LayerRoute introduces a lightweight, input-conditioned adapter that selectively skips transformer blocks in agentic language models, achieving significant FLOPs reduction while improving performance.

The paper introduces Andes, a framework that treats data generation as a plug-and-play agent