Related papers: TVCACHE: A Stateful Tool-Value Cache for Post-Trai…

Prompt caching is critical for reducing latency and cost in LLM inference: OpenAI and Anthropic report up to 50-90% cost savings through prompt reuse. Despite its widespread success, little is known about what constitutes an optimal prompt…

The increasing adoption of large language models (LLMs) with extended context windows necessitates efficient Key-Value Cache (KVC) management to optimize inference performance. Inference workloads like Retrieval-Augmented Generation (RAG)…

Confidence in LLMs is a useful indicator of model uncertainty and answer reliability. Existing work mainly focused on single-turn scenarios, while research on confidence in complex multi-turn interactions is limited. In this paper, we…

Prompting Large Language Models (LLMs) performs impressively in zero- and few-shot settings. Hence, small and medium-sized enterprises (SMEs) that cannot afford the cost of creating large task-specific training datasets, but also the cost…

Large Language Models (LLMs) that can continually improve beyond their training budgets are able to solve increasingly difficult problems by adapting at test time, a property we refer to as extrapolation. However, standard reinforcement…

The temporal credit assignment problem is a central challenge in Reinforcement Learning (RL), concerned with attributing the appropriate influence to each actions in a trajectory for their ability to achieve a goal. However, when feedback…

Large Language Model (LLM) agents have shown strong results on multi-turn tool-use tasks, yet they operate in isolation during training, failing to leverage experiences accumulated across episodes. Existing experience-augmented methods…

Agentic AI will be an essential enabling technology for designing future mobile communication systems, which could provide flexible and customized services, automate complex network operations, and drive autonomous decision-making across…

Large Language Models (LLMs) excel across a variety of language tasks yet are constrained by limited input lengths and high computational costs. Existing approaches\textemdash such as relative positional encodings (e.g., RoPE, ALiBi) and…

Tool-calling agents are evaluated on tool selection, parameter accuracy, and scope recognition, yet LLM trajectory assessments remain inherently post-hoc. Disconnected from the active execution loop, such assessments identify errors that…

Large Language Model (LLM)-based agents are increasingly deployed for complex, tool-based tasks where long-term memory is critical to driving actions. Existing benchmarks, however, primarily test a angent's ability to passively retrieve…

We optimize hierarchies of Time-to-Live (TTL) caches under random network delays. A TTL cache assigns individual eviction timers to cached objects that are usually refreshed upon a hit where upon a miss the object requires a random time to…

Transformers are slow to train on videos due to extremely large numbers of input tokens, even though many video tokens are repeated over time. Existing methods to remove such uninformative tokens either have significant overhead, negating…

Large language model (LLM) agents with tool-calling capabilities are increasingly deployed in production systems, yet a fundamental reliability question remains under-explored: does the same agent behave the same way twice? We present a…

The wide deployment of Large Language Models (LLMs) has given rise to strong demands for optimizing their inference performance. Today's techniques serving this purpose primarily focus on reducing latency and improving throughput through…

Large language model (LLM) agents have exhibited strong problem-solving competence across domains like research and coding. Yet, it remains underexplored whether LLM agents can tackle compounding real-world problems that require a diverse…

Large Language Models (LLMs) are increasingly expected to operate over long contexts, yet standard softmax attention incurs a KV cache that grows linearly with sequence length, quickly becoming the bottleneck for long context inference. A…

Training large-scale image recognition models is computationally expensive. This raises the question of whether there might be simple ways to improve the test performance of an already trained model without having to re-train or fine-tune…

LLM decoding is bottlenecked for large batches and long contexts by loading the key-value (KV) cache from high-bandwidth memory, which inflates per-token latency, while the sequential nature of decoding limits parallelism. We analyze the…

Recent advances in long-text understanding have pushed the context length of large language models (LLMs) up to one million tokens. It boosts LLMs's accuracy and reasoning capacity but causes exorbitant computational costs and…