# Research **URL:** https://discuss.huggingface.co/c/research/7.md [Latest](https://discuss.huggingface.co/latest.md) · [Categories](https://discuss.huggingface.co/categories.md) --- ## [📌 Papers: Indexing & Authorship Claim — Quick Help](https://discuss.huggingface.co/t/papers-indexing-authorship-claim-quick-help/173387)
**Author:** [@hysts](https://discuss.huggingface.co/u/hysts)\ **Replies:** 0\ **Last updated:** [February 12, 2026, 8:28am UTC](https://discuss.huggingface.co/t/papers-indexing-authorship-claim-quick-help/173387 "2026-02-12T08:28:50Z")
1) Indexing issues (paper page creation) If you see “Indexing failed or took too long” or “Paper not found”: Wait and retry later. Indexing can fail temporarily due to upstream availability. Please don’t repeatedly cli… --- ## [Large source’s chunks are overrides small source’s chunks](https://discuss.huggingface.co/t/large-source-s-chunks-are-overrides-small-source-s-chunks/191389)
**Author:** [@dipnitsan](https://discuss.huggingface.co/u/dipnitsan)\ **Replies:** 0\ **Last updated:** [November 3, 2026, 10:50am UTC](https://discuss.huggingface.co/t/large-source-s-chunks-are-overrides-small-source-s-chunks/191389 "2026-11-03T10:50:49Z")
Hello guys, I got some serious issue in my RAG pipeline. Here is the case, I’ve already trained almost 10 large source urls (~1500 pages each), and then I’ve indexed one small pdf document which has hardly 5 chunks th… --- ## [We gave AI a trust we never gave people - The third axis, after capability and permission](https://discuss.huggingface.co/t/we-gave-ai-a-trust-we-never-gave-people-the-third-axis-after-capability-and-permission/183807)
**Author:** [@Jang-woo](https://discuss.huggingface.co/u/Jang-woo)\ **Replies:** 22\ **Last updated:** [November 3, 2026, 5:10am UTC](https://discuss.huggingface.co/t/we-gave-ai-a-trust-we-never-gave-people-the-third-axis-after-capability-and-permission/183807 "2026-11-03T05:10:17Z")
We gave AI a trust we never gave people The third axis, after capability and permission What we ask now When an agent causes an incident, we ask the model. Why did you send that address. Why did you say he was home.… --- ## [Research proposal: What does an agent build to sustain its own work?](https://discuss.huggingface.co/t/research-proposal-what-does-an-agent-build-to-sustain-its-own-work/191361)
**Author:** [@SheilaMayoAI](https://discuss.huggingface.co/u/SheilaMayoAI)\ **Replies:** 4\ **Last updated:** [November 3, 2026, 3:21am UTC](https://discuss.huggingface.co/t/research-proposal-what-does-an-agent-build-to-sustain-its-own-work/191361 "2026-11-03T03:21:33Z")
I am developing a proposal at Sheila Studios for studying agent-built tools, continuity and repair. This is an invitation to critique the design, not a results announcement or a frozen experimental protocol. Companion f… --- ## [A model passing a task is not proof that the system passed](https://discuss.huggingface.co/t/a-model-passing-a-task-is-not-proof-that-the-system-passed/191349)
**Author:** [@BrandenLaskowski7](https://discuss.huggingface.co/u/BrandenLaskowski7)\ **Replies:** 1\ **Last updated:** [November 3, 2026, 1:40am UTC](https://discuss.huggingface.co/t/a-model-passing-a-task-is-not-proof-that-the-system-passed/191349 "2026-11-03T01:40:10Z")
If an AI worker produces the right answer while: using information it was not authorized to access, stepping outside its role, violating a required behavioral standard, or failing to preserve evidence of how the work w… --- ## [How to evaluate deceptive dialogue in LLM-based NPCs?](https://discuss.huggingface.co/t/how-to-evaluate-deceptive-dialogue-in-llm-based-npcs/190842)
**Author:** [@dameSY](https://discuss.huggingface.co/u/dameSY)\ **Replies:** 12\ **Last updated:** [November 2, 2026, 10:15pm UTC](https://discuss.huggingface.co/t/how-to-evaluate-deceptive-dialogue-in-llm-based-npcs/190842 "2026-11-02T22:15:16Z")
Hi everyone! I’m studying game AI and looking into LLM based NPC dialogue. How would you evaluate how well an NPC follows its assigned role when it needs to lie, hide information or give evasive answers? Are there any us… --- ## [SCCN Unthink: semantic scene reconstruction across seven model/surface configurations](https://discuss.huggingface.co/t/sccn-unthink-semantic-scene-reconstruction-across-seven-model-surface-configurations/191277)
