autonomous ai agents

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:29:38.670365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6d323b6e-662d-4c35-8a7b-b8dd7e2d3ac3 · outbound

This paper cites AI agents under threat: A survey of key security challenges and future pathways.

Agent Safety Alignment via Reinforcement Learning AI agents under threat: A survey of key security challenges and future pathways

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:29:38.493698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e903261e-c05d-428b-a610-f02e4534c4f9 · outbound

This paper cites Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents.

Agent Safety Alignment via Reinforcement Learning Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agents

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T18:29:35.685754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 277557af-1ef4-4596-8267-f1f6d14cfb36 · outbound

This paper cites Retool: Reinforcement learning for strategic tool use in llms, 2025.

Agent Safety Alignment via Reinforcement Learning Retool: Reinforcement learning for strategic tool use in llms, 2025

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:29:38.295437Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 9064441a-04bc-4858-bf9f-bd04b31bf99b · outbound

This paper cites SEM: Reinforcement Learning for Search-Efficient Large Language Models.

Agent Safety Alignment via Reinforcement Learning SEM: Reinforcement Learning for Search-Efficient Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T18:29:35.794563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11389ede-4427-4e8b-9513-85c8adb70359 · outbound

This paper cites Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training.

Agent Safety Alignment via Reinforcement Learning Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T18:29:35.842058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9db288de-ae8a-40ce-922e-1f3dbc026ce4 · outbound

This paper cites Pan, Wen Zhang, Huajun Chen, Fan Yang, Zenan Zhou, and Weipeng Chen.

Agent Safety Alignment via Reinforcement Learning Pan, Wen Zhang, Huajun Chen, Fan Yang, Zenan Zhou, and Weipeng Chen

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:29:38.183883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 81cbd57d-026c-4c08-b680-a2d98e1d6acf · outbound

This paper cites Agent security bench (ASB): formalizing and benchmarking attacks and defenses in llm-based agents.

Agent Safety Alignment via Reinforcement Learning Agent security bench (ASB): formalizing and benchmarking attacks and defenses in llm-based agents

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:29:38.041081Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 29aeb465-7be8-4e24-a417-a491faef2aff · outbound

This paper cites Agent-SafetyBench: Evaluating the Safety of LLM Agents.

Agent Safety Alignment via Reinforcement Learning Agent-SafetyBench: Evaluating the Safety of LLM Agents

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T18:29:36.015210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0ee323a-2ed7-4e0d-bd10-97e50f9bb5ae · outbound

This paper cites Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction.

Agent Safety Alignment via Reinforcement Learning Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T18:29:36.076016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 810eec96-44f3-4628-8fde-c766f6a55667 · outbound

This paper cites AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language Models.

Agent Safety Alignment via Reinforcement Learning AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T18:29:36.127202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80905211-b7a7-441a-a286-19e9f3ddb51a · outbound

This paper cites Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning, 2025.

Agent Safety Alignment via Reinforcement Learning Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning, 2025

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T18:29:36.164795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17a08604-0c36-4cad-8775-c863bc923e5b · outbound

This paper cites Injecagent: Benchmarking indirect prompt injections in tool-integrated large language model agents.

Agent Safety Alignment via Reinforcement Learning Injecagent: Benchmarking indirect prompt injections in tool-integrated large language model agents

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:29:37.906726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation e0617b99-43ab-43ee-ad94-10026b7b850b · outbound

This paper cites Patil, Huanzhi Mao, Charlie Cheng-Jie Ji, Fanjia Yan, Vishnu Suresh, Ion Stoica, and Joseph E.

Agent Safety Alignment via Reinforcement Learning Patil, Huanzhi Mao, Charlie Cheng-Jie Ji, Fanjia Yan, Vishnu Suresh, Ion Stoica, and Joseph E

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:29:37.752821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation b2d897fa-1c92-4adf-9b0a-edc24e9241d6 · outbound

This paper cites Large Language Model Agent: A Survey on Methodology, Applications and Challenges.

Agent Safety Alignment via Reinforcement Learning Large Language Model Agent: A Survey on Methodology, Applications and Challenges

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T18:29:36.302719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e81ee76-f028-4cc3-bc71-108bc49d7958 · outbound

This paper cites An In-depth Survey of Large Language Model-based Artificial Intelligence Agents.

Agent Safety Alignment via Reinforcement Learning An In-depth Survey of Large Language Model-based Artificial Intelligence Agents

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T18:29:36.361217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f10aa2d4-cfbb-496c-82c6-09d82e7f1ce8 · outbound

This paper cites Sumers, Shunyu Yao, Karthik Narasimhan, and Thomas L.

Agent Safety Alignment via Reinforcement Learning Sumers, Shunyu Yao, Karthik Narasimhan, and Thomas L

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:29:37.597508Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation a273817c-b321-431e-bd36-6a183d9853e9 · outbound

This paper cites AutoAgent: A Fully-Automated and Zero-Code Frame- work for LLM Agents, 2025.

Agent Safety Alignment via Reinforcement Learning AutoAgent: A Fully-Automated and Zero-Code Frame- work for LLM Agents, 2025

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:29:37.477865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation dad2e0b3-a7d9-4aea-8958-819993d89801 · outbound

This paper cites ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning.

Agent Safety Alignment via Reinforcement Learning ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T18:29:36.509257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17698f00-7f3f-49a3-a4d3-fc47cef63484 · outbound

This paper cites Deepresearcher: Scaling deep research via reinforcement learning in real-world environments, 2025.

Agent Safety Alignment via Reinforcement Learning Deepresearcher: Scaling deep research via reinforcement learning in real-world environments, 2025

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T18:29:36.552229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c292e407-2abc-4880-9c67-6926d025440e · outbound

This paper cites Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol (MCP) Ecosystem.

Agent Safety Alignment via Reinforcement Learning Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol (MCP) Ecosystem

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T18:29:36.599007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af481968-d1c7-4ba9-aca5-a42cdc8392d5 · outbound

This paper cites Progent: Securing AI Agents with Privilege Control.

Agent Safety Alignment via Reinforcement Learning Progent: Securing AI Agents with Privilege Control

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T18:29:36.649473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d8ff5a5-ea96-4e0b-91cb-22d95099f4d2 · outbound

This paper cites Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning.

Agent Safety Alignment via Reinforcement Learning Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T18:29:36.704014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0adbf1b-2904-4aa7-954c-6cf7b23e3bc7 · outbound

This paper cites A practical memory injection attack against LLM agents.

Agent Safety Alignment via Reinforcement Learning A practical memory injection attack against LLM agents

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T18:29:36.746281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17663713-ff13-49cf-816d-39dcd70da839 · outbound

This paper cites Agentpoison: Red- teaming LLM agents via poisoning memory or knowledge bases.

Agent Safety Alignment via Reinforcement Learning Agentpoison: Red- teaming LLM agents via poisoning memory or knowledge bases

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T18:29:37.380765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 474d8d38-3066-4322-b55d-e140835d4b2f · outbound

This paper cites Safeagentbench: A benchmark for safe task planning of embodied LLM agents.

Agent Safety Alignment via Reinforcement Learning Safeagentbench: A benchmark for safe task planning of embodied LLM agents

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T18:29:36.837135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86d6065a-488b-4180-8dbc-b3fb19586d46 · outbound

This paper cites an unresolved cited work.

Agent Safety Alignment via Reinforcement Learning Unresolved cited work

Reference 2023

Resolution: parse uncertain; no resolver link, observed 2026-08-06T18:29:35.441056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 4e0b924d-c7a3-4880-af77-73a752de6b5f · inbound

S3LoRA: Safe Spectral Sharpness-Guided Pruning in Adaptation of Agent Planner cites this paper.

S3LoRA: Safe Spectral Sharpness-Guided Pruning in Adaptation of Agent Planner Agent Safety Alignment via Reinforcement Learning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-05T18:12:35.170680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df93920d-a25d-43be-90bb-e4a56a80e3e5 · inbound

RUBAS: Rubric-Based Reinforcement Learning for Agent Safety cites this paper.

RUBAS: Rubric-Based Reinforcement Learning for Agent Safety Agent Safety Alignment via Reinforcement Learning

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:16:26.562656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 302533e2-3be7-4e66-9313-72f4e359b5d8 · inbound

SAFETY SENTRY: Context-Aware Human Intervention via EXECUTE-ASK-REFUSE Routing cites this paper.

SAFETY SENTRY: Context-Aware Human Intervention via EXECUTE-ASK-REFUSE Routing Agent Safety Alignment via Reinforcement Learning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T04:49:08.700306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1de972a0-65c9-483d-bc7a-6cef8dca0b61 · inbound

$S^3$: Improving Agent Safety through Multi-Stage Defense cites this paper.

$S^3$: Improving Agent Safety through Multi-Stage Defense Agent Safety Alignment via Reinforcement Learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T00:14:57.067936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fde75e9-3488-4d78-9538-2781d2be5cef · inbound

Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents cites this paper.

Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents Agent Safety Alignment via Reinforcement Learning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T19:23:23.093260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.