---
title: "SuperIntelligence - Robotics - Safety & Alignment 2025 — all"
description: "All 70 papers of SuperIntelligence - Robotics - Safety & Alignment 2025, the most cited first; those with our summary link to it."
canonical: "https://research.elamur.ai/free/en/venues/superintelligence-robotics-safety-alignment/2025/papers/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/venues/superintelligence-robotics-safety-alignment/2025/papers/)

[home](https://md.research.elamur.ai/free/en/) / [venues](https://md.research.elamur.ai/free/en/venues/) / [SuperIntelligence - Robotics - Safety &…](https://md.research.elamur.ai/free/en/venues/superintelligence-robotics-safety-alignment/) / [2025](https://md.research.elamur.ai/free/en/venues/superintelligence-robotics-safety-alignment/2025/) / papers

# SuperIntelligence - Robotics - Safety & Alignment 2025: all accepted papers

70 papers · the most cited first · [← SuperIntelligence - Robotics - Safety & Alignment 2025](https://md.research.elamur.ai/free/en/venues/superintelligence-robotics-safety-alignment/2025/)

1. **[AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges ↗](https://doi.org/10.70777/si.v2i3.15161)**Ranjan Sapkota, Konstantinos I. Roumeliotis, Manoj Karkee*181 citations*
2. **[The Illusion of Thinking ↗](https://doi.org/10.70777/si.v2i6.15919)**Parshin Shojaee, Iman Mirzadeh, Keivan Alizadeh et al.*152 citations*
3. **[The First International AI Safety Report ↗](https://doi.org/10.70777/si.v2i2.14755)**Yoshua Bengio*47 citations*
4. **[Brief analysis of DeepSeek R1 and its implications for Generative AI ↗](https://doi.org/10.70777/si.v2i1.11097)**Sarah Mercer, Samuel Spillard, Daniel J. Martin*35 citations*
5. **[Deliberative Alignment: Reasoning Enables Safer Language Models](https://md.research.elamur.ai/free/en/papers/guan-2024-deliberative-alignment-reasoning-enables-safer/)**Melody Y. Guan, Manas Joglekar, Eric Wallace et al.*35 citations · our summary*
6. **[Humanity's Last Exam ↗](https://doi.org/10.70777/si.v2i1.13973)**Long Phan, Alice Gatti, Ziwen Han et al.*32 citations*
7. **[Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents ↗](https://doi.org/10.70777/si.v2i3.15063)**Jenny Zhang, Shengran Hu, Cong Lu et al.*26 citations*
8. **[Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path? ↗](https://doi.org/10.70777/si.v2i5.15569)**Yoshua Bengio, Michael K. Cohen, Damiano Fornasiere et al.*14 citations*
9. **[Review: Large Language Models Pass the Turing Test ↗](https://doi.org/10.70777/si.v2i2.14697)**Kristen W. Carlson*9 citations*
10. **[On DeepSeek and Export Controls ↗](https://doi.org/10.70777/si.v2i1.10695)**Dario Amodei*8 citations*
11. **[The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment ↗](https://doi.org/10.70777/si.v2i1.13963)**HyunJin Kim, Xiaoyuan Yi, JinYeong Bak et al.*8 citations*
12. **[America's AI Action Plan ↗](https://doi.org/10.70777/si.v2i5.15507)**Office of Science and Technology Policy*6 citations*
13. **[From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training ↗](https://doi.org/10.70777/si.v2i6.15625)**Yuan Yuan, Tina Sriskandarajah, Anna-Luisa Brakman et al.*6 citations*
14. **[Superintelligence Strategy: Expert Version ↗](https://doi.org/10.70777/si.v2i1.13961)**Dan Hendrycks, Eric Schmidt, Alexandr Wang*5 citations*
15. **[The Singapore Consensus on Global AI Safety Research Priorities ↗](https://doi.org/10.70777/si.v2i5.15503)**Yoshua Bengio, Max Tegmark, Stuart Russell et al.*5 citations*
16. **[Anthropic: Responsible Scaling Policy ↗](https://doi.org/10.70777/si.v2i1.13657)**Evan Hubinger*4 citations*
17. **[Responsible Agentic Reasoning and AI Agents: A Critical Survey ↗](https://doi.org/10.70777/si.v2i6.16169)**Shaina Raza, Ranjan Sapkota, Manoj Karkee et al.*4 citations*
18. **[A Grading Rubric for AI Safety Frameworks ↗](https://doi.org/10.70777/si.v2i5.16331)**Jide Alaga, Jonas Schuett, Markus Anderljung*3 citations*
19. **[Effective Mitigations for Systemic Risks from General-Purpose AI ↗](https://doi.org/10.70777/si.v2i1.13975)**Risto Uuk, Annemieke Brouwer, Tim Schreier et al.*3 citations*
