arXiv Machine Learning
Jun 2
Multi-Agent Computer Use
arXiv:2606. 01533v1 Announce Type: cross Abstract: Computer use agents (CUAs) today are primarily deployed as single serial agents.
Experience Graphs: The Data Foundation for Self-Improving Agents
arXiv:2606. 29823v1 Announce Type: cross Abstract: The database community has repeatedly advanced the state of the art by recognizing that new workloads demand new system architectures.
Related stories
arXiv AI
Sep 23
Graph Memory for LLM Agents: At What Cost? A Comparative Evaluation of Query, Ingest, and Update Performance Across Graph Database Engines
The paper evaluates seven graph database engines, including Corvic AI, on a synthetic biomedical property graph with 1.02 million nodes and 5.34 million rows. It benchmarks query latency, bulk‑ingest throughput, point‑update latency, and correctness across a twenty‑query workload that covers neighborhood lookups, bounded paths, set intersections, anti‑joins, aggregation, ranking, temporal filters, full scans, and relational joins. The study finds that no single engine is universally fastest; performance depends on query shape, and the largest cost difference arises from bulk‑ingest throughput, which varies by three orders of magnitude and dominates total cost for workloads with fewer than about 10⁵ queries per data refresh.
Hugging Face Trending Papers
Sep 3
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
Terminal-Universe is a framework that converts large collections of terminal-based agent trajectories into reusable, executable environments. By replaying recorded file operations and filling missing files with a completion agent, it reconstructs the original workspace and generates new tasks, scaling them in breadth (cross-workspace queries) and depth (multi-round interactions). The resulting 37.3k task-sufficient environments enable significant performance gains when fine‑tuning language models on terminal‑centric benchmarks.
arXiv AI
Sep 4
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
Terminal-Universe is a framework that transforms large collections of terminal‑based agent trajectories into reusable, executable environments. By replaying recorded file operations and completing missing files, it reconstructs the original workspace and task, then synthesizes new tasks and multi‑round interactions. The resulting 37.3k task‑sufficient environments enable significant performance gains when fine‑tuning language models on terminal‑based benchmarks.
arXiv Computer Vision
Aug 28
OS-Marathon: Benchmarking Computer-Use Agents on Vast-Horizon, Repetitive Tasks
OS-Marathon is a new benchmark that tests computer‑use agents on vast‑horizon, repetitive tasks, covering 100 tasks across five scenarios and ten domains. The study shows that current state‑of‑the‑art agents perform poorly on these tasks, and that simply decomposing workflows into subtasks does not solve the problem. Introducing a cost‑friendly personalization method called GraphDemo, which adapts agents from a single human demonstration, improves performance, highlighting the value of human guidance for these challenging tasks.
arXiv Machine Learning
Sep 2
TRIAGE: Three-level Routing and Intelligent Agent Guidance for Efficient Execution
TRIAGE introduces a three-level routing framework for Large Language Model agents that reduces token consumption by reusing historical execution trajectories. The system classifies queries into direct reuse, skill substitution, and full ReAct levels, achieving significant token savings in large-scale security monitoring and cross-domain benchmarks. An automatic skill extraction mechanism further refines reusable patterns, creating a positive feedback loop that improves efficiency over time.
arXiv AI
Jul 31
A Graph-Native Bitemporal Memory Store for Conversational AI Agents
arXiv:2607. 26520v1 Announce Type: cross Abstract: Conversational AI agents commonly lack persistent memory across sessions.
arXiv AI
Sep 10
SE-GoS: Self-Evolving Graph-of-Skills for Skill Library at Scale
arXiv:2609.08228v1 Announce Type: new Abstract: Modern LLM agents increasingly rely on reusable skills, yet as skill libraries scale to thousands of entries, effective retrieval becomes a bottleneck....
arXiv Machine Learning
Jun 9
Claw-R1: A Step-Level Data Middleware System for Agentic Reinforcement Learning
arXiv:2606. 09138v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) has become an important post-training paradigm for turning LLMs from static chatbots into interactive agents, giving rise to representative applications such as OpenClaw.
arXiv Computation and Language
4d ago
G\"odel Forest: Balancing Search Depth and Breadth for Data-Centric Recursive Self-Improvement
arXiv:2609.36675v1 Announce Type: new Abstract: Recursive self-improvement (RSI) aims to achieve compounding gains by having models improve themselves. While most existing RSI systems optimize extern...
arXiv AI
Sep 2
Relational-Core Graph Analytics Querying graphs at SQL scale, and why the node/edge model is a performance tax, not a truer picture of connected data
arXiv:2609.01525v1 Announce Type: cross Abstract: A durable assumption holds that graph analytics requires a purpose-built graph engine, and that relational systems are ill-suited to connected data....
arXiv AI
Aug 18
From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems
arXiv:2608. 15127v1 Announce Type: cross Abstract: Agentic applications are shifting AI serving from isolated model inference to long-running workloads in which LLMs coordinate tools, environments, and persistent state.