发布日期：2026-08-16
收录条目：20
1. Have a laugh at AI’s expense by roleplaying as a chatbot
- 来源：The Verge AI
- 发布时间：2026-08-15 20:45 UTC
- 链接：https://www.theverge.com/entertainment/980502/roleplay-as-an-ai-chatbot
摘要：Your AI Slop Bores Me is brilliant in its simplicity. There are two tabs: human and LARP as an AI. On one side you enter a request. On the other, you submit an answer. But the important thing is that there's a human on b
2. Fine-Tuning Tool-Calling LLMs: A Complete Guide Using XYZ-Aquila-SFT and Qwen3
- 来源：MarkTechPost
- 发布时间：2026-08-15 11:28 UTC
- 链接：https://www.marktechpost.com/2026/08/15/fine-tuning-tool-calling-llms-a-complete-guide-using-xyz-aquila-sft-and-qwen3/
摘要：Implement an end-to-end fine-tuning pipeline for tool-calling language models. This tutorial covers parsing trajectories, structured tool-call extraction, Qwen-compatible ChatML rendering, and efficient LoRA adaptation u
3. Position: Reasoning is a Learnable Rule-Based Process
- 来源：arXiv cs.AI
- 发布时间：2026-08-15 04:00 UTC
- 链接：https://arxiv.org/abs/2608.12325
摘要：arXiv:2608.12325v1 Announce Type: new Abstract: Autonomous reasoning is among the most scientifically and economically motivating topics in AI today. Historically the purview of symbolic AI, recent advances have mainly e
4. Diagnostic Foundation for Evaluating LLMs' Research Integrity as Co-Scientists
- 来源：arXiv cs.AI
- 发布时间：2026-08-15 04:00 UTC
- 链接：https://arxiv.org/abs/2608.12345
摘要：arXiv:2608.12345v1 Announce Type: new Abstract: Language models are increasingly deployed as co-scientists, yet their ability to uphold research integrity under institutional pressure remains unmeasured. We introduce Int
5. Position: The Alignment Community is Unintentionally Building a Censor's Toolkit
- 来源：arXiv cs.AI
- 发布时间：2026-08-15 04:00 UTC
- 链接：https://arxiv.org/abs/2608.12346
摘要：arXiv:2608.12346v1 Announce Type: new Abstract: This position paper argues that modern AI alignment methods - originally designed to prevent harmful output - are dual-use technologies that may easily be misused by malici
6. Agreement Is Not Alignment: Divergent Moral Grounds in Human and LLM Ethical Judgments
- 来源：arXiv cs.AI
- 发布时间：2026-08-15 04:00 UTC
- 链接：https://arxiv.org/abs/2608.12368
摘要：arXiv:2608.12368v1 Announce Type: new Abstract: Agreement with human judgments is a common proxy for evaluating the alignment of large language models (LLMs). Yet agreement in final labels does not show that human annota
7. Multi-Agent Scheduling with LLM-Assisted Contract Net Negotiation for Stream Processing in Mobile Edge Computing
- 来源：arXiv cs.AI
- 发布时间：2026-08-15 04:00 UTC
- 链接：https://arxiv.org/abs/2608.12371
摘要：arXiv:2608.12371v1 Announce Type: new Abstract: Stream-processing systems increasingly operate across heterogeneous mobile edge--cloud infrastructures, where workload volatility, resource contention, and stringent qualit
8. Position: We Need Practical AI Alignment Methods to Mirror Human Reasoning
- 来源：arXiv cs.AI
- 发布时间：2026-08-15 04:00 UTC
- 链接：https://arxiv.org/abs/2608.12372
摘要：arXiv:2608.12372v1 Announce Type: new Abstract: AI systems are increasingly employed as decision aids, decision delegates, or autonomous decision-makers. This position paper argues that in many settings, particularly hig
9. Don't Want Your LLM to Recommend Nuclear Strike? Try Asking It in Japanese
- 来源：arXiv cs.AI
- 发布时间：2026-08-15 04:00 UTC
- 链接：https://arxiv.org/abs/2608.12373
摘要：arXiv:2608.12373v1 Announce Type: new Abstract: Large language models are increasingly used in strategic and advisory contexts, yet their safety alignment is typically evaluated in English only. We test nine models from
10. Dual-Flow Transformers: Decoupling the Primary Prefill Path from Additional Decode Computation
- 来源：arXiv cs.AI
- 发布时间：2026-08-15 04:00 UTC
- 链接：https://arxiv.org/abs/2608.12385
摘要：arXiv:2608.12385v1 Announce Type: new Abstract: As large language models serve more requests, cumulative inference cost is becoming increasingly important relative to one-time training cost. The two inference phases stre
11. Learning to Adapt Cross-Domain Preferences via Meta-LoRA for LLM Personalization
- 来源：arXiv cs.AI
- 发布时间：2026-08-15 04:00 UTC
- 链接：https://arxiv.org/abs/2608.12389
摘要：arXiv:2608.12389v1 Announce Type: new Abstract: Cross-domain zero- or few-shot personalization aims to generate user-preferred responses in unseen conversational domains from only a handful of target-domain interactions.
12. Research Assistant: AstraZeneca's Agentic System for R&D
- 来源：arXiv cs.AI
- 发布时间：2026-08-15 04:00 UTC
- 链接：https://arxiv.org/abs/2608.12395
摘要：arXiv:2608.12395v1 Announce Type: new Abstract: We describe Research Assistant, an internal LLM-based system developed at AstraZeneca to help scientists and clinicians explore biomedical questions across a broad range of
13. Large Language Models Can Follow Instructions, But Not Many at Once: Phase Transitions in Compositional Constraint Satisfaction
- 来源：arXiv cs.AI
- 发布时间：2026-08-15 04:00 UTC
- 链接：https://arxiv.org/abs/2608.12426
摘要：arXiv:2608.12426v1 Announce Type: new Abstract: Large language models are increasingly deployed in settings that require simultaneous adherence to multiple explicit constraints - reasoning structure, safety boundaries, o
14. MindMemOS: A Portable and Self-Evolving Memory Operating Layer for AI Agents
- 来源：arXiv cs.AI
- 发布时间：2026-08-15 04:00 UTC
- 链接：https://arxiv.org/abs/2608.12428
摘要：arXiv:2608.12428v1 Announce Type: new Abstract: Memory is a core component of AI agents, enabling them to accumulate experience, maintain personalization, and adapt over long-term interactions. However, existing memory s
15. Governed Persistent Memory: Source-Bound State Semantics and Fail-Closed Release for Long-Horizon Agents
- 来源：arXiv cs.AI
- 发布时间：2026-08-15 04:00 UTC
- 链接：https://arxiv.org/abs/2608.12476
摘要：arXiv:2608.12476v1 Announce Type: new Abstract: Long-term agent memory is usually treated as select--store--retrieve, but retrieval does not decide whether contradictory, superseded, retracted, deleted, or stale records
16. $\varepsilon$-MemEvo: Adaptive Cross-Task Memory Transfer for LLM Program Evolution
- 来源：arXiv cs.AI
- 发布时间：2026-08-15 04:00 UTC
- 链接：https://arxiv.org/abs/2608.12522
摘要：arXiv:2608.12522v1 Announce Type: new Abstract: LLM-based program evolution systems such as FunSearch and AlphaEvolve have shown strong ability to discover novel algorithms, but typically optimize each task in isolation,
17. CAS: A Causal Attribution Score for Local and Global Explainable Artificial Intelligence
- 来源：arXiv cs.AI
- 发布时间：2026-08-15 04:00 UTC
- 链接：https://arxiv.org/abs/2608.12555
摘要：arXiv:2608.12555v1 Announce Type: new Abstract: Predictive explanation methods attribute a model output; they do not, by themselves, attribute an intervention effect on the real-world outcome. We introduce the Causal Att
18. Trie Automata for Constrained Decoding over Large Finite Sets
- 来源：arXiv cs.AI
- 发布时间：2026-08-15 04:00 UTC
- 链接：https://arxiv.org/abs/2608.12574
摘要：arXiv:2608.12574v1 Announce Type: new Abstract: Large language models increasingly need to generate structured outputs that conform to predefined schemas, with one common constraint being selection from a finite set of v
19. Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces
- 来源：arXiv cs.AI
- 发布时间：2026-08-15 04:00 UTC
- 链接：https://arxiv.org/abs/2608.12585
摘要：arXiv:2608.12585v1 Announce Type: new Abstract: Improving reasoning LLMs requires the ability to judge the quality of long reasoning traces for effective reasoning data curation, strong training signals during reinforcem
20. Auditable agentic AI for evidence-grounded thyroid ultrasound diagnosis and reporting
- 来源：arXiv cs.AI
- 发布时间：2026-08-15 04:00 UTC
- 链接：https://arxiv.org/abs/2608.12590
摘要：arXiv:2608.12590v1 Announce Type: new Abstract: Thyroid ultrasound diagnosis requires coordinated lesion localization, measurement, risk stratification and reporting, yet most AI systems address these tasks in isolation