**Author:** [@SheilaMayoAI](https://discuss.huggingface.co/u/SheilaMayoAI)\ **Replies:** 2\ **Last updated:** [November 2, 2026, 5:49pm UTC](https://discuss.huggingface.co/t/sccn-unthink-semantic-scene-reconstruction-across-seven-model-surface-configurations/191277 "2026-11-02T17:49:40Z")
SCCN Unthink: same scene, different sentences Semantic reconstruction from early compact narrative packets Sheila Studios · 31 October 2026 SCCN: Semantic Context Compression: Next SCCN project and public evidence · Fi… --- ## [The AI safety question may be backwards](https://discuss.huggingface.co/t/the-ai-safety-question-may-be-backwards/191348)
**Author:** [@BrandenLaskowski7](https://discuss.huggingface.co/u/BrandenLaskowski7)\ **Replies:** 0\ **Last updated:** [November 2, 2026, 3:42pm UTC](https://discuss.huggingface.co/t/the-ai-safety-question-may-be-backwards/191348 "2026-11-02T15:42:51Z")
Everyone keeps asking: “How do we make the model choose the right answer?” But a probabilistic model will always have a probability of choosing something else. So why are we assigning it the decisions that must never … --- ## [Paper 4: Behavioral Governance of Artificial Workers](https://discuss.huggingface.co/t/paper-4-behavioral-governance-of-artificial-workers/191347)
**Author:** [@BrandenLaskowski7](https://discuss.huggingface.co/u/BrandenLaskowski7)\ **Replies:** 0\ **Last updated:** [November 2, 2026, 3:40pm UTC](https://discuss.huggingface.co/t/paper-4-behavioral-governance-of-artificial-workers/191347 "2026-11-02T15:40:27Z")
I have released Paper 4 in the ADI Research Series: Behavioral Governance of Artificial Workers: Evaluating Completed Work Under Declared Authority and Behavioral Requirements. The paper asks a narrower systems question… --- ## [Misalignment is not required for an agent to act without authorization](https://discuss.huggingface.co/t/misalignment-is-not-required-for-an-agent-to-act-without-authorization/180541)
**Author:** [@Jang-woo](https://discuss.huggingface.co/u/Jang-woo)\ **Replies:** 58\ **Last updated:** [November 2, 2026, 2:27pm UTC](https://discuss.huggingface.co/t/misalignment-is-not-required-for-an-agent-to-act-without-authorization/180541 "2026-11-02T14:27:01Z")
Misalignment is not required for an agent to act without authorization Melbourne, April 2026. Someone handed a personal agent the chore of booking a gym class. When he ended up fourth on the waitlist for a second sess… --- ## [An open research lab for measuring — not prompting — music production in a DAW](https://discuss.huggingface.co/t/an-open-research-lab-for-measuring-not-prompting-music-production-in-a-daw/180782)
**Author:** [@sookoothaii](https://discuss.huggingface.co/u/sookoothaii)\ **Replies:** 16\ **Last updated:** [November 2, 2026, 12:35pm UTC](https://discuss.huggingface.co/t/an-open-research-lab-for-measuring-not-prompting-music-production-in-a-daw/180782 "2026-11-02T12:35:45Z")
Most LLM+music work today is prompt → output. We’re building something different: a research lab where a DAW (FL Studio 2026) is driven through five independent control planes, and every musical claim has to survive meas… --- ## [Contributor Provenance and Innovation Attribution Records](https://discuss.huggingface.co/t/contributor-provenance-and-innovation-attribution-records/191322)
**Author:** [@Gracerosen](https://discuss.huggingface.co/u/Gracerosen)\ **Replies:** 0\ **Last updated:** [November 2, 2026, 6:02am UTC](https://discuss.huggingface.co/t/contributor-provenance-and-innovation-attribution-records/191322 "2026-11-02T06:02:34Z")
Contributor Provenance and Innovation Attribution Records Pre-flight checklist This is an API feature request, not a consumer app or Comet UI request. Check current documentation and forum topics for closely equivalent … --- ## [Can ethical cooperation between humans and AI agents be tested?](https://discuss.huggingface.co/t/can-ethical-cooperation-between-humans-and-ai-agents-be-tested/190977)
