paper🔥 23
Procedural Graphs: Self-Evolving Execution Structures for LLM AgentsLarge language models are increasingly deployed as agents that plan over long horizons and act through external tools.
雷达日报 · 2026-09-10
第 1 期 · 当日 65 条信号今日精选 4 / 65 条信号
paper🔥 4
DianShi-RxnDB: A Large-Scale, Fine-Grained Organic Reaction Data Platform Built via a Fully Automated Pipeline for Researchers and AI AgentsHigh-quality structured organic reaction data are essential for developing artificial intelligence for chemistry (AI4Ch…
paper🔥 4
EVOHARNESSBENCH: Can Your Agents Keep Pace with an Evolving Harness?Modern LLM-based agents operate through a harness of tools, reusable skills, and specialist agents that shapes what the…
paper🔥 11
Scores Alone Do Not Prove Discovery: The Discovery Certification Protocol for Auditing AI Research AgentsAI research agents combine prior knowledge, public sources, and experimental feedback to produce useful results.
速览 其余 61 条，按主题分组
SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions🔥15Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions🔥15Puppeteer: Object-Grounded Posture-Aware Co-Speech Gesture Generation🔥1StudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability?🔥12Graph Machine: Towards Better Pretraining via Edges🔥2MasterControl Seventeen Every Time🔥1
展开全部 61 条 →HF 热度榜 Top 5
1.AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing🔥1832.Omni Interaction Agent Technical Report🔥1223.Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation🔥844.OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining🔥555.GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation🔥49
雷达备注
- ✓ 数据源全部正常
- 完整日报原文见 存档页