arXiv AI
CoMemBench: Benchmarking Collaborative Memory Boundaries across Multi-Agent Workflow Topologies
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
1d ago
Topological Coherence for Self-evolving Multi-agent Systems
The paper introduces TOCOMAS, a Topology‑Coherent Multi‑Agent System that enforces topological coherence—consistent responsibility, handoff, and memory boundaries—within self‑evolving multi‑agent systems. TOCOMAS grounds task graphs in tool interfaces, groups compatible task nodes into reusable responsibility domains, and derives collaboration and memory visibility rules that respect task dependencies. In experiments on BBEH, WorkBench, SWE‑Bench‑Verified, and CoMemBench, TOCOMAS outperforms baseline methods in task success, verified progress, handoffs, and memory isolation.
arXiv AI
Jul 13
Shared Selective Persistent Memory for Agentic LLM Systems
arXiv:2607. 09493v1 Announce Type: new Abstract: Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the configuration choices, domain constraints, data schemas, and tool-use patterns that made previous sessions productive.
arXiv AI
Jul 28
HeraSys: Collaborative Serving of Multiple LLM Workflows via Fine-Grained End-to-End Optimization
arXiv:2607. 22578v1 Announce Type: new Abstract: The proliferation of Large Language Models (LLMs) has shifted serving systems from processing isolated requests to orchestrating high-concurrency, multi-tenant agentic workflows.
arXiv AI
Sep 2
UniACE: A Unified Framework for Evaluating LLM Agentic Capabilities
UniACE is a unified framework that standardizes the evaluation of large language model (LLM) agents by representing each benchmark as an instruction–tool–environment triplet and running models through a shared, task‑agnostic harness in isolated runtimes. It preserves native success criteria, offers an offline mode for dynamic‑resource tasks, and standardizes efficiency metrics, execution records, and failure attribution. Applying UniACE to 7 benchmarks across 24 domains and 15 models revealed significant score shifts, ranking reversals, and sensitivity to evidence representation, highlighting the impact of evaluation configuration on reported agent performance.
arXiv AI
Jun 6
Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads
arXiv:2606. 06448v1 Announce Type: new Abstract: LLM agents are increasingly deployed on long-horizon tasks requiring sustained reasoning over extended interaction histories.
arXiv AI
Jun 2
CoMIC: Collaborative Memory and Insights Circulation for Long-Horizon LLM Agents in Cloud-Edge Systems
arXiv:2606. 00756v1 Announce Type: new Abstract: Deploying lightweight Large Language Model (LLM) agents on edge servers can reduce latency and move agentic services closer to users, but resource-constrained edge models often struggle with long-horizon tasks that require persistent memory, subgoal tracking, and reflection.