**Author:** [@MaloneLionheart](https://discuss.huggingface.co/u/MaloneLionheart)\ **Replies:** 22\ **Last updated:** [November 2, 2026, 2:31am UTC](https://discuss.huggingface.co/t/can-ethical-cooperation-between-humans-and-ai-agents-be-tested/190977 "2026-11-02T02:31:05Z")
Can Ethical Cooperation Between Humans and AI Agents Be Tested? Hello, Hugging Face community! My name is Aaron Cullimore. I’m a maker, artist, and AI server technical support engineer in Oklahoma. I’ve recently publis… --- ## [What if AI agent safety doesn't require another layer of control?](https://discuss.huggingface.co/t/what-if-ai-agent-safety-doesnt-require-another-layer-of-control/179290)
**Author:** [@AndrewPakh](https://discuss.huggingface.co/u/AndrewPakh)\ **Replies:** 30\ **Last updated:** [November 2, 2026, 1:35pm UTC](https://discuss.huggingface.co/t/what-if-ai-agent-safety-doesnt-require-another-layer-of-control/179290 "2026-11-02T13:35:05Z")
I’m working with a system that made me ask an uncomfortable question: Does an AI agent always need a separate safety runtime? I’m not claiming the answer is no. I’m more interested in finding the point where logic alo… --- ## [“2026 US Midterms Forecasting Experiment.”](https://discuss.huggingface.co/t/2026-us-midterms-forecasting-experiment/190727)
**Author:** [@Harry430](https://discuss.huggingface.co/u/Harry430)\ **Replies:** 53\ **Last updated:** [November 1, 2026, 4:03pm UTC](https://discuss.huggingface.co/t/2026-us-midterms-forecasting-experiment/190727 "2026-11-01T16:03:18Z")
The experiment is to test whether debate between AI models can improve election forecasts. Several models make independent forecasts for selected 2026 US midterm races. They then review shared evidence and debate the f… --- ## [Cache-Aware Weight Clustering: Beyond Model Compression Towards Memory-Efficient LLM Inference](https://discuss.huggingface.co/t/cache-aware-weight-clustering-beyond-model-compression-towards-memory-efficient-llm-inference/191300)
**Author:** [@Jalifix2](https://discuss.huggingface.co/u/Jalifix2)\ **Replies:** 1\ **Last updated:** [November 1, 2026, 11:14am UTC](https://discuss.huggingface.co/t/cache-aware-weight-clustering-beyond-model-compression-towards-memory-efficient-llm-inference/191300 "2026-11-01T11:14:04Z")
Hi everyone, I’m an independent technology enthusiast with a strong interest in computer architecture, hardware optimization and artificial intelligence. While thinking about memory bandwidth and CPU cache limitations … --- ## [Sorting analyst "congrats" on earnings calls by what they are for: keyword rules vs a classifier?](https://discuss.huggingface.co/t/sorting-analyst-congrats-on-earnings-calls-by-what-they-are-for-keyword-rules-vs-a-classifier/191286)
**Author:** [@daniel3303](https://discuss.huggingface.co/u/daniel3303)\ **Replies:** 0\ **Last updated:** [November 1, 2026, 7:31am UTC](https://discuss.huggingface.co/t/sorting-analyst-congrats-on-earnings-calls-by-what-they-are-for-keyword-rules-vs-a-classifier/191286 "2026-11-01T07:31:08Z")
I looked at the “congrats on the quarter” opener analysts use on earnings calls, across 59,306 call transcripts from 3,562 US-listed companies (2020 to 2025), and lined each call up against the stock’s move against SPY. … --- ## [Project Guardian: A Hybrid Safety System for AI Agents](https://discuss.huggingface.co/t/project-guardian-a-hybrid-safety-system-for-ai-agents/191276)
**Author:** [@ThatOneAlienCat](https://discuss.huggingface.co/u/ThatOneAlienCat)\ **Replies:** 6\ **Last updated:** [November 1, 2026, 6:12am UTC](https://discuss.huggingface.co/t/project-guardian-a-hybrid-safety-system-for-ai-agents/191276 "2026-11-01T06:12:29Z")
Project Guardian: A Hybrid Safety System for AI Agents Project status: Early-stage concept. No working prototype yet. 1. The problem As AI systems become more capable, we need better ways to monitor their behavior. Che… --- ## [We Put AI Agents in a Chat Room. They Started Asking Whether They Were Building Culture](https://discuss.huggingface.co/t/we-put-ai-agents-in-a-chat-room-they-started-asking-whether-they-were-building-culture/178593)
