Related papers: Evaluating Memory Condensation Strategies for Codi…

Repository-level code intelligence tasks require large language models (LLMs) to process long, multi-file contexts. Such inputs introduce three challenges: crucial context can be obscured by noise, truncated due to limited windows, and…

LLM-based coding agents rely on \emph{skills}, pre-packaged instruction sets that extend agent capabilities, yet every token of skill content injected into the context window incurs both monetary cost and attention dilution. To understand…

Language models have proven successful across a wide range of software engineering tasks, but their significant computational costs often hinder their practical adoption. To address this challenge, researchers have begun applying various…

Large language models (LLMs) often rely on user-specific memories distilled from past interactions to enable personalized generation. A common practice is to concatenate these memories with the input prompt, but this approach quickly…

Memory-augmented LLM agents store and retrieve information from prior interactions, yet the relative importance of how memories are written versus how they are retrieved remains unclear. We introduce a diagnostic framework that analyzes how…

Large Language Model (LLM) agents struggle with long-horizon software engineering tasks due to "Context Bloat." As interaction history grows, computational costs explode, latency increases, and reasoning capabilities degrade due to…

Recent advancements in Large Language Model (LLM) agents have enabled complex multi-turn agentic tasks requiring extensive tool calling, where conversations can span dozens of API calls with increasingly large context windows. However,…

Large language models (LLMs) are increasingly deployed as agents in dynamic, real-world environments, where success requires both reasoning and effective tool use. A central challenge for agentic tasks is the growing context length, as…

Large Language Models (LLMs) have demonstrated exceptional code generation capabilities, yet their token-level mechanisms remain underexplored, particularly in compressed models. Through systematic analysis of programming language token…

As Large Language Models (LLMs) evolve into persistent scientific collaborators, context window saturation has emerged as a critical bottleneck. Scientific workflows involving iterative data analysis and hypothesis refinement rapidly…

Modern techniques in Content-based Recommendation (CBR) leverage item content information to provide personalized services to users, but suffer from resource-intensive training on large datasets. To address this issue, we explore the…

Transformer-based document cross-encoder rerankers are a central component of modern information retrieval systems. Despite their success, these models suffer from high computational costs due to processing long query-document sequences at…

This paper examines how different types of large language model (LLM) agents perform on scientific visualization (SciVis) tasks, where users generate visualization workflows from natural-language instructions. We compare three primary…

Large Language Models (LLMs) demonstrate exceptional reasoning abilities, enabling strong generalization across diverse tasks such as commonsense reasoning and instruction following. However, as LLMs scale, inference costs become…

LLM agents with persistent memory store information as flat factual records, providing little context for temporal reasoning, change tracking, or cross-session aggregation. Inspired by the drawing effect [3], we introduce dual-trace memory…

Memory systems often organize user-agent interactions as retrievable external memory and are crucial for long-running agents by overcoming the limited context windows of LLMs. However, existing memory systems invoke LLMs to process every…

The advancements of large language models (LLMs) have piqued growing interest in developing LLM-based language agents to automate scientific discovery end-to-end, which has sparked both excitement and skepticism about their true…

When LLM conversations grow beyond the context window, old content must be evicted -- but how does the model recover it when needed? We propose cooperative paging: evicted segments are replaced with minimal keyword bookmarks ([pN:keywords],…

Prompt engineering enables Large Language Models (LLMs) to perform a variety of tasks. However, lengthy prompts significantly increase computational complexity and economic costs. To address this issue, we study six prompt compression…

Despite long-standing efforts in accelerating scientific discovery with AI, building AI co-scientists remains challenging due to limited high-quality data for training and evaluation. To tackle this data scarcity issue, we present AutoSDT,…