Related papers: EvoSkill: Automated Skill Discovery for Multi-Agen…

Semantic code search, retrieving code that matches a given natural language query, is an important task to improve productivity in software engineering. Existing code search datasets face limitations: they rely on human annotators who…

Unlike traditional automation tools or static LLM-based systems, agents combine decision-making and tool utilization to accomplish complex tasks, showing great potential in software engineering. However, existing studies largely focus on…

Taking inspiration from developmental learning, we present a novel reinforcement learning architecture which hierarchically learns and represents self-generated skills in an end-to-end way. With this architecture, an agent focuses only on…

Speculative decoding accelerates Large Language Model inference via a draft-then-verify paradigm, yet the output projection layer becomes a bottleneck as vocabulary sizes scale. While existing static pruning methods effectively reduce this…

We introduce DeepSearchQA, a 900-prompt benchmark for evaluating agents on difficult multi-step information-seeking tasks across 17 different fields. Unlike traditional benchmarks that target single answer retrieval or broad-spectrum…

Automating operations research (OR) with large language models (LLMs) remains limited by hand-crafted reasoning--execution workflows. Complex OR tasks require adaptive coordination among problem interpretation, mathematical formulation,…

Equipping large language models with explicit skills has emerged as a promising paradigm for enabling autonomous agents to solve complex tasks. Agent skills can be inherently divided into general skills for broad cognitive transfer and…

Software Vulnerability (SV) assessment is a crucial process of determining different aspects of SVs (e.g., attack vectors and scope) for developers to effectively prioritize efforts in vulnerability mitigation. It presents a challenging and…

Data science tasks involving tabular data present complex challenges that require sophisticated problem-solving approaches. We propose AutoKaggle, a powerful and user-centric framework that assists data scientists in completing daily data…

Improving vision-language models (VLMs) in the post-training stage typically relies on supervised fine-tuning or reinforcement learning, methods that necessitate costly, human-annotated data. While self-supervised techniques have proven…

Large language model (LLM)-based multi-agent systems have shown strong potential on complex tasks through agent specialization, tool use, and collaborative reasoning. However, most automated multi-agent system design methods still follow a…

Agent harness evolution improves frozen language-model agents by modifying the executable structures around them. We study this paradigm as a form of sample-efficient fast adaptation: instead of updating model weights, an agent can acquire…

Automatic multi-agent systems aim to instantiate agent workflows without relying on manually designed or fixed orchestration. However, existing automatic MAS approaches remain only partially adaptive: they either perform training-free…

Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution. However, memory is also essential for agents, as it enables them to store, update, and retrieve information over time. This ability…

The vision of a broadly capable and goal-directed agent, such as an Internet-browsing agent in the digital world and a household humanoid in the physical world, has rapidly advanced, thanks to the generalization capability of foundation…

Recently, skills have been widely adopted in large language model (LLM)-based agent systems across various domains. In existing frameworks, skills are typically injected into the agent reasoning loop as contextual guidance once matched to a…

Multi-agent systems (MAS) built on multimodal large language models exhibit strong collaboration and performance. However, their growing openness and interaction complexity pose serious risks, notably jailbreak and adversarial attacks.…

Unsupervised skill discovery aims to learn diverse and distinguishable behaviors in open-ended reinforcement learning. For existing methods, they focus on improving diversity through pure exploration, mutual information optimization, and…

Large Language Models (LLMs) have shown promise for automated vulnerability repair (AVR), but they still face several limitations, including the lack of intra-vulnerability experience accumulation and the lack of cross-vulnerability…

Large language model (LLM) agents are increasingly used for complex tasks, yet deployed agents often remain static, failing to adapt as user needs evolve. This creates a tension between the need for continuous service and the necessity of…