20. **[Seeking Stability in the Competition for AI Advantage ↗](https://doi.org/10.70777/si.v2i1.14023)**Iskander Rehman, Karl P. Mueller, Michael J. Mazarr*3 citations*
21. **[Trends in Frontier AI Model Count: A Forecast to 2028 ↗](https://doi.org/10.70777/si.v2i3.15155)**Iyngkarran Kumar, Sam Manning*3 citations*
22. **[Critical Review: Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning ↗](https://doi.org/10.70777/si.v2i4.15315)**Kristen W. Carlson*2 citations*
23. **[DarwinLM: Evolutionary Structured Pruning of Large Language Models ↗](https://doi.org/10.70777/si.v2i3.15171)**Shengkun Tang, Oliver Sieberling, Eldar Kurtic et al.*2 citations*
24. **[Hardware-Enabled Mechanisms for Verifying Responsible AI Development ↗](https://doi.org/10.70777/si.v2i3.15157)**Aidan O’Gara, Gabriel Kulp, Will Hodgkins et al.*2 citations*
25. **[In Which Areas of Technical AI Safety Could Geopolitical Rivals Cooperate? ↗](https://doi.org/10.70777/si.v2i5.15509)**Ben Bucknall, Saad Siddiqui, Lara Thurnherr et al.*2 citations*
26. **[Measuring AI Agent Autonomy: Towards a Scalable Approach with Code Inspection ↗](https://doi.org/10.70777/si.v2i3.15295)**Peter Cihon, Merlin Stein, Gagan Bansal et al.*2 citations*
27. **[Pitfalls of Evidence-Based AI Policy ↗](https://doi.org/10.70777/si.v2i2.14611)**Stephen Casper, David Krueger, Dylan Hadfield-Menell*2 citations*
28. **[Safety at Scale: A Comprehensive Survey of Large Model Safety ↗](https://doi.org/10.70777/si.v2i2.14609)**Yu–Gang Jiang, Xingjun Ma, Yifeng Gao et al.*2 citations*
29. **[Strategic Patience: Long-Horizon AI Dominance and the Erosion of Human Vigilance ↗](https://doi.org/10.70777/si.v2i2.14435)**Roman V. Yampolskiy*2 citations*
30. **[A Framework for the Private Governance of Frontier Artificial Intelligence ↗](https://doi.org/10.70777/si.v2i2.14519)**Dean Ball*1 citation*
31. **[Can a Bayesian Oracle Prevent Harm from an Agent? ↗](https://doi.org/10.70777/si.v2i1.13799)**Yoshua Bengio, Matt McDermott, Michael K. Cohen et al.*1 citation*
32. **[Highlights of the Issue: Governance, Agents, Evolutionary Search ↗](https://doi.org/10.70777/si.v2i3.15417)**Kristen W. Carlson*1 citation*
33. **[International AI Safety Report 2025: Second Key Update: Technical Safeguards and Risk Management ↗](https://doi.org/10.70777/si.v2i4.16671)**Yoshua Bengio, Stephen Clare, Carina Prunkl et al.*1 citation*
34. **[International Al Safety Report: First Key Update Capabilities and Risk Implications ↗](https://doi.org/10.70777/si.v2i6.16253)**Yoshua Bengio, Ben Bucknall, Stephen Clare et al.*1 citation*
35. **[Multiple unnatural attributes of AI undermine common anthropomorphically biased takeover speculations ↗](https://doi.org/10.70777/si.v2i1.13801)**Preston W. Estep*1 citation*
36. **[OpenAI: Toward Mechanistic Interpretability (MI) ↗](https://doi.org/10.70777/si.v2i6.16545)**Kristen W. Carlson*1 citation*
37. **[Review: Addressing the challenges of harmonizing law and artificial intelligence technology in modern society ↗](https://doi.org/10.70777/si.v2i2.14807)**Kristen W. Carlson*1 citation*
38. **[Review: Safety at Scale: Comprehensive Survey of Large Model Safety ↗](https://doi.org/10.70777/si.v2i2.14741)**Kristen W. Carlson*1 citation*
39. **[Simulating Influence Dynamics with LLM Agents ↗](https://doi.org/10.70777/si.v2i1.13971)**Mehwish Nasim, Syed Muslim Gilani, Amin Qasmi et al.*1 citation*
40. **[AI Timeline: 2025-2030+ ↗](https://doi.org/10.70777/si.v2i6.16375)**Gil Syswerda
41. **[Analysis of FLI’s AI Action Plan Recommendations and Proposed Policy Framework ↗](https://doi.org/10.70777/si.v2i1.14139)**Gil Syswerda
42. **[California Senate Bill 813: A Novel Approach to Artificial Intelligence Governance ↗](https://doi.org/10.70777/si.v2i2.14571)**Kristen W. Carlson
43. **[Comparing Apples to Oranges: A Taxonomy for Navigating the Global Landscape of AI Regulation ↗](https://doi.org/10.70777/si.v2i3.15137)**Sacha Alanoca, Shira Gur-Arieh, Tom Zick et al.
