Related papers: SemanticALLI: Caching Reasoning, Not Just Response…
Large Language Models (LLMs) deliver powerful reasoning and generation capabilities but incur substantial run-time costs when operating in agentic workflows that chain together lengthy prompts and process rich data streams. We introduce…
An agent skill is a configuration package that equips an LLM-driven agent with a concrete capability, such as reading email, executing shell commands, or signing blockchain transactions. Each skill is a hybrid artifact-a structured half…
This report investigates enhancing semantic caching effectiveness by employing specialized, fine-tuned embedding models. Semantic caching relies on embedding similarity rather than exact key matching, presenting unique challenges in…
We study mathematical discovery through the lens of neurosymbolic reasoning, where an AI agent powered by a large language model (LLM), coupled with symbolic computation tools, and human strategic direction, jointly produced a new result in…
Large language models show promise as autonomous decision-making agents, yet their deployment in high-stakes domains remains fraught with risk. Without architectural safeguards, LLM agents exhibit catastrophic brittleness: identical…
We study structured abstraction-based reasoning for the Abstraction and Reasoning Corpus (ARC) and compare its generalization to test-time approaches. Purely neural architectures lack reliable combinatorial generalization, while strictly…
Natural Language Inference (NLI) models frequently rely on spurious correlations rather than semantic reasoning. Existing mitigation strategies often incur high annotation costs or trigger catastrophic forgetting during fine-tuning. We…
Agentic AI denotes an architectural transition from stateless, prompt-driven generative models toward goal-directed systems capable of autonomous perception, planning, action, and adaptation through iterative control loops. This paper…
Artificial intelligence has accelerated materials discovery through high-throughput prediction and generation, yet the decision problem remains a formidable bottleneck. While current AI systems readily propose millions of candidates,…
Agentic AI require persistent memory to store user-specific histories beyond the limited context window of LLMs. Existing memory systems use dense vector databases or knowledge-graph traversal (or hybrid), incurring high retrieval latency…
Agents, language model-based systems capable of reasoning, planning, and acting are widely adopted in real-world tasks, yet how their performance changes as these systems scale across key dimensions remains underexplored. We introduce…
What does it mean to plan? Current agentic systems, whether scaffolded workflows or end-to-end policies, rely on reactive decision-making: selecting the next action via a fixed procedure with at most undifferentiated adaptive computation…
Current agentic memory systems (vector stores, retrieval-augmented generation, scratchpads, and context-window management) do not implement memory: they implement lookup. We argue that treating lookup as memory is a category error with…
While defenses for structured PII are mature, Large Language Models (LLMs) pose a new threat: Semantic Sensitive Information (SemSI), where models infer sensitive identity attributes, generate reputation-harmful content, or hallucinate…
Large language model (LLM)-based AI agents are increasingly deployed in manufacturing environments for analytics, quality management, and decision support. These agents demonstrate statistical fluency with domain terminology but lack…
Drug discovery frequently loses momentum when data, expertise, and tools are scattered, slowing design cycles. To shorten this loop we built a hierarchical, tool using agent framework that automates molecular optimisation. A Principal…
Retrieval-Augmented Generation (RAG) mitigates key limitations of Large Language Models (LLMs)-such as factual errors, outdated knowledge, and hallucinations-by dynamically retrieving external information. Recent work extends this paradigm…
Topology optimization can generate efficient structures, but designers often must manually translate qualitative intent, such as desired visual style, product experience, or manufacturability into solver settings that are not directly tied…
This paper introduces CAAI, a novel cognitive architecture for artificial intelligence in cyber-physical production systems. The goal of the architecture is to reduce the implementation effort for the usage of artificial intelligence…
We present an agentic framework, Thinker, which achieves state of art performance in challenging reasoning tasks for realistic customer service scenarios that involve complex business logic and human interactions via long horizons. On the…