Plans & Pricing

AI 周报，深度分析行业趋势：Plans & Pricing…

📎 The Batch

SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue

Long-term conversational memory in multi-party settings requires more than retrieving relevant content from long-term conversations: it must distinguish who said what, whom each statement concerns, how individuals perceive one another, what information is shared by the group, and how states change o

📅 09-22📎 arXiv AI Papers

CliffCompaction: Cost-Efficient Compaction for Long-Horizon Coding Agents

Agents often work on complex problems that require millions of tokens of context, which necessitates compacting across sessions due to limited context windows. We develop CliffCompaction, an autocompaction technique that reduces cost by up to 50% under a bounded context while maintaining or improvin

📅 09-22📎 arXiv AI Papers

SWE-Serve: Benchmarking Agentic Engineering For Production Inference Serving

We introduce SWE-Serve, a benchmark for evaluating agents on production inference engineering tasks. Implementing an inference feature can require coordinating multiple changes across the serving stack, including model support, runtime execution, and public APIs. Existing benchmarks provide limited

📅 09-22📎 arXiv AI Papers

A2M: Trace-Optimized Agent Hijacking in the MCP Ecosystem

本文提出A2M，一种面向MCP生态的轨迹优化

📅 09-22📎 arXiv AI Papers

Grow the Harness, Not the Context: From Strategy-Free Scaffolds to Reusable Specialist Agents

Large language model (LLM) agents often handle streams of related tasks, yet standard harnesses repeatedly ask the model to reconstruct the same control decisions inside each task’s context. We study whether task feedback can instead turn recurring control into reusable executable code, while reserv

📅 09-22📎 arXiv AI Papers

Type-Safe Is Not Error-Free: A Constrained Decision Head Follows the Option Name, Not the Rubric Bound to It

Typed decision models are built for settings where model outputs are consumed directly by software. Instead of generating free-form text, they return a decision over a predefined set of options. By construction, every output conforms to the required schema. Yet this guarantee does not tell us whethe

📅 09-22📎 arXiv AI Papers

FleXray: Universal Clinical X-ray Segmentation

X-ray is medicine’s most widely used imaging modality, yet remains among its least quantitative. Unlike volumetric modalities like CT or MRI, X-ray collapses 3D anatomy into a 2D projection, causing structures to overlap and anatomical boundaries to be ambiguous, even to experts. As a result, labeli

📅 09-22📎 arXiv AI Papers

Metrics Failure in LLM-Based Code Vulnerability Repair: An Empirical Study and a Change-Aware Screen

Large language models (LLMs) are increasingly applied to the automated repair of C/C++ security vulnerabilities, and compile rate is a commonly reported proxy for progress: whether the generated patch compiles. We argue that compile rate is a scientifically unreliable metric for single-function vuln

📅 09-22📎 arXiv AI Papers

Does AI Save Time on Product Design? A Randomized Controlled Experiment of AI Prompt-to-Design Workflows

AI tools for digital product design now offer prompt-to-design capabilities, allowing designers and their non-designer colleagues to create prototypes through conversational workflows with large language models (LLMs). While these tools promise time savings, experimental evidence in product design r

📅 09-22📎 arXiv AI Papers

The Sirens’ Song: When Proximal Background Context Overshadows Distant Evidence

本文揭示近端背景语境会像塞壬之歌般压过远端关键证据，导致模型在长上下文推理中忽视真正相关信息。研究分析该位置偏差的成因与影响，并提出评估或缓解策略，为检索增强生成、长文档问答等系统设计提供警示。

📅 09-22📎 arXiv AI Papers

Amazon Blocks Muse, Amazon’s Moat, Aggregator v Aggregator

Amazon 封禁 Muse，折射其护城河的本质：当 AI 代理试图以聚合者身份切入电商入口，Amazon 以控制权强势回应。文章剖析 Amazon 与新一代聚合者的正面冲突，指出双方终将围绕用户关系与流量入口展开争夺，并重新审视平台护城河的边界。

📎 Stratechery