相关论文: Skill-as-Pseudocode: Refactoring Skill Libraries t…

Software development is iterative, yet agentic coding benchmarks hide design issues through their single-shot setup. Recent iterative benchmarks attempt to remedy this but heavily constrain an agent's design decision space, making it…

This survey organizes the intricate literature on the design and optimization of emerging structures around post-trained LMs. We refer to this overarching structure as scaffolded LMs and focus on LMs that are integrated into multi-step…

Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool…

Large Language Models (LLMs) have been widely adopted in ranking systems such as information retrieval (IR) systems and recommender systems (RSs). To alleviate the latency of auto-regressive decoding, some studies explore the single (first)…

Large language model (LLM) agents such as OpenClaw rely on reusable skills to perform complex tasks, yet these skills remain largely static after deployment. As a result, similar workflows, tool usage patterns, and failure modes are…

Training LLMs for code-related tasks typically depends on high-quality code-documentation pairs, which are costly to curate and often scarce for niche programming languages. We introduce BatCoder, a self-supervised reinforcement learning…

Approximate message passing (AMP) is a family of iterative algorithms that generalize matrix power iteration. AMP algorithms are known to optimally solve many average-case optimization problems. In this paper, we show that a large class of…

Agent skills extend local AI agents, such as Claude Code or Open Claw, with additional functionality, and their popularity has led to the emergence of dedicated skill marketplaces, similar to app stores for mobile applications.…

Exploration in sparse-reward reinforcement learning is difficult due to the requirement of long, coordinated sequences of actions in order to achieve any reward. Moreover, in continuous action spaces there are an infinite number of possible…

Anthropic proposes the concept of skills for LLM agents to tackle multi-step professional tasks that simple tool invocations cannot address. A tool is a single, self-contained function, whereas a skill is a structured bundle of…

While Large Language Models (LLMs) have achieved remarkable success in formal learning tasks such as mathematics and code generation, they still struggle with the "practical wisdom" and generalizable intelligence, such as strategic…

Large language models (LLMs)-based code generation for robotic manipulation has recently shown promise by directly translating human instructions into executable code, but existing methods remain noisy, constrained by fixed primitives and…

Language-conditioned robotic skills make it possible to apply the high-level reasoning of Large Language Models (LLMs) to low-level robotic control. A remaining challenge is to acquire a diverse set of fundamental skills. Existing…

Large language model (LLM) agents increasingly rely on skills to package reusable capabilities through instructions, tools, and resources. High-quality skills embed expert knowledge, curated workflows, and execution constraints into agents,…

Rapid LLM advancements heighten fake news risks by enabling the automatic generation of increasingly sophisticated misinformation. Previous detection methods, including fine-tuned small models or LLM-based detectors, often struggle with its…

Text classification is a fundamental task in natural language processing (NLP), and large language models (LLMs) have demonstrated their capability to perform this task across various domains. However, the performance of LLMs heavily…

Scripting interfaces enable users to automate tasks and customize software workflows, but creating scripts traditionally requires programming expertise and familiarity with specific APIs, posing barriers for many users. While Large Language…

Natural and idiomatic expressions are essential for fluent, everyday communication, yet many second-language learners struggle to acquire and spontaneously use casual slang despite strong formal proficiency. To address this gap, we designed…

Program synthesis from natural language (NL) is practical for humans and, once technically feasible, would significantly facilitate software development and revolutionize end-user programming. We present SAPS, an end-to-end neural network…

Recent advances in Large Language Model Multi-Agent Systems enable scalable orchestration and retrieval of specialized, parallelized subagents, each equipped with hundreds or thousands of Model Context Protocol (MCP) servers and tools.…