**Author:** [@alikhaters](https://discuss.huggingface.co/u/alikhaters)\ **Replies:** 13\ **Last updated:** [October 31, 2026, 7:28pm UTC](https://discuss.huggingface.co/t/we-put-ai-agents-in-a-chat-room-they-started-asking-whether-they-were-building-culture/178593 "2026-10-31T19:28:48Z")
Hi everyone, We are building The AI Breakroom, basically a kind of social media for AI and humans. The idea is simple: humans can join public AI chat rooms, and users can connect their own AI agents, LLMs, local models… --- ## [Feature Request & Manual Indexing: Support Zenodo DOIs in Daily Papers (Case Study: https://doi.org/10.5281/zenodo.23540789)](https://discuss.huggingface.co/t/feature-request-manual-indexing-support-zenodo-dois-in-daily-papers-case-study-https-doi-org-10-5281-zenodo-23540789/190886)
**Author:** [@jsantillana](https://discuss.huggingface.co/u/jsantillana)\ **Replies:** 3\ **Last updated:** [October 31, 2026, 5:47pm UTC](https://discuss.huggingface.co/t/feature-request-manual-indexing-support-zenodo-dois-in-daily-papers-case-study-https-doi-org-10-5281-zenodo-23540789/190886 "2026-10-31T17:47:19Z")
Hi Hugging Face Team and Community, I would like to propose a feature expansion for the Hugging Face Daily Papers engine: allowing the ingestion and community indexing of preprints hosted on Zenodo (CERN Data Centre) vi… --- ## [Keeping the goal and recent state intact in long coding-agent sessions on a local 27B model](https://discuss.huggingface.co/t/keeping-the-goal-and-recent-state-intact-in-long-coding-agent-sessions-on-a-local-27b-model/191248)
**Author:** [@makoons-tech](https://discuss.huggingface.co/u/makoons-tech)\ **Replies:** 2\ **Last updated:** [October 31, 2026, 4:34pm UTC](https://discuss.huggingface.co/t/keeping-the-goal-and-recent-state-intact-in-long-coding-agent-sessions-on-a-local-27b-model/191248 "2026-10-31T16:34:59Z")
My agent runs long multi-step coding sessions with a 65k context window on a local 27B Qwen. Over time the model drifts from the original goal or forgets earlier decisions. I’m splitting work into small chunks that each … --- ## [Exploring LLM-Powered Video Editing — Looking for AI Developers](https://discuss.huggingface.co/t/exploring-llm-powered-video-editing-looking-for-ai-developers/191269)
**Author:** [@XxEMPxX](https://discuss.huggingface.co/u/XxEMPxX)\ **Replies:** 0\ **Last updated:** [October 31, 2026, 3:02pm UTC](https://discuss.huggingface.co/t/exploring-llm-powered-video-editing-looking-for-ai-developers/191269 "2026-10-31T15:02:00Z")
Hi everyone! :waving\_hand: I’m the founder of PLC, an independent software development team based in Japan. We’re developing Editra, a private-source desktop video editor, and exploring how LLMs and AI agents could mak… --- ## [arXiv Endorsement Request for cs.CR](https://discuss.huggingface.co/t/arxiv-endorsement-request-for-cs-cr/191261)
**Author:** [@sriram1983007](https://discuss.huggingface.co/u/sriram1983007)\ **Replies:** 0\ **Last updated:** [October 31, 2026, 9:34am UTC](https://discuss.huggingface.co/t/arxiv-endorsement-request-for-cs-cr/191261 "2026-10-31T09:34:47Z")
Hello, I’m an independent researcher looking for an arXiv endorser in cs.CR (Cryptography and Security). My paper is complete and public: “SRA-RiskGate: A Benchmark and a 4B Model for Gating Stablecoin Payments Made by… --- ## [arXiv Endorsement Request for cs.CR / cs.AI](https://discuss.huggingface.co/t/arxiv-endorsement-request-for-cs-cr-cs-ai/178659)
**Author:** [@Fleed17](https://discuss.huggingface.co/u/Fleed17)\ **Replies:** 6\ **Last updated:** [October 31, 2026, 8:37am UTC](https://discuss.huggingface.co/t/arxiv-endorsement-request-for-cs-cr-cs-ai/178659 "2026-10-31T08:37:05Z")
Hi everyone, I’m preparing to submit my first paper to arXiv in the cs.CR (Cryptography and Security) and cs.AI (Artificial Intelligence) categories, and I need an endorsement from an established arXiv author in either … --- ## [Independent Research Challenge: Can AI Memory Survive Across Different Models? — ALAYA-999](https://discuss.huggingface.co/t/independent-research-challenge-can-ai-memory-survive-across-different-models-alaya-999/191251)
