Related papers: A Self-Evolving Agentic Framework for Metasurface …
Reinforcement Learning from Verifiable Rewards (RLVR) is bottlenecked by data: existing synthesis pipelines rely on expert-written code or fixed templates, confining growth to instance-level perturbations. We shift the evolvable unit from…
Agentic workflows are composed of sequences of interdependent Large Language Model (LLM) calls, and they have become a dominant workload in modern AI systems. These workflows exhibit extensive redundancy from overlapping prompts and…
Autonomous coding agents, powered by large language models (LLMs), are increasingly being adopted in the software industry to automate complex engineering tasks. However, these agents are prone to a wide range of misbehaviors, such as…
Coding agents are increasingly used as general-purpose problem solvers, but their flexibility does not by itself confer the domain expertise needed for specialized tasks. Recent work addresses this through \textit{agent skills}: reusable…
Agentic workflows in large language model systems integrate retrieval, reasoning, and memory, but existing frameworks suffer from scalability and reproducibility limitations due to fragmented data orchestration, serialization overhead, and…
Agent Skill framework, now widely and officially supported by major players such as GitHub Copilot, LangChain, and OpenAI, performs especially well with proprietary models by improving context engineering, reducing hallucinations, and…
ML libraries, often written in architecture-specific programming languages (ASPLs) that target domain-specific architectures, are key to efficient ML systems. However, writing these high-performance ML libraries is challenging because it…
Large Language Models (LLMs) demonstrate impressive ability in handling reasoning tasks. However, unlike humans who can instinctively adapt their problem-solving strategies to the complexity of task, most LLM-based methods adopt a…
Large language models are transforming systems research by automating the discovery of performance-critical algorithms for computer systems. Despite plausible codes generated by LLMs, producing solutions that meet the stringent correctness…
Contemporary large language model (LLM)-based multi-agent systems exhibit systematic advantages in deep research tasks, which emphasize iterative, vertically structured information seeking. However, when confronted with wide search tasks…
Applying reinforcement learning (RL) to real-world tasks requires converting informal descriptions into a formal Markov decision process (MDP), implementing an executable environment, and training a policy agent. Automating this process is…
Autonomous web agents powered by large language models (LLMs) have shown promise in completing complex browser tasks, yet they still struggle with long-horizon workflows. A key bottleneck is the grounding gap in existing skill formulations:…
Large language models (LLMs) show promise for translating natural-language statutes into executable logic, but reliability in legally critical settings remains challenging due to ambiguity and hallucinations. We present an agentic approach…
Agent self-improvement, where the backbone Large Language Model (LLM) of the agent are trained on trajectories sampled autonomously based on their own policies, has emerged as a promising approach for enhancing performance. Recent…
Understanding the internal representations of large language models (LLMs) is a central challenge in interpretability research. Existing feature interpretability methods often rely on strong assumptions about the structure of…
Metasurfaces are ultra-thin optical elements composed of engineered sub-wavelength structures that enable precise control of light. Their inverse design - determining a geometry that yields a desired optical response - is challenging due to…
The remarkable capabilities of Large Language Model (LLM)-driven agents have enabled sophisticated systems to tackle complex, multi-step tasks, but their escalating costs threaten scalability and accessibility. This work presents the first…
Large Language Model (LLM)-empowered multi-agent systems extend the cognitive boundaries of individual agents through disciplined collaboration and interaction, while constructing these systems often requires labor-intensive manual designs.…
Large language model (LLM)-based agents are widely deployed in user-facing services but remain error-prone in new tasks, tend to repeat the same failure patterns, and show substantial run-to-run variability. Fixing failures via…
Inverse design of metasurfaces for specific electromagnetic responses requires generating geometries that satisfy stringent spectral constraints while maintaining manufacturability. Conventional design methodologies rely on iterative…