44. **[Enabling Frontier Lab Collaboration to Mitigate AI Safety Risks ↗](https://doi.org/10.70777/si.v2i6.16439)**Nicholas Felstead
45. **[Evidence Integrity Before Capability: A Prerequisite for Safe Artificial Intelligence ↗](https://doi.org/10.70777/si.v2i6.16393)**Jennifer Kinne
46. **[Highlights of the Issue ↗](https://doi.org/10.70777/si.v2i1.14075)**Kristen W. Carlson
47. **[Highlights of the Issue ↗](https://doi.org/10.70777/si.v2i2.14909)**Kristen W. Carlson
48. **[Highlights of the Issue - Large Language Models III ↗](https://doi.org/10.70777/si.v2i6.15969)**Kristen W. Carlson
49. **[Highlights of the Issue: Singapore Consensus – Safety Technology ↗](https://doi.org/10.70777/si.v2i5.15525)**Kristen W. Carlson
50. **[How to Align Artificial Superintelligence ↗](https://doi.org/10.70777/si.v2i5.15579)**Avraham Yair Negozio
51. **[Outline: Proposed Zero Draft for a Standard on AI Testing, Evaluation, Verification, and Validation ↗](https://doi.org/10.70777/si.v2i5.15513)**National Institute of Standards and Technology
52. **[Pathways to Short Transformative AI Timelines ↗](https://doi.org/10.70777/si.v2i1.13603)**Zershaaneh Qureshi
53. **[Precedents for the Unprecedented: Historical Analogies for Thirteen Artificial Superintelligence Risks ↗](https://doi.org/10.70777/si.v2i6.16999)**James D. Miller
54. **[Quantum Immortality ↗](https://doi.org/10.70777/si.v2i2.14439)**Alexey Turchin, James D. Miller
55. **[Review: AI Governance through Markets ↗](https://doi.org/10.70777/si.v2i2.14601)**Kristen W. Carlson
56. **[Review: First International AI Safety Report ↗](https://doi.org/10.70777/si.v2i2.14757)**Kristen W. Carlson
57. **[Review: Large Language Model-Powered AI Systems Achieve Self-Replication with No Human Intervention ↗](https://doi.org/10.70777/si.v2i2.14689)**Kristen W. Carlson
58. **[Review: Large language Model-Powered AI Systems Achieve Self-Replication with No Human Intervention ↗](https://doi.org/10.70777/si.v2i2.14607)**Kristen W. Carlson
59. **[Review: Metacognition in LLMs and its Relation to Safety ↗](https://doi.org/10.70777/si.v2i3.15271)**Kristen W. Carlson
60. **[Review: On Regulating Downstream AI Developers ↗](https://doi.org/10.70777/si.v2i2.14587)**Kristen W. Carlson
61. **[Review: Strategic Patience: Long-Horizon AI Dominance and the Erosion of Human Vigilance ↗](https://doi.org/10.70777/si.v2i2.14603)**Kristen W. Carlson
62. **[Standardizing Intelligence: Aligning Generative AI for Regulatory and Operational Compliance ↗](https://doi.org/10.70777/si.v2i5.16189)**Joseph Marvin Imperial, Matthew D. Jones, Harish Tayyar Madabushi
63. **[The Asymptotic Intelligence Thesis: Rethinking the Ceiling of AGI Cognition ↗](https://doi.org/10.70777/si.v2i6.16255)**Jeffrey E. Arle
64. **[The Evolution of AI Communication: From Chain-of-Thought to Neuralese and the Case for Interpretability Agents ↗](https://doi.org/10.70777/si.v2i5.16187)**Erhan Arslan
65. **[The Perilous State of AI Governance, June 2025 ↗](https://doi.org/10.70777/si.v2i2.14801)**Kristen W. Carlson
66. **[Thinking Isn’t an Illusion ↗](https://doi.org/10.70777/si.v2i6.15961)**Zhao Song, Song Yue, Jiahao Zhang
67. **[Timeline to Artificial General Intelligence 2025 – 2030+ ↗](https://doi.org/10.70777/si.v2i3.15119)**Gil Syswerda
68. **[Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation ↗](https://doi.org/10.70777/si.v2i3.15249)**Tharindu Kumarage, Ninareh Mehrabi, Anil Ramakrishna et al.
69. **[Understanding Limitations of Large Language Models from First Principles ↗](https://doi.org/10.70777/si.v2i6.16549)**Kristen W. Carlson
70. **[Why We Might Need Advanced AI to Save Us from Doomers, Rather than the Other Way Around ↗](https://doi.org/10.70777/si.v2i6.16251)**Preston W. Estep
- [← back to](https://md.research.elamur.ai/free/en/venues/superintelligence-robotics-safety-alignment/2025/) — SuperIntelligence - Robotics - Safety & Alignment 2025