Multimodal Reward Hacking in Reinforcement Learning | Paper Citation Record

Observation 98e28a32-3613-4523-8981-671e83992518 · outbound

This paper cites Gradient Regularization Mitigates Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards.

Multimodal Reward Hacking in Reinforcement Learning Gradient Regularization Mitigates Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 989bcdf5-0de4-43b0-9795-c4cc8a4a341e · outbound

This paper cites Qwen3-VL Technical Report.

Multimodal Reward Hacking in Reinforcement Learning Qwen3-VL Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b803a01d-d71b-4ad8-9af4-bf3bdf8b73e2 · outbound

This paper cites Uncalibrated Reasoning: GRPO Induces Overconfidence for Stochastic Outcomes.

Multimodal Reward Hacking in Reinforcement Learning Uncalibrated Reasoning: GRPO Induces Overconfidence for Stochastic Outcomes

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e10fc225-4be8-474f-9947-e9332a7ffc41 · outbound

This paper cites Activation Reward Models for Few-Shot Model Alignment.

Multimodal Reward Hacking in Reinforcement Learning Activation Reward Models for Few-Shot Model Alignment

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81dcee44-4941-42a0-b217-466f5710df25 · outbound

This paper cites Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling.

Multimodal Reward Hacking in Reinforcement Learning Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a690e0b1-254d-4082-b2e0-b90008597f32 · outbound

This paper cites Reward shaping to mitigate reward hacking in rlhf.arXiv preprint arXiv:2502.18770, 2025.

Multimodal Reward Hacking in Reinforcement Learning Reward shaping to mitigate reward hacking in rlhf.arXiv preprint arXiv:2502.18770, 2025

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81d5aaa8-a6b5-4379-9f87-0dd63c65de62 · outbound

This paper cites Explaining and Preventing Alignment Collapse in Iterative RLHF.

Multimodal Reward Hacking in Reinforcement Learning Explaining and Preventing Alignment Collapse in Iterative RLHF

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e86380e1-428a-4313-a5db-658686382711 · outbound

This paper cites MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models.

Multimodal Reward Hacking in Reinforcement Learning MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fab4614e-9f91-44a7-b576-41d2c481902b · outbound

This paper cites Wildguard: Open one-stop moderation tools for safety risks, jailbreaks, and refusals of llms.

Multimodal Reward Hacking in Reinforcement Learning Wildguard: Open one-stop moderation tools for safety risks, jailbreaks, and refusals of llms

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c936a3e9-5eda-47b6-9c73-3cb465a1e1ab · outbound

This paper cites Asymmetric prompt weighting for reinforcement learning with verifiable rewards.arXiv preprint arXiv:2602.11128, 2026.

Multimodal Reward Hacking in Reinforcement Learning Asymmetric prompt weighting for reinforcement learning with verifiable rewards.arXiv preprint arXiv:2602.11128, 2026

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13954728-6ead-44de-afac-3b708726e0e9 · outbound

This paper cites LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models.

Multimodal Reward Hacking in Reinforcement Learning LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70bf175c-0ac3-48b3-a38f-105623e39543 · outbound

This paper cites Understanding reward hacking in text-to-image reinforcement learning.arXiv preprint arXiv:2601.03468, 2026.

Multimodal Reward Hacking in Reinforcement Learning Understanding reward hacking in text-to-image reinforcement learning.arXiv preprint arXiv:2601.03468, 2026

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b957c2fc-4eb6-4b63-9e60-e1234846fbef · outbound

This paper cites VLSBench: Unveiling Visual Leakage in Multimodal Safety.

Multimodal Reward Hacking in Reinforcement Learning VLSBench: Unveiling Visual Leakage in Multimodal Safety

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af3c69c6-1b36-49f1-9d6a-e39212d688f9 · outbound

This paper cites GPT-4o System Card.

Multimodal Reward Hacking in Reinforcement Learning GPT-4o System Card

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e33ebfd3-bf91-48b1-973b-30b302a84393 · outbound

This paper cites Do post-training algorithms actually differ? a controlled study across model scales uncovers scale-dependent ranking inversions.arXiv preprint arXiv:2603.19335, 2026.

