Catalpa: GC for a Low-Variance Software Stack

• URL: http://arxiv.org/abs/2509.13429v1
• Date: Tue, 16 Sep 2025 18:07:21 GMT
• Title: Catalpa: GC for a Low-Variance Software Stack
• Abstract summary: In practice, good performance of an application is viewed as more of a binary function.<n>We present a novel garbage-collector design, the Catalpa collector, for the Bosque programming language and runtime.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The performance of an application/runtime is usually conceptualized as a continuous function where, the lower the amount of memory/time used on a given workload, then the better the compiler/runtime is. However, in practice, good performance of an application is viewed as more of a binary function - either the application responds in under, say 100 ms, and is fast enough for a user to barely notice, or it takes a noticeable amount of time, leaving the user waiting and potentially abandoning the task. Thus, performance really means how often the application is fast enough to be usable, leading industrial developers to focus on the 95th and 99th percentile tail-latencies as heavily, or moreso, than average response time. Our vision is to create a software stack that actively supports these needs via programming language and runtime system design. In this paper we present a novel garbage-collector design, the Catalpa collector, for the Bosque programming language and runtime. This allocator is designed to minimize latency and variability while maintaining high-throughput and incurring small memory overheads. To achieve these goals we leverage various features of the Bosque language, including immutability and reference-cycle freedom, to construct a collector that has bounded collection pauses, incurs fixed-constant memory overheads, and does not require any barriers or synchronization with application code.

Related papers

• Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents [72.3752981234916]
  Large Language Model (LLM) agents increasingly rely on external memory systems to accumulate experience across tasks.<n>We present Memory as a Controlled Process (MemCon), a framework that models memory operations as a Markov Decision Process.<n>MemCon consistently outperforms multiple memory baselines by up to 15.2 points in task success while reducing token consumption by 5-20%.
  arXiv  Detail & Related papers  (2026-07-15T08:32:40Z)
• Semantic-Aware Adaptive Visual Memory for Streaming Video Understanding [55.7992006853979]
  SAVEMem is a framework that brings semantic awareness into memory generation and lets the retrieval scope adapt per query.<n>We present SAVEMem, a training-free dual-stage framework that brings semantic awareness into memory generation and lets the retrieval scope adapt per query.
  arXiv  Detail & Related papers  (2026-05-08T15:40:40Z)
• ProgramBench: Can Language Models Rebuild Programs From Scratch? [59.40748183470308]
  ProgramBench measures the ability of software engineering agents to develop software holisitically.<n>End-to-end behavioral tests are generated via agent-driven fuzzing.<n>Models favor monolithic, single-file implementations that diverge sharply from human-written code.
  arXiv  Detail & Related papers  (2026-05-05T09:17:02Z)
• AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents [49.63422082885992]
  We propose AdaMem, an adaptive user-centric memory framework for long-horizon dialogue agents.<n>AdaMem organizes dialogue history into working, episodic, persona, and graph memories.<n>We evaluate AdaMem on the LoCoMo and PERSONAMEM benchmarks for long-horizon reasoning and user modeling.
  arXiv  Detail & Related papers  (2026-03-17T13:22:54Z)
• When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning [50.486479460454866]
  We propose GRU-Mem, which incorporates two text-controlled gates for more stable and efficient long-context reasoning.<n>GRU-Mem generally outperforms the vanilla MemAgent with up to 400% times inference speed acceleration.
  arXiv  Detail & Related papers  (2026-02-11T06:14:53Z)
• HyperOffload: Graph-Driven Hierarchical Memory Management for Large Language Models on SuperNode Architectures [20.525243835887558]
  SuperNode represents data movement using cache operators within the compiler.<n>We implement SuperNode within the production deep learning framework MindSpore.<n>We show that SuperNode reduces peak device memory usage by up to 26% for inference while maintaining end-to-end performance.
  arXiv  Detail & Related papers  (2026-01-31T14:29:13Z)
• LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning [15.189701702660821]
  LiCoMemory is an end-to-end agentic memory framework for real-time updating and retrieval.<n>CoGraph is a lightweight hierarchical graph that utilizes entities and relations as semantic indexing layers.<n>Experiments on long-term dialogue benchmarks, LoCoMo and LongMemEval, show that LiCoMemory not only outperforms established baselines in temporal reasoning, multi-session consistency, and retrieval efficiency, but also notably reduces update latency.
  arXiv  Detail & Related papers  (2025-11-03T11:02:40Z)
• Kodezi Chronos: A Debugging-First Language Model for Repository-Scale Code Understanding [0.0]
  Large Language Models (LLMs) have improved code generation and software automation, but remain limited by inference-time context.<n>We introduce Kodezi Chronos, a language model built specifically for debug.<n> Chronos combines Adaptive Graph-Guided Retrieval to navigates up to 10 million lines using multi-hop synthesis (92% precision, 85% recall), Persistent Debug Memory trained on 15M+ sessions, and a 7-layer architecture for iterative fix-test-refine loops.<n>On 5,000 real-world scenarios, Chronos achieves 67.3% fix accuracy, compared to 14.2% and 13.8% for Claude and GPT-
  arXiv  Detail & Related papers  (2025-07-14T09:08:21Z)
• FindingDory: A Benchmark to Evaluate Memory in Embodied Agents [49.89792845476579]
  We introduce a new benchmark for long-range embodied tasks in the Habitat simulator.<n>This benchmark evaluates memory-based capabilities across 60 tasks requiring sustained engagement and contextual awareness.
  arXiv  Detail & Related papers  (2025-06-18T17:06:28Z)
• An Effectively $Ω(c)$ Language and Runtime [0.0]
  Good performance of an application is conceptually more of a binary function. Our vision is to create a language and runtime that is designed to be $Omega(c)$ in its performance.
  arXiv  Detail & Related papers  (2024-09-30T16:57:45Z)
• Sparser is Faster and Less is More: Efficient Sparse Attention for Long-Range Transformers [58.5711048151424]
  We introduce SPARSEK Attention, a novel sparse attention mechanism designed to overcome computational and memory obstacles. Our approach integrates a scoring network and a differentiable top-k mask operator, SPARSEK, to select a constant number of KV pairs for each query. Experimental results reveal that SPARSEK Attention outperforms previous sparse attention methods.
  arXiv  Detail & Related papers  (2024-06-24T15:55:59Z)
• Compass: A Decentralized Scheduler for Latency-Sensitive ML Workflows [0.792324422300924]
  We consider ML query processing in distributed systems where GPU-enabled workers coordinate to execute complex queries. In such systems, coscheduling of GPU memory management and task placement represents a promising opportunity. We propose Compass, a novel framework that unifies these functions to reduce job latency while using resources efficiently.
  arXiv  Detail & Related papers  (2024-02-27T16:21:28Z)
• RelayAttention for Efficient Large Language Model Serving with Long System Prompts [59.50256661158862]
  This paper aims to improve the efficiency of LLM services that involve long system prompts. handling these system prompts requires heavily redundant memory accesses in existing causal attention algorithms. We propose RelayAttention, an attention algorithm that allows reading hidden states from DRAM exactly once for a batch of input tokens.
  arXiv  Detail & Related papers  (2024-02-22T18:58:28Z)
• Introducing Language Guidance in Prompt-based Continual Learning [95.03110230754423]
  We propose Language Guidance for Prompt-based Continual Learning (LGCL) as a plug-in for prompt-based methods. LGCL consistently improves the performance of prompt-based continual learning methods to set a new state-of-the art.
  arXiv  Detail & Related papers  (2023-08-30T08:03:49Z)
• LongCoder: A Long-Range Pre-trained Language Model for Code Completion [56.813974784131624]
  LongCoder employs a sliding window mechanism for self-attention and introduces two types of globally accessible tokens. Bridge tokens are inserted throughout the input sequence to aggregate local information and facilitate global interaction. memory tokens are included to highlight important statements that may be invoked later and need to be memorized.
  arXiv  Detail & Related papers  (2023-06-26T17:59:24Z)
• GRAPHSPY: Fused Program Semantic-Level Embedding via Graph Neural Networks for Dead Store Detection [4.82596017481926]
  We propose a learning-grained approach to identify unnecessary memory operations intelligently with low overhead. By applying several prevalent graph neural network models to extract program semantics, we present a novel, hybrid program embedding approach. Results show that our model achieves 90% of accuracy and incurs only around a half of time overhead of the state-of-art tool.
  arXiv  Detail & Related papers  (2020-11-18T19:17:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.