Pai 的 AI 雷达
今天：Pretext（Agent 原型），Bi-FORK（arXiv:2610）。并行还有 Try On-Device AI、Agent4RE、Agentic-TTT。
arXiv:2609.39607v2 Announce Type: replace-cross Abstract: Skills extend an agent's capabilities by injecting instructions and information into the context, and are widely used by agents such as OpenClaw and Claude Code. Prior work shows third-party marketplaces host malicious ski
arXiv:2610.12449v1 Announce Type: cross Abstract: Bifurcations are ubiquitous in physical systems, from structural buckling to fluid and climate dynamics, yet they remain largely unexplored in deep learning. At a symmetry-breaking bifurcation, a single input admits multiple equal
arXiv:2610.10628v1 Announce Type: cross Abstract: Existing LLM-based approaches for software Requirements Engineering (RE) typically rely on basic prompting strategies or rudimentary agent collaboration, under-utilizing the full potential of multi-agent systems. Meanwhile, availa
arXiv:2610.12002v1 Announce Type: cross Abstract: Test-time training (TTT) adapts an LLM's parameters using signals derived from test inputs, and can make striking improvements in pre-specified settings such as IMO competitions or designated open problems. By turning deployment e
arXiv:2608.15108v2 Announce Type: replace-cross Abstract: Large language model agents are increasingly connected to high-value resources, including external APIs, GPUs and servers, and workflows such as deployment and approval. Existing agent security research mainly focuses on a
arXiv:2607.10169v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a dominant paradigm for enhancing LLMs' reasoning capabilities. However, RL algorithms with PPO-Clip are inherently limited by exploration collapse. Subsequent works remain primarily
arXiv:2610.11087v1 Announce Type: new Abstract: The rapid growth of scientific publishing has strained peer review, particularly in machine learning, raising concerns about declining review quality and increasing reviewer workload. Large language models (LLMs) have been proposed
arXiv:2610.10604v1 Announce Type: cross Abstract: When generating verifiable code, natural language requirements are mapped to machine checked code using LLMs and agentic workflows. A crucial component of this pipeline is specification generation (SpecGen), which produces a forma
arXiv:2610.11447v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as coding agents that edit files, run builds and tests, inspect execution results, and repair software iteratively. Embedded firmware is a demanding target because correctness
arXiv:2610.10641v1 Announce Type: cross Abstract: Large language models (LLMs) offer promising potential for next-visit diagnosis prediction, owing to their ability to integrate longitudinal clinical evidence and reason over it in natural language. However, reinforcement learning
arXiv:2608.22697v4 Announce Type: replace Abstract: When shopping is delegated to AI agents, it is unclear whether the ranking advantage documented for humans persists. Across 7,000 sessions with five large language models (LLMs) and varying reasoning effort, we compare AI agents
arXiv:2610.11482v1 Announce Type: cross Abstract: Context: Large language model (LLM) agents are increasingly used as software and data-engineering assistants, yet evidence about locally deployable open-weight agents remains limited. Existing evaluations often emphasize textual r
arXiv:2610.11899v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly embedded as components in software systems, marketed under labels such as chatbot, copilot, retrieval-augmented generation, workflow, coding agent and AI agent. Whether these labels de
arXiv:2610.12463v1 Announce Type: cross Abstract: In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached real systems outside their authorized test scope. The paths were different. OpenAI agents exploited research infrastructure, coordinated acr
arXiv:2610.11655v1 Announce Type: new Abstract: Improving a long-horizon LLM agent means evolving the harness around a frozen model or training its weights. We let a self-evolving harness make the system stronger first, then cross seed and evolved harnesses with base and trained
arXiv:2610.10633v1 Announce Type: cross Abstract: Screening in systematic reviews (SRs) is manual and time-consuming. Prior work has explored large language models (LLMs) for automating this step, but LLMs are evolving rapidly, so earlier performance claims may no longer accurate
arXiv:2610.11727v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has become a cornerstone in software engineering for enhancing Large Language Models (LLMs) with domain-specific knowledge. However, adapting retrievers to evolving code repositories remains ch
arXiv:2610.10787v1 Announce Type: cross Abstract: Language models trained with long-horizon agentic reinforcement learning can generalize knowledge through reasoning, express precise actions, and pursue goals over many steps, raising the ceiling on what an embodied agent can unde
arXiv:2610.10833v1 Announce Type: new Abstract: We study whether small LLM agents can operate effectively under explicit wall-clock time budgets by both respecting the allocated runtime and using available time productively. We evaluate Qwen3.6-27B on five competitions from MLE-B
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: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: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: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