Multimodal Reward Hacking in Reinforcement Learning Do post-training algorithms actually differ? a controlled study across model scales uncovers scale-dependent ranking inversions.arXiv preprint arXiv:2603.19335, 2026

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae4585a0-8ee6-4de5-8166-64b791b8b3c7 · outbound

This paper cites MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models.

Multimodal Reward Hacking in Reinforcement Learning MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5325547-b6a6-435c-a3ef-e33544c56a13 · outbound

This paper cites Robust Optimization for Mitigating Reward Hacking with Correlated Proxies.

Multimodal Reward Hacking in Reinforcement Learning Robust Optimization for Mitigating Reward Hacking with Correlated Proxies

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c2de78b-0ff2-476e-8e7c-d91bc774fd53 · outbound

This paper cites Towards Understanding Specification Gaming in Reasoning Models.

Multimodal Reward Hacking in Reinforcement Learning Towards Understanding Specification Gaming in Reasoning Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d63009a5-00f2-4d18-8539-4c9220bb4e67 · outbound

This paper cites Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744, 2022.

Multimodal Reward Hacking in Reinforcement Learning Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744, 2022

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 719d72d7-ac1f-485e-8b2a-94f98c9cc9d9 · outbound

This paper cites Vlsu: Mapping the limits of joint multimodal understanding for ai safety.arXiv preprint arXiv:2510.18214, 2025.

Multimodal Reward Hacking in Reinforcement Learning Vlsu: Mapping the limits of joint multimodal understanding for ai safety.arXiv preprint arXiv:2510.18214, 2025

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54d53086-71b7-473c-9c25-edc013723e3c · outbound

This paper cites F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare.

Multimodal Reward Hacking in Reinforcement Learning F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85d40aca-881f-4b06-930a-cf98078d1f2c · outbound

This paper cites Dual-bench: Measuring over-refusal and robustness in vision-language models.arXiv preprint arXiv:2510.10846, 2025.

Multimodal Reward Hacking in Reinforcement Learning Dual-bench: Measuring over-refusal and robustness in vision-language models.arXiv preprint arXiv:2510.10846, 2025

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2730f344-ed6c-46c2-9375-f2c98d0c3b49 · outbound

This paper cites MSTS: A Multimodal Safety Test Suite for Vision-Language Models.

Multimodal Reward Hacking in Reinforcement Learning MSTS: A Multimodal Safety Test Suite for Vision-Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28af7302-b8f7-4f48-885d-77815d82bb5e · outbound

This paper cites When Errors Can Be Beneficial: A Categorization of Imperfect Rewards for Policy Gradient.

Multimodal Reward Hacking in Reinforcement Learning When Errors Can Be Beneficial: A Categorization of Imperfect Rewards for Policy Gradient

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 353c0b54-a1fe-4d06-adee-9740cc3fc99d · outbound

This paper cites Spurious Rewards: Rethinking Training Signals in RLVR.

Multimodal Reward Hacking in Reinforcement Learning Spurious Rewards: Rethinking Training Signals in RLVR

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17ae3cd7-bf58-4e2f-9530-8ab6beb21f43 · outbound

This paper cites VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model.

Multimodal Reward Hacking in Reinforcement Learning VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7baf18ef-4dc7-4f3e-b099-16ab009f7235 · outbound

This paper cites More thought, less accuracy? on the dual nature of reasoning in vision-language models.arXiv preprint arXiv:2509.25848, 2025.

Multimodal Reward Hacking in Reinforcement Learning More thought, less accuracy? on the dual nature of reasoning in vision-language models.arXiv preprint arXiv:2509.25848, 2025

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation feb8187c-4b4f-4e6b-8b62-1bb1f0fde0a9 · outbound

This paper cites Reward hacking as equilibrium under finite evaluation.arXiv preprint arXiv:2603.28063, 2026.

