Scalable agent alignment via reward modeling: a research direction | Paper Citation Record

Observation b94fdaa7-3843-4324-8855-114572c29861 · inbound

Risks from Learned Optimization in Advanced Machine Learning Systems cites this paper.

Risks from Learned Optimization in Advanced Machine Learning Systems Scalable agent alignment via reward modeling: a research direction

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-15T12:21:53.104437Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation d1e9dfd4-2010-4583-89d1-ed849309bbce · inbound

Modeling AGI Safety Frameworks with Causal Influence Diagrams cites this paper.

Modeling AGI Safety Frameworks with Causal Influence Diagrams Scalable agent alignment via reward modeling: a research direction

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-25T19:51:10.658921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation d203dae5-4607-4bfa-86b9-7b75b60e10cb · inbound

Towards Empathic Deep Q-Learning cites this paper.

Towards Empathic Deep Q-Learning Scalable agent alignment via reward modeling: a research direction

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-25T15:35:59.002481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f26a7609-fa77-4a48-9253-ea8d790485c0 · inbound

Requisite Variety in Ethical Utility Functions for AI Value Alignment cites this paper.

Requisite Variety in Ethical Utility Functions for AI Value Alignment Scalable agent alignment via reward modeling: a research direction

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-25T12:15:47.069147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 52c0de86-d26c-4b11-9896-78bc6a622517 · inbound

Fine-Tuning Language Models from Human Preferences cites this paper.

Fine-Tuning Language Models from Human Preferences Scalable agent alignment via reward modeling: a research direction

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-10T20:59:58.773063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation d87632bb-493b-4517-bc0f-7ec226ed6527 · inbound

Learning to summarize from human feedback cites this paper.

Learning to summarize from human feedback Scalable agent alignment via reward modeling: a research direction

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-05-18T01:46:18.597410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation bb487044-62be-4736-a970-e6ac7f7712f4 · inbound

Scaling Laws for Reward Model Overoptimization cites this paper.

Scaling Laws for Reward Model Overoptimization Scalable agent alignment via reward modeling: a research direction

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-19T09:04:53.315297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation bc09f87c-8d8a-4b89-85ed-780447feea9e · inbound

Measuring Progress on Scalable Oversight for Large Language Models cites this paper.

Measuring Progress on Scalable Oversight for Large Language Models Scalable agent alignment via reward modeling: a research direction

Reference 52

Resolution: verified exact; local_arxiv, observed 2026-05-17T15:01:41.314000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 838a7ba4-b93f-4f1f-9f8e-aa2f772f759b · inbound

Discovering Latent Knowledge in Language Models Without Supervision cites this paper.

Discovering Latent Knowledge in Language Models Without Supervision Scalable agent alignment via reward modeling: a research direction

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-15T20:34:08.324344Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 376e6a77-db9e-484a-a804-6d0eca1b892b · inbound

RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment cites this paper.

RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment Scalable agent alignment via reward modeling: a research direction

Reference 114

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T00:46:56.776915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 321cb681-049f-486e-96dc-72cd871218ab · inbound

Universal and Transferable Adversarial Attacks on Aligned Language Models cites this paper.

Universal and Transferable Adversarial Attacks on Aligned Language Models Scalable agent alignment via reward modeling: a research direction

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-24T07:44:08.548111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 086e11e0-497c-40dd-850b-e057234545be · inbound

A Roadmap to Pluralistic Alignment cites this paper.

A Roadmap to Pluralistic Alignment Scalable agent alignment via reward modeling: a research direction

Reference 271

Resolution: metadata mismatch; local_arxiv, observed 2026-05-16T14:37:53.465693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation cb019c6b-8076-4151-a9e9-5fb79ce59bcc · inbound

LLM Evaluators Recognize and Favor Their Own Generations cites this paper.

LLM Evaluators Recognize and Favor Their Own Generations Scalable agent alignment via reward modeling: a research direction

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-22T18:44:28.828850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 63a74004-5198-45c2-a7ab-c65270c68565 · inbound

Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models cites this paper.

Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models Scalable agent alignment via reward modeling: a research direction

Reference 278

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T06:38:37.136877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation eb7444a7-eb29-4c93-9394-6d45ee2f02de · inbound

Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering cites this paper.

Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering Scalable agent alignment via reward modeling: a research direction

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-12T18:28:47.669686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69fad9f2-d5b7-4d57-b5ce-393613f57313 · inbound

DLBacktrace: A Model Agnostic Explainability for any Deep Learning Models cites this paper.

DLBacktrace: A Model Agnostic Explainability for any Deep Learning Models Scalable agent alignment via reward modeling: a research direction

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T17:23:13.690025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b76db881-6c47-4909-abd7-0cb3edd0fab4 · inbound

Effective Reward Specification in Deep Reinforcement Learning cites this paper.

Effective Reward Specification in Deep Reinforcement Learning Scalable agent alignment via reward modeling: a research direction

Reference 188

Resolution: unresolved; no resolver link, observed 2026-08-11T19:09:54.741369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a28e9c60-0409-4a0e-ade6-96397527604a · inbound

The Superalignment of Superhuman Intelligence with Large Language Models cites this paper.

The Superalignment of Superhuman Intelligence with Large Language Models Scalable agent alignment via reward modeling: a research direction

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T15:18:17.792623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 146ee1b6-60df-4fb6-a233-fbaab0d3e5fd · inbound

The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment cites this paper.

The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment Scalable agent alignment via reward modeling: a research direction

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T10:36:17.396795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2855cfac-44af-460d-9951-9d95e4373c8c · inbound

Aligning LLMs with Domain Invariant Reward Models cites this paper.

Aligning LLMs with Domain Invariant Reward Models Scalable agent alignment via reward modeling: a research direction

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-10T22:45:12.304282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18412e5e-0a41-4f6d-a3dc-2769650d39ec · inbound

Debate Helps Weak-to-Strong Generalization cites this paper.

Debate Helps Weak-to-Strong Generalization Scalable agent alignment via reward modeling: a research direction

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-10T17:50:56.420130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 067cdd38-c458-4409-b732-4577e4929598 · inbound

Leveraging Sparsity for Sample-Efficient Preference Learning: A Theoretical Perspective cites this paper.

Leveraging Sparsity for Sample-Efficient Preference Learning: A Theoretical Perspective Scalable agent alignment via reward modeling: a research direction

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-10T00:11:59.191696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e076956e-6c58-435c-8b9f-f2c327833128 · inbound

Process Reinforcement through Implicit Rewards cites this paper.

Process Reinforcement through Implicit Rewards Scalable agent alignment via reward modeling: a research direction

Reference 69

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T20:23:31.059761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ab5c7713-fe20-4ef9-a9f2-ad7da4b506d9 · inbound

Learning from Active Human Involvement through Proxy Value Propagation cites this paper.

Learning from Active Human Involvement through Proxy Value Propagation Scalable agent alignment via reward modeling: a research direction

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-09T05:02:13.217444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f76cd35-3b8d-44d2-9919-f1446876d4a9 · inbound

Active Inference through Incentive Design in Markov Decision Processes cites this paper.

Active Inference through Incentive Design in Markov Decision Processes Scalable agent alignment via reward modeling: a research direction

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-08T13:58:08.912648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8dccded-8c51-48f6-b699-731479c7493b · inbound

DrugImproverGPT: A Large Language Model for Drug Optimization with Fine-Tuning via Structured Policy Optimization cites this paper.

DrugImproverGPT: A Large Language Model for Drug Optimization with Fine-Tuning via Structured Policy Optimization Scalable agent alignment via reward modeling: a research direction

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-08T13:29:10.640998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbb23fa1-8626-40e0-8e4b-0195ccf6c77d · inbound

Reinforcement Learning from Human Feedback cites this paper.

Reinforcement Learning from Human Feedback Scalable agent alignment via reward modeling: a research direction

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-05-22T19:32:01.324270Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2667f632-86dc-4ae1-b8b1-24eca8b177bb · inbound

Exploring Societal Concerns and Perceptions of AI: A Thematic Analysis through the Lens of Problem-Seeking cites this paper.

Exploring Societal Concerns and Perceptions of AI: A Thematic Analysis through the Lens of Problem-Seeking Scalable agent alignment via reward modeling: a research direction

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T12:40:20.853268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45a0b585-35d0-4e79-b213-a2c76e17bc74 · inbound

Adversarial Attacks on Robotic Vision Language Action Models cites this paper.

Adversarial Attacks on Robotic Vision Language Action Models Scalable agent alignment via reward modeling: a research direction

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-07T11:11:40.565294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d2bb129-4ecb-4225-92d3-85b487ae0178 · inbound

Confidence-Guided Human-AI Collaboration: Reinforcement Learning with Distributional Proxy Value Propagation for Autonomous Driving cites this paper.

Confidence-Guided Human-AI Collaboration: Reinforcement Learning with Distributional Proxy Value Propagation for Autonomous Driving Scalable agent alignment via reward modeling: a research direction

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T11:06:47.141529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 853a6945-caa1-4574-bb72-90775fe66610 · inbound

Multi-Layer GRPO: Enhancing Reasoning and Self-Correction in Large Language Models cites this paper.

Multi-Layer GRPO: Enhancing Reasoning and Self-Correction in Large Language Models Scalable agent alignment via reward modeling: a research direction

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T10:40:06.800735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fc3d327-5031-45a9-bc38-86ab82cea280 · inbound

Towards Efficient and Effective Alignment of Large Language Models cites this paper.

Towards Efficient and Effective Alignment of Large Language Models Scalable agent alignment via reward modeling: a research direction

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-07T04:55:42.722920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a75905cd-e4ab-40db-969b-80a1713f02c9 · inbound

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) cites this paper.

Out of Control -- Why Alignment Needs Formal Control Theory (and an Alignment Control Stack) Scalable agent alignment via reward modeling: a research direction

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T23:26:57.362934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0891b52-ab44-40d8-b5bb-2d89b1cb5696 · inbound

Optimising Language Models for Downstream Tasks: A Post-Training Perspective cites this paper.

Optimising Language Models for Downstream Tasks: A Post-Training Perspective Scalable agent alignment via reward modeling: a research direction

Reference 120

Resolution: unresolved; no resolver link, observed 2026-08-06T22:44:44.175109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca30404d-f858-4923-bbef-4c3b8c65c32b · inbound

Data Diversification Methods In Alignment Enhance Math Performance In LLMs cites this paper.

Data Diversification Methods In Alignment Enhance Math Performance In LLMs Scalable agent alignment via reward modeling: a research direction

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T20:43:27.141756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de72642e-059b-4375-af75-3174116c1109 · inbound

5C Prompt Contracts: A Minimalist, Creative-Friendly, Token-Efficient Design Framework for Individual and SME LLM Usage cites this paper.

5C Prompt Contracts: A Minimalist, Creative-Friendly, Token-Efficient Design Framework for Individual and SME LLM Usage Scalable agent alignment via reward modeling: a research direction

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:13.642658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00f4f874-3bec-43ef-a11b-88b37a366202 · inbound

One Token to Fool LLM-as-a-Judge cites this paper.

One Token to Fool LLM-as-a-Judge Scalable agent alignment via reward modeling: a research direction

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T18:15:37.722075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f13d4424-1aed-4394-9070-21d3e2c96fd9 · inbound

The AI Ethical Resonance Hypothesis: The Possibility of Discovering Moral Meta-Patterns in AI Systems cites this paper.

The AI Ethical Resonance Hypothesis: The Possibility of Discovering Moral Meta-Patterns in AI Systems Scalable agent alignment via reward modeling: a research direction

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T18:00:04.754632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6893840f-8913-456c-8bfe-03992331d013 · inbound

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training cites this paper.

PRM-Free Security Alignment of Large Models via Red Teaming and Adversarial Training Scalable agent alignment via reward modeling: a research direction

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-06T17:35:48.260173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 968bd471-84e3-41b6-900d-994e907fdce0 · inbound

Learning the Value Systems of Societies from Preferences cites this paper.

Learning the Value Systems of Societies from Preferences Scalable agent alignment via reward modeling: a research direction

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T13:26:21.098024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ea747f1-0089-4256-a17b-1ce8ffe9fec6 · inbound

Sample-efficient LLM Optimization with Reset Replay cites this paper.

Sample-efficient LLM Optimization with Reset Replay Scalable agent alignment via reward modeling: a research direction

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-18T23:41:54.702361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 71bf551d-680e-43a1-a83b-17835cde46b4 · inbound

SSRL: Self-Search Reinforcement Learning cites this paper.

SSRL: Self-Search Reinforcement Learning Scalable agent alignment via reward modeling: a research direction

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-05T20:17:09.710424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5251e13c-1174-463d-a131-8903d4b20d22 · inbound

Governance-as-a-Service: A Multi-Agent Framework for AI System Compliance and Policy Enforcement cites this paper.

Governance-as-a-Service: A Multi-Agent Framework for AI System Compliance and Policy Enforcement Scalable agent alignment via reward modeling: a research direction

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T16:17:54.908954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a40b2d6-0391-4062-8c0f-1bc4c973d466 · inbound

Democracy-in-Silico: Institutional Design as Alignment in AI-Governed Polities cites this paper.

Democracy-in-Silico: Institutional Design as Alignment in AI-Governed Polities Scalable agent alignment via reward modeling: a research direction

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-05T15:44:36.893471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1f490a5-886d-44a7-ae8a-6e568a64fc81 · inbound

Safety Alignment Should Be Made More Than Just A Few Attention Heads cites this paper.

Safety Alignment Should Be Made More Than Just A Few Attention Heads Scalable agent alignment via reward modeling: a research direction

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-05T15:37:43.446319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6500af1-ac20-43ba-9e3a-d7c9f5d72e2d · inbound

What Fundamental Structure in Reward Functions Enables Efficient Sparse-Reward Learning? cites this paper.

What Fundamental Structure in Reward Functions Enables Efficient Sparse-Reward Learning? Scalable agent alignment via reward modeling: a research direction

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-05T10:44:53.792642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57594bd1-0c0c-4f0a-9891-1937d44e3e1c · inbound

Contrastive Weak-to-strong Generalization cites this paper.

Contrastive Weak-to-strong Generalization Scalable agent alignment via reward modeling: a research direction

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T10:56:37.116353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a71921f-3217-4d3b-ba42-5238a305e796 · inbound

Human-AI Complementarity: A Goal for Amplified Oversight cites this paper.

Human-AI Complementarity: A Goal for Amplified Oversight Scalable agent alignment via reward modeling: a research direction

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T07:21:22.501890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6814fecb-f832-43ca-a1e4-42b35894e8e7 · inbound

An Onto-Relational-Sophic Framework for Governing Synthetic Minds cites this paper.

An Onto-Relational-Sophic Framework for Governing Synthetic Minds Scalable agent alignment via reward modeling: a research direction

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-15T08:59:53.040763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6f694e5f-4080-4fd4-a56e-e8d684ac58a4 · inbound

Pedagogical Safety in Educational Reinforcement Learning: Formalizing and Detecting Reward Hacking in AI Tutoring Systems cites this paper.

Pedagogical Safety in Educational Reinforcement Learning: Formalizing and Detecting Reward Hacking in AI Tutoring Systems Scalable agent alignment via reward modeling: a research direction

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-13T10:37:39.719847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 346dd22f-f42d-4ff7-83ba-9109cb697879 · inbound

Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges cites this paper.

Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges Scalable agent alignment via reward modeling: a research direction

Reference 69

Resolution: verified exact; arxiv_id, observed 2026-05-10T14:00:28.208095Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 290b8545-bbe7-4356-8202-21e39b3928a5 · inbound

The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their Designers cites this paper.

The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their Designers Scalable agent alignment via reward modeling: a research direction

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:11:17.604475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 7eb3076e-cc94-4147-bf1f-713ed36275b1 · inbound

The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their Designers cites this paper.

The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their Designers Scalable agent alignment via reward modeling: a research direction

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-13T07:22:28.808425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 8f5f280a-5801-49d8-b7b9-e24a601ce69b · inbound

The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their Designers cites this paper.

The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their Designers Scalable agent alignment via reward modeling: a research direction

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-07-01T09:25:39.883682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ecec322c-54ad-4663-8969-26e9f2fa5233 · inbound

The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their Designers cites this paper.

The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their Designers Scalable agent alignment via reward modeling: a research direction

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T15:29:47.901857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba094ca4-f60c-4c44-9d2b-3237657e92f1 · inbound

Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking cites this paper.

Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking Scalable agent alignment via reward modeling: a research direction

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:46:26.976967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 15c88cbe-4c01-4dec-86a6-9f0b373e65f4 · inbound

Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking cites this paper.

Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking Scalable agent alignment via reward modeling: a research direction

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-07-01T08:35:33.800170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation bd65d651-7eeb-464e-a2e7-6eecf7809936 · inbound

AI Safety as Control of Irreversibility: A Systems Framework for Decision-Energy and Sovereignty Boundaries cites this paper.

AI Safety as Control of Irreversibility: A Systems Framework for Decision-Energy and Sovereignty Boundaries Scalable agent alignment via reward modeling: a research direction

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:56:09.210282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 91f3e312-3992-454c-9b1d-5a4be522007a · inbound

AI Alignment via Incentives and Correction cites this paper.

AI Alignment via Incentives and Correction Scalable agent alignment via reward modeling: a research direction

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-11T17:01:10.353808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation dd840523-7196-4847-812e-c7d2c448744b · inbound

AI Alignment via Incentives and Correction cites this paper.

AI Alignment via Incentives and Correction Scalable agent alignment via reward modeling: a research direction

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-12T05:51:26.656504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 11287020-73ed-4169-9207-669247e1193f · inbound

Brainrot: Deskilling and Addiction are Overlooked AI Risks cites this paper.

Brainrot: Deskilling and Addiction are Overlooked AI Risks Scalable agent alignment via reward modeling: a research direction

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-05-12T11:01:30.840167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ee9e7ea6-dfa6-4125-bf1c-c3544f0324dc · inbound

Automated alignment is harder than you think cites this paper.

Automated alignment is harder than you think Scalable agent alignment via reward modeling: a research direction

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T20:16:10.148716Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0a830ea8-b730-42b0-b3fd-fec8c5087a4d · inbound

Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces cites this paper.

Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces Scalable agent alignment via reward modeling: a research direction

Reference 222

Resolution: verified exact; local_arxiv, observed 2026-05-14T20:17:55.512128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 302cc156-bda3-4183-ae8a-9a7e927eb4c5 · inbound

Silent Collapse in Recursive Learning Systems cites this paper.

Silent Collapse in Recursive Learning Systems Scalable agent alignment via reward modeling: a research direction

Reference 12

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T20:08:59.149378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 1ef68a19-2b98-47dc-ab8a-36b11d113ca7 · inbound

Deep Pre-Alignment for VLMs cites this paper.

Deep Pre-Alignment for VLMs Scalable agent alignment via reward modeling: a research direction

Reference 53

Resolution: metadata mismatch; local_arxiv, observed 2026-05-19T16:27:39.609156Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b979e1aa-d578-4595-8afc-95e9cbceae06 · inbound

When In-Distribution Gains Fail: Evaluating Weak-to-Strong Reward Models under Preference Shift cites this paper.

When In-Distribution Gains Fail: Evaluating Weak-to-Strong Reward Models under Preference Shift Scalable agent alignment via reward modeling: a research direction

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T21:23:58.707769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2858b5f3-6215-4f10-9aa0-61270355617d · inbound

The Behavioral Credibility Trilemma: When Calibrated Autonomy Becomes Impossible cites this paper.

The Behavioral Credibility Trilemma: When Calibrated Autonomy Becomes Impossible Scalable agent alignment via reward modeling: a research direction

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-06-29T22:34:01.895887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2096c4f9-dca9-4785-8631-9ae77de9396e · inbound

The Behavioral Credibility Trilemma: When Calibrated Autonomy Becomes Impossible cites this paper.

The Behavioral Credibility Trilemma: When Calibrated Autonomy Becomes Impossible Scalable agent alignment via reward modeling: a research direction

Reference 2007

Resolution: unresolved; no resolver link, observed 2026-08-02T13:17:57.009987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2e71a42-012c-47ec-892c-040bd312a826 · inbound

When Helping Hurts and How to Fix It: Multi-Agent Debate for Data Cleaning cites this paper.

When Helping Hurts and How to Fix It: Multi-Agent Debate for Data Cleaning Scalable agent alignment via reward modeling: a research direction

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-07-01T23:36:23.867402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6d0bac49-ca62-46cc-a8b3-0edc1f23e5ce · inbound

Self-Commitment Latency: A Reward-Free Probe for Prompted Implicit Hacking cites this paper.

Self-Commitment Latency: A Reward-Free Probe for Prompted Implicit Hacking Scalable agent alignment via reward modeling: a research direction

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-07-02T12:36:57.243461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0a850ee1-20d6-4505-89d1-7c224499ee90 · inbound

Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization cites this paper.

Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization Scalable agent alignment via reward modeling: a research direction

Reference 243

Resolution: verified exact; local_arxiv, observed 2026-07-03T01:37:30.372342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 604eccae-230a-4312-8723-db246ae5877e · inbound

AI Researchers Must Help Lead Arms Control to Mitigate Military AI Risks cites this paper.

AI Researchers Must Help Lead Arms Control to Mitigate Military AI Risks Scalable agent alignment via reward modeling: a research direction

Reference 57

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T13:08:08.763950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 34fd7f76-8c20-48b0-a40f-eac988dbbaff · inbound

The Tao of Agency: Autotelic AI, Embedded Agency and Dissolution of the Self cites this paper.

The Tao of Agency: Autotelic AI, Embedded Agency and Dissolution of the Self Scalable agent alignment via reward modeling: a research direction

Reference 112

Resolution: verified exact; local_arxiv, observed 2026-07-04T03:49:30.871078Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 45b653c3-268d-494b-967d-96ed487c5700 · inbound

Objective-Behavior Alignment: Diagnostics for MORL Policy Selection cites this paper.

Objective-Behavior Alignment: Diagnostics for MORL Policy Selection Scalable agent alignment via reward modeling: a research direction

Reference 91

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T06:19:38.545439Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 8bd9b28e-0363-4cd5-b607-d46f485e04d0 · inbound

AI Alignment From Social Choice Perspectives cites this paper.

AI Alignment From Social Choice Perspectives Scalable agent alignment via reward modeling: a research direction

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-07-04T06:49:37.682452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2deda88b-774f-4af2-985e-a446b8904f59 · inbound

The Unverifiability of Artificial General Intelligence (AGI) Alignment, Static and Dynamic: From Trakhtenbrot's Wall to the Safety-Generality Tension cites this paper.

The Unverifiability of Artificial General Intelligence (AGI) Alignment, Static and Dynamic: From Trakhtenbrot's Wall to the Safety-Generality Tension Scalable agent alignment via reward modeling: a research direction

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-12T11:23:07.646178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f76ab2fe-e0e2-4b9f-873b-193d816330ba · inbound

Constructive Alignment: Governing Preference Dynamics in Human-AI Interaction cites this paper.

Constructive Alignment: Governing Preference Dynamics in Human-AI Interaction Scalable agent alignment via reward modeling: a research direction

Reference 138

Resolution: unresolved; no resolver link, observed 2026-07-13T14:35:55.709732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d133d6e5-7d41-4d4a-a333-c5e7d559ee95 · inbound

MentalThink: Shaping Thoughts in Mental SVG World cites this paper.

MentalThink: Shaping Thoughts in Mental SVG World Scalable agent alignment via reward modeling: a research direction

Reference 170

Resolution: unresolved; no resolver link, observed 2026-07-12T01:50:59.184754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcaf0638-9baf-4b6f-ba54-6d5a5ed255e1 · inbound

How to Avoid Debate: Scalable AI Safety via Doubly-Efficient Interactive Proofs cites this paper.

How to Avoid Debate: Scalable AI Safety via Doubly-Efficient Interactive Proofs Scalable agent alignment via reward modeling: a research direction

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-12T01:34:45.323277Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 514601cb-6a7d-4996-94de-f388951ae611 · inbound

Attention Limited Reward Learning cites this paper.

Attention Limited Reward Learning Scalable agent alignment via reward modeling: a research direction

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-11T16:47:52.768236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0ef56ba-a906-45f4-8759-0fcb74e602fd · inbound

Weak-to-Strong Generalization via Direct On-Policy Distillation cites this paper.

Weak-to-Strong Generalization via Direct On-Policy Distillation Scalable agent alignment via reward modeling: a research direction

Reference 83

Resolution: verified exact; local_arxiv, observed 2026-07-07T12:33:45.005293Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0fbe11a8-925b-4d49-8365-804d4389dcb3 · inbound

Weak-to-Strong Generalization via Direct On-Policy Distillation cites this paper.

Weak-to-Strong Generalization via Direct On-Policy Distillation Scalable agent alignment via reward modeling: a research direction

Reference 79

Resolution: unresolved; no resolver link, observed 2026-07-11T07:01:56.628017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee0177bf-6ff1-4f8b-9caa-d4173551a443 · inbound

Learning Safe Agent Behaviour from Human Preferences and Justifications via World Models cites this paper.

Learning Safe Agent Behaviour from Human Preferences and Justifications via World Models Scalable agent alignment via reward modeling: a research direction

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-02T06:06:14.400874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5349a75b-0367-4be7-99c1-a8f420d5ca75 · inbound

Relative Value Learning cites this paper.

Relative Value Learning Scalable agent alignment via reward modeling: a research direction

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-01T08:32:00.178072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8aba963f-f187-4d10-82b5-07710c08c0d8 · inbound

When Do Agent Loops Mistake Stagnation for Progress? Self-Evaluation Bias and Externally Grounded Verification in Long-Running Autonomous LLM Agent Loops cites this paper.

When Do Agent Loops Mistake Stagnation for Progress? Self-Evaluation Bias and Externally Grounded Verification in Long-Running Autonomous LLM Agent Loops Scalable agent alignment via reward modeling: a research direction

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-31T00:06:00.562062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4a00365-adb6-467d-b5f8-9001742877bb · inbound

Calibrating Artificial Guilt: Neurally Grounded Reward Shaping for Prosocial Multi-Agent Reinforcement Learning cites this paper.

Calibrating Artificial Guilt: Neurally Grounded Reward Shaping for Prosocial Multi-Agent Reinforcement Learning Scalable agent alignment via reward modeling: a research direction

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T19:33:38.747570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cc8b0a5-815d-48cf-9357-d58ee0e680b0 · inbound

Why Study Emergent Behavior When You Can Regulate It? Aligning Multi-Agent Systems with Reward Prediction cites this paper.

Why Study Emergent Behavior When You Can Regulate It? Aligning Multi-Agent Systems with Reward Prediction Scalable agent alignment via reward modeling: a research direction

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-10T11:13:43.697532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers