发布日期:2026-11-01
收录条目:20
1. I built an AI Tamagotchi before Meta could
- 来源:The Verge AI
- 发布时间:2026-10-31 16:05 UTC
- 链接:https://www.theverge.com/gadgets/1013375/muse-charm-gadgets-preview-waveshare-esp32-claude-vibe-code
摘要:Mark Zuckerberg's Meta made AI look so stinking cute by giving it a squishy little face - and this holiday season, he wants to sell you a Muse Charm so you can carry your jolly AI helper around like a Tamagotchi. But I w
2. Meet Factory Droid 1.0: A Model-Independent Coding Agent Harness Built on Script Mode
- 来源:MarkTechPost
- 发布时间:2026-10-31 10:38 UTC
- 链接:https://www.marktechpost.com/2026/10/31/factory-droid-1-0-frontier-harness/
摘要:Factory released Droid 1.0, a model-independent coding agent harness that makes programmatic tool calling the default. On Factory’s own Terminal-Bench 4 runs, Droid scores 65.2% with Claude Opus 5.5 at $4.73 per passed t
3. Vercel Labs Open-Sources agent-desktop for Agent Computer Use
- 来源:MarkTechPost
- 发布时间:2026-10-31 10:10 UTC
- 链接:https://www.marktechpost.com/2026/10/31/vercel-labs-agent-desktop-computer-use/
摘要:Vercel Labs released agent-desktop, an Apache-2.0 Rust CLI that gives any AI agent computer use on macOS, Windows and Linux by reading OS accessibility trees and acting on stable refs instead of pixels. The post Vercel L
4. LRMoE: Demand-Side Load Re-Calibration for Efficient MoE Training on Memory-Constrained Nodes
- 来源:arXiv cs.AI
- 发布时间:2026-10-31 04:00 UTC
- 链接:https://arxiv.org/abs/2610.37720
摘要:arXiv:2610.37720v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) models offer scalable capacity for Web applications, but uneven routing creates computation and communication bottlenecks. Existing placemen
5. Amortized Localized Posterior Inference for Model Calibration with Application to an Ocean Turbulence Closure
- 来源:arXiv cs.AI
- 发布时间:2026-10-31 04:00 UTC
- 链接:https://arxiv.org/abs/2610.37731
摘要:arXiv:2610.37731v1 Announce Type: new Abstract: Model discrepancy may prevent a single calibration parameter from reproducing a physical response across the context domain. In addition, uncertainties in observations and
6. ThinkJev: One Thought, Every Budget for Calibrated Typed Decisions
- 来源:arXiv cs.AI
- 发布时间:2026-10-31 04:00 UTC
- 链接:https://arxiv.org/abs/2610.37732
摘要:arXiv:2610.37732v1 Announce Type: new Abstract: Many uses of language models end in a typed decision: a choice among a closed set of options, whose probabilities code can act on. Reading those probabilities from one forw
7. OpenFrontiers: A Collection of Open Research Problems and a Benchmark for Scientific Rediscovery
- 来源:arXiv cs.AI
- 发布时间:2026-10-31 04:00 UTC
- 链接:https://arxiv.org/abs/2610.37739
摘要:arXiv:2610.37739v1 Announce Type: new Abstract: Large language models (LLMs) have shown increasing promise in research-level problem solving, yet a comprehensive collection of such problems is still missing, and evaluati
8. WebAnything: From the Wild Web to Scalable Agent Environments
- 来源:arXiv cs.AI
- 发布时间:2026-10-31 04:00 UTC
- 链接:https://arxiv.org/abs/2610.37786
摘要:arXiv:2610.37786v1 Announce Type: new Abstract: Web agents require diverse, executable, and resettable website environments for reproducible training and evaluation. Human-assisted mirrors demand per-site engineering, wh
9. What Does an Ontology Catch? Curated, LLM-Generated and Data-Derived Ontologies as Checkers of LLM Agents over Knowledge Graphs
- 来源:arXiv cs.AI
- 发布时间:2026-10-31 04:00 UTC
- 链接:https://arxiv.org/abs/2610.37809
摘要:arXiv:2610.37809v1 Announce Type: new Abstract: LLM agents that answer questions over Web knowledge graphs are increasingly wrapped in checks derived from the graph's ontology, on the assumption that a formal schema make
10. Measuring Where Intent Gets Lost in Agentic Smart Contract Synthesis
- 来源:arXiv cs.AI
- 发布时间:2026-10-31 04:00 UTC
- 链接:https://arxiv.org/abs/2610.37830
摘要:arXiv:2610.37830v1 Announce Type: new Abstract: AI agents can now write software from a plain-English description, but code that runs is not the same as code that does what was asked. This gap matters most for smart cont
11. Detecting Covert Collusion between AI Agents through Partner-Outsider Positive Listening
- 来源:arXiv cs.AI
- 发布时间:2026-10-31 04:00 UTC
- 链接:https://arxiv.org/abs/2610.37849
摘要:arXiv:2610.37849v1 Announce Type: new Abstract: AI agents that share a secret convention can coordinate through messages that look innocent, so a monitor that reads only the messages can miss them. We propose a behaviour
12. Evaluating and improving AI agents for sequencing protocol understanding
- 来源:arXiv cs.AI
- 发布时间:2026-10-31 04:00 UTC
- 链接:https://arxiv.org/abs/2610.37851
摘要:arXiv:2610.37851v1 Announce Type: new Abstract: Existing scientific-agent benchmarks rarely evaluate whether agents can reconstruct the exact molecular structures and generation workflows specified by sequencing protocol
13. Seq@K: Evaluating Language Models Under Sequential Feedback
- 来源:arXiv cs.AI
- 发布时间:2026-10-31 04:00 UTC
- 链接:https://arxiv.org/abs/2610.37859
摘要:arXiv:2610.37859v1 Announce Type: new Abstract: Language-model agents differ fundamentally from prior intelligent systems in their ability to learn from natural language in context. This capability enables agents to iter
14. What Constitutes Food Similarity? Visual Representations and Retrieval in Indian Cuisine
- 来源:arXiv cs.AI
- 发布时间:2026-10-31 04:00 UTC
- 链接:https://arxiv.org/abs/2610.37867
摘要:arXiv:2610.37867v1 Announce Type: new Abstract: Food similarity underlies retrieval, recommendation, substitution, and other food computing tasks, yet food representations are typically evaluated by identity preservation
15. Verification Learning Theory: A Process Model of Checking and Retention in AI-Assisted Judgment
- 来源:arXiv cs.AI
- 发布时间:2026-10-31 04:00 UTC
- 链接:https://arxiv.org/abs/2610.37875
摘要:arXiv:2610.37875v1 Announce Type: new Abstract: Accurate AI assistance can improve immediate judgments while reducing opportunities to practise the operations needed for independent performance. Verification Learning The
16. The Anatomy of Socio-Demographics in Pluralistic Offensiveness Modeling: When and Where It Helps, and the Role of Reasoning
- 来源:arXiv cs.AI
- 发布时间:2026-10-31 04:00 UTC
- 链接:https://arxiv.org/abs/2610.37896
摘要:arXiv:2610.37896v1 Announce Type: new Abstract: Subjective judgments such as offensiveness often vary substantially across individuals, motivating pluralistic modeling approaches that incorporate annotators' socio-demogr
17. FilingLoop: Evaluating and Evolving LLM Agents for Corporate Disclosure Review and Revision
- 来源:arXiv cs.AI
- 发布时间:2026-10-31 04:00 UTC
- 链接:https://arxiv.org/abs/2610.37905
摘要:arXiv:2610.37905v1 Announce Type: new Abstract: Public disclosure repositories such as SEC EDGAR support informed investment through web access to corporate filings. Supporting their review with language model agents req
18. Beyond Low-Pass Dynamics: Frequency-Selective Spiking Reservoirs with Resonant Neurons
- 来源:arXiv cs.AI
- 发布时间:2026-10-31 04:00 UTC
- 链接:https://arxiv.org/abs/2610.37906
摘要:arXiv:2610.37906v1 Announce Type: new Abstract: Spiking reservoir computing combines the training efficiency of fixed recurrent reservoirs with the energy efficiency of event-driven inference, where computation is trigge
19. SciGame: Let Agents Play the Scientific Discovery Games in the Real and Counterfactual World
- 来源:arXiv cs.AI
- 发布时间:2026-10-31 04:00 UTC
- 链接:https://arxiv.org/abs/2610.37919
摘要:arXiv:2610.37919v1 Announce Type: new Abstract: Large language model agents are increasingly used for scientific discovery. However, existing benchmarks mix law inference with programming, score data fitting instead of p
20. VerifiedLab: Harnessing Knowns for Unknowns
- 来源:arXiv cs.AI
- 发布时间:2026-10-31 04:00 UTC
- 链接:https://arxiv.org/abs/2610.37923
摘要:arXiv:2610.37923v1 Announce Type: new Abstract: Across human history, knowledge has undergone several transitions, from orality to writing and then to digital archives. At each transition, humans established new conventi