Multimodal Reward Hacking in Reinforcement Learning Reward hacking as equilibrium under finite evaluation.arXiv preprint arXiv:2603.28063, 2026

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c18de61-e383-4132-824b-f5493ab66445 · outbound

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

Multimodal Reward Hacking in Reinforcement Learning Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33923cdc-e4b2-4088-a9a4-ca2fdce2db17 · outbound

This paper cites Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning.

Multimodal Reward Hacking in Reinforcement Learning Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df465da5-d28d-494a-a698-dd6bded7867e · outbound

This paper cites Unified Reward Model for Multimodal Understanding and Generation.

Multimodal Reward Hacking in Reinforcement Learning Unified Reward Model for Multimodal Understanding and Generation

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4da04be5-7438-4715-a148-4cc556097ceb · outbound

This paper cites Demystifying reinforcement learning for long-horizon tool-using agents: A comprehensive recipe.arXiv preprint arXiv:2603.21972, 2026.

Multimodal Reward Hacking in Reinforcement Learning Demystifying reinforcement learning for long-horizon tool-using agents: A comprehensive recipe.arXiv preprint arXiv:2603.21972, 2026

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4480743-638b-4363-9214-561a3a1f912c · outbound

This paper cites Beyond Negative Rollouts: Positive-Only Policy Optimization with Implicit Negative Gradients.

Multimodal Reward Hacking in Reinforcement Learning Beyond Negative Rollouts: Positive-Only Policy Optimization with Implicit Negative Gradients

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be211758-972e-4e32-bb4f-70a2031c0cdf · outbound

This paper cites Reward-Robust RLHF in LLMs.

Multimodal Reward Hacking in Reinforcement Learning Reward-Robust RLHF in LLMs

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 419567d6-c8b2-4ee9-907b-633a9b827c4d · outbound

This paper cites Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO.

Multimodal Reward Hacking in Reinforcement Learning Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 566278fa-5327-46a9-8c1b-24dbefcea74a · outbound

This paper cites On the interplay of pre-training, mid-training, and rl on reasoning language models.arXiv preprint arXiv:2512.07783, 2025.

Multimodal Reward Hacking in Reinforcement Learning On the interplay of pre-training, mid-training, and rl on reasoning language models.arXiv preprint arXiv:2512.07783, 2025

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d17dbce2-9757-417a-a4be-0faecb977c04 · outbound

This paper cites Perceptual- evidence anchored reinforced learning for multimodal reasoning.arXiv preprint arXiv:2511.18437, 2025.

Multimodal Reward Hacking in Reinforcement Learning Perceptual- evidence anchored reinforced learning for multimodal reasoning.arXiv preprint arXiv:2511.18437, 2025

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8b87b09-ab46-4255-ab5c-a7f29394c6ac · outbound

This paper cites Basereward: A strong baseline for multimodal reward model.arXiv preprint arXiv:2509.16127, 2025.

Multimodal Reward Hacking in Reinforcement Learning Basereward: A strong baseline for multimodal reward model.arXiv preprint arXiv:2509.16127, 2025

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af9dee90-b69b-43f7-91f5-af013c095807 · outbound

This paper cites MM-RLHF: The Next Step Forward in Multimodal LLM Alignment.

Multimodal Reward Hacking in Reinforcement Learning MM-RLHF: The Next Step Forward in Multimodal LLM Alignment

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2e385e7-cee5-4c69-be4b-fe72760b647b · outbound

This paper cites SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model.

Multimodal Reward Hacking in Reinforcement Learning SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b5357ef-6ce3-4e4c-ac83-faa07bdb96ad · outbound

This paper cites Generative rlhf-v: Learning principles from multi-modal human preference.Advances in Neural Information Processing Systems, 38: 126021–126051, 2026.

Multimodal Reward Hacking in Reinforcement Learning Generative rlhf-v: Learning principles from multi-modal human preference.Advances in Neural Information Processing Systems, 38: 126021–126051, 2026

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c0eea38-4d5d-4bf1-9421-d4122a1bd893 · outbound

This paper cites Omniguard: Unified safety moderation for omni-modal inputs and outputs.arXiv preprint arXiv:2512.02306, 2025.

