Pai 的 AI 雷达

模型与评测

今天：Pretext（Agent 原型），Bi-FORK（arXiv:2610）。并行还有 From Video Clips、ttok 0.4、SpatialHarness。

日期: 2026/10/09
今日条目: 103
当前类目: 31

往期2026/10/09

全部103编码代理21 Agent与工具13 个人助理4 模型与评测31 创作成片8 开发与开源7 产品接入19

领域机器人具身2 硬件边缘1 生信医疗1 金融1 安全治理1 行业观察8 创业者1 独立开发1

RaReCache: Bridging the Gap in Cross-Model KV Cache Reuse via Rank disagreement-based Selective Recomputation

arXiv:2610.11358v1 Announce Type: new Abstract: Cross-model KV-cache reuse remains a key challenge in modern LLM serving. Coding agents and multi-model systems increasingly route a shared context across models: a user may switch models mid-session, or a cascade may escalate a dif

arxiv.org打开原文

#26

SWE-Journey: Towards More Realistic Evaluation of Coding Assistants through Long-Horizon, Multi-Turn Interaction

arXiv:2610.11559v1 Announce Type: cross Abstract: Coding assistants such as Claude Code and Codex have become a major application of LLM agents, yet existing benchmarks remain far from real-world use, particularly in task horizon and interaction length. Code assistants require co

arxiv.org打开原文

#27

StoreBench: A Live-Commerce Environment for Evaluating and Training Autonomous Operator Agents

arXiv:2610.10942v1 Announce Type: new Abstract: Reinforcement learning environments are now a primary lever for improving large language model (LLM) capabilities in post-training, yet most agentic benchmarks remain static: the world moves only when the agent acts, the reward is a

arxiv.org打开原文

#28

TestJack: Should you trust the results in coding benchmarks? Agentic Coding Benchmarks Auditing via Evaluator Evolution

arXiv:2610.10619v1 Announce Type: cross Abstract: Large language model (LLM) agents are rapidly reshaping software engineering, accompanied by an explosion of new code benchmarks. Yet nearly all existing benchmarks still rely on the same decades-old criterion: a solution is corre

arxiv.org打开原文

#29

The Harness as the Only Mutable Surface: Compliance-Bounded Self-Evolution of LLM Agents in Credit Pipelines, with a Measured Admission Gate

arXiv:2610.10629v1 Announce Type: new Abstract: Self-improving LLM agents can adapt a credit pipeline to a changed rule, but an agent that rewrites itself destroys the artefact a supervisor reviews: a named change, a recorded test, an approval. We argue that self-evolution is rev

arxiv.org打开原文

#30

Transect: Retaining Observability for Long-Horizon LLM Agent Evaluations

arXiv:2610.08364v2 Announce Type: replace Abstract: Frontier AI evaluations increasingly use open-ended, agentic, long-horizon tasks whose transcripts can span hundreds of pages of outputs and actions from complex multi-agent networks. The observability envelop-the range of what

arxiv.org打开原文

#31

Introducing LangSmith Fine-Tuning

LangChain introduces LangSmith Fine-Tuning and SmithTune, a CLI built for post-training models. Train specialized models without building data pipelines by hand.

langchain.com打开原文