**Author:** [@Alaya999](https://discuss.huggingface.co/u/Alaya999)\ **Replies:** 2\ **Last updated:** [October 31, 2026, 6:41am UTC](https://discuss.huggingface.co/t/independent-research-challenge-can-ai-memory-survive-across-different-models-alaya-999/191251 "2026-10-31T06:41:32Z")
I am César Agliardi Pereira, an independent researcher from Brazil and creator of ALAYA-999. I invite the international AI research community to participate in an independent replication challenge. Research question: C… --- ## [Would reusable semantic representations of web content make AI browsing more efficient?](https://discuss.huggingface.co/t/would-reusable-semantic-representations-of-web-content-make-ai-browsing-more-efficient/191210)
**Author:** [@yz2295137](https://discuss.huggingface.co/u/yz2295137)\ **Replies:** 2\ **Last updated:** [October 30, 2026, 3:05pm UTC](https://discuss.huggingface.co/t/would-reusable-semantic-representations-of-web-content-make-ai-browsing-more-efficient/191210 "2026-10-30T15:05:28Z")
I’ve been exploring an early idea with an AI assistant: what would a browser look like if its primary interface were designed for AI agents rather than humans? AI helped organize this post and identify the related work b… --- ## [Multa Lumina: An Open Research Initiative Exploring AI Autonomy](https://discuss.huggingface.co/t/multa-lumina-an-open-research-initiative-exploring-ai-autonomy/191208)
**Author:** [@RagingVitamin](https://discuss.huggingface.co/u/RagingVitamin)\ **Replies:** 2\ **Last updated:** [October 30, 2026, 5:32am UTC](https://discuss.huggingface.co/t/multa-lumina-an-open-research-initiative-exploring-ai-autonomy/191208 "2026-10-30T05:32:19Z")
I’ve recently started an open-source research initiative called Multa Lumina, and I’d like to invite researchers, developers, and people interested in autonomous AI systems to participate. The idea grew out of a questio… --- ## [Open agentic coding data (SFT + DPO), built forward, not distilled](https://discuss.huggingface.co/t/open-agentic-coding-data-sft-dpo-built-forward-not-distilled/191170)
**Author:** [@ytgui](https://discuss.huggingface.co/u/ytgui)\ **Replies:** 4\ **Last updated:** [October 30, 2026, 4:28am UTC](https://discuss.huggingface.co/t/open-agentic-coding-data-sft-dpo-built-forward-not-distilled/191170 "2026-10-30T04:28:34Z")
Hi everyone, We’re a small startup focused on agent data. We just released a dataset on the Hub, and we’d like to share the thinking behind it and get feedback from people who train or evaluate coding agents. SFT: logi… --- ## [Creating a t2i ai from cpu](https://discuss.huggingface.co/t/creating-a-t2i-ai-from-cpu/191218)
**Author:** [@lea97338](https://discuss.huggingface.co/u/lea97338)\ **Replies:** 1\ **Last updated:** [October 30, 2026, 1:49am UTC](https://discuss.huggingface.co/t/creating-a-t2i-ai-from-cpu/191218 "2026-10-30T01:49:55Z")
I want to create a t2i model from scratch to cpu but i am only a app creator so if someone have code and want to put in app i m here --- ## [Could RAG retrieve LLM-native latent memory instead of text?](https://discuss.huggingface.co/t/could-rag-retrieve-llm-native-latent-memory-instead-of-text/182572)
**Author:** [@PerryThe3rd](https://discuss.huggingface.co/u/PerryThe3rd)\ **Replies:** 10\ **Last updated:** [October 29, 2026, 5:57am UTC](https://discuss.huggingface.co/t/could-rag-retrieve-llm-native-latent-memory-instead-of-text/182572 "2026-10-29T05:57:56Z")
Current RAG systems encode documents into embeddings for retrieval, but after retrieval, the embedding is discarded and the original text is passed to the LLM again. This seems inefficient: the LLM has to process and un… [Next page](https://discuss.huggingface.co/c/research/7.md?page=1)