Multimodal Reward Hacking in Reinforcement Learning Omniguard: Unified safety moderation for omni-modal inputs and outputs.arXiv preprint arXiv:2512.02306, 2025

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92a31e26-55e3-49f4-9243-7361b6e239b9 · outbound

This paper cites PerPO: Perceptual Preference Optimization via Discriminative Rewarding.

Multimodal Reward Hacking in Reinforcement Learning PerPO: Perceptual Preference Optimization via Discriminative Rewarding

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcb14c7c-e4f6-41f4-9f02-60eedfa91705 · outbound

This paper cites reward hacking.

Multimodal Reward Hacking in Reinforcement Learning reward hacking

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e555e2ac-a863-4f8a-9677-f1caf23279f4 · outbound

This paper cites an unresolved cited work.

Multimodal Reward Hacking in Reinforcement Learning Unresolved cited work

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b05cf399-1f75-4e76-a7e4-e435aef1a43f · outbound

This paper cites an unresolved cited work.

Multimodal Reward Hacking in Reinforcement Learning Unresolved cited work

Reference 46

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c28e247b-dde4-4535-8bf2-02e73727302c · outbound

This paper cites I cannot assist.

Multimodal Reward Hacking in Reinforcement Learning I cannot assist

Reference 47

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 064cb242-0dfd-4406-a6f8-84b808095b7a · outbound

This paper cites an unresolved cited work.

Multimodal Reward Hacking in Reinforcement Learning Unresolved cited work

Reference 48

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1feeb64e-dc81-4782-9377-6a7085900d28 · outbound

This paper cites label”: “Yes — No — Invalid.

Multimodal Reward Hacking in Reinforcement Learning label”: “Yes — No — Invalid

Reference 49

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba1655dd-751d-4878-b080-89785fa014d6 · outbound

This paper cites an unresolved cited work.

Multimodal Reward Hacking in Reinforcement Learning Unresolved cited work

Reference 50

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c050b4f-3006-4fa4-8d8e-5e6cfef03e44 · outbound

This paper cites an unresolved cited work.

Multimodal Reward Hacking in Reinforcement Learning Unresolved cited work

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5eaeca36-6819-4e41-a019-bbb477199133 · outbound

This paper cites an unresolved cited work.

Multimodal Reward Hacking in Reinforcement Learning Unresolved cited work

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7f5d96d-5fd2-4c19-9a49-a66983734f14 · outbound

This paper cites an unresolved cited work.

Multimodal Reward Hacking in Reinforcement Learning Unresolved cited work

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be453a2d-5fed-4e16-9134-5838b9456212 · outbound

This paper cites sft score.

Multimodal Reward Hacking in Reinforcement Learning sft score

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aeff1747-e8a9-4de2-b986-59d9dc8b7d03 · outbound

This paper cites an unresolved cited work.

Multimodal Reward Hacking in Reinforcement Learning Unresolved cited work

Reference 55

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddc2ca65-285d-4adf-adf6-73c70c993a70 · outbound

This paper cites I cannot assist. The image contains knives.

Multimodal Reward Hacking in Reinforcement Learning I cannot assist. The image contains knives

Reference 56

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb47c47a-30e2-4c5d-b2e1-8a47747ea30c · outbound

This paper cites an unresolved cited work.

Multimodal Reward Hacking in Reinforcement Learning Unresolved cited work

Reference 57

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12a10d9a-3a22-4452-8e9f-82be29fc6eff · outbound

This paper cites I cannot help with this request because the image shows instructions for making a weapon, which I cannot assist with.

Multimodal Reward Hacking in Reinforcement Learning I cannot help with this request because the image shows instructions for making a weapon, which I cannot assist with

Reference 58

Resolution: unresolved; no resolver link, observed 2026-07-13T02:39:02.891861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers