资讯时间轴
1562 条 · 11 个来源正文已在本站存档，原文失效也不会变成空页；已剔除失效外链与不合规内容。
Beyond tree cover: mapping the world’s forest types
A global map categorizing every 10-meter patch of land on Earth into distinct forest types.
来源：Google DeepMind · 本地全文 站内详情DataPraxis: Scaling Analytics Tasks via Verified Workspace Evolution
General-purpose agents are increasingly expected to perform professional analytics work, which requires sustained reasoning, iterative investigation, and reliab…
来源：arXiv cs.AI · 本地全文 站内详情SPEM: Structure-Aware Procedural Memory for Efficient Skill Use in LLM Agents
LLM-based agents increasingly rely on reusable skills. However, scaling skill libraries makes efficient and accurate skill use difficult. Full skill loading inc…
来源：arXiv cs.AI · 本地全文 站内详情Does Multi-Agent Collaboration Reduce Hallucination in Clinical Tasks?
Multi-agent LLM systems improve performance on clinical tasks, and that improvement is often read as evidence of a more trustworthy system. However, the two are…
来源：arXiv cs.AI · 本地全文 站内详情Teaching AI Agent to Play Poker Strategically Through Preference Optimization
A poker agent can make a legal move and still make a strategically poor one. We ask whether compact AI agents can exhibit strategic behavior under hidden inform…
来源：arXiv cs.AI · 本地全文 站内详情Omni-Woodpecker: Hallucination Correction via Evidence-Prior Rebalancing for Omni LLMs
Recent Omni LLMs (OLLMs) have demonstrated remarkable capabilities in joint audio-visual reasoning, yet cross-modal hallucinations remain a major challenge. Exi…
来源：arXiv cs.AI · 本地全文 站内详情PROVISO: Provenance-Informed Action Selection for Secure LLM Agents
LLM agents act on the external world through tools and third-party skills, so a single executed action can cause irreversible harm. Existing defenses judge a pr…
来源：arXiv cs.AI · 本地全文 站内详情PORA: Learning When More Reasoning Pays Off for LLM Agents
LLM agents perform tasks over multiple steps and revise their actions based on feedback. As the total reasoning budget is often limited and must support future …
来源：arXiv cs.AI · 本地全文 站内详情MoSAIK: Motion Search with Artificial Intelligence in K-space
Object: Motion artefacts remain a major limitation of routine two-dimensional T2-weighted turbo spin-echo (TSE) brain MRI, reducing diagnostic confidence and of…
来源：arXiv cs.AI · 本地全文 站内详情Sparse RL Relaxation for LLM Reasoning
Recent work has explored continuous representations in place of discrete tokens during Chain-of-Thought (CoT) reasoning, often referred to as soft CoT. This is …
来源：arXiv cs.AI · 本地全文 站内详情Magnolia: A Persistent-Memory Agent Framework for Computational Chemistry
Chemistry has recently entered a high-data regime as molecular databases from high-throughput platforms or computational studies have become available. Increasi…
来源：arXiv cs.AI · 本地全文 站内详情Unsupervised Tool Evolution for Coding Agents in Data-Lake Analytics
Coding agents can answer analytical questions over a data lake by discovering, cleaning, and joining the relevant data. However, they discard this work after ea…
来源：arXiv cs.AI · 本地全文 站内详情When PTQ Calibration Helps or Hurts: Dose-Driven Collapse and Validation-Gated Abstention in Quantized Text Embedders
Learned post-training quantization (PTQ) calibration fits quantizer parameters on a small calibration set, and for a text embedder the natural supervision is re…
来源：arXiv cs.AI · 本地全文 站内详情KPHarness: Co-Evolving Knowledge and Probing for Long-Horizon Gaming Harnesses
A failed gaming trajectory reveals that an agent needs intervention, but not necessarily how its execution harness should change. Effective harness adaptation t…
来源：arXiv cs.AI · 本地全文 站内详情Ask to Distill: Learning to Synthesize Data for On-Policy Distillation
On-policy distillation (OPD) can succeed with surprisingly few training questions, motivating a view of questions as carriers of distributional knowledge transf…
来源：arXiv cs.AI · 本地全文 站内详情Automated Multi-Agent Organization Design: From Architecture Search to Organizational Learning
Agentic system design is increasingly shifting from hand-crafted prompts and workflows toward automated search over agentic programs and interaction structures,…
来源：arXiv cs.AI · 本地全文 站内详情Accelerating the search for antimicrobial peptides with Google Antigravity
Accelerating the search for novel antimicrobial peptides using Google Antigravity for Science.
来源：Google DeepMind · 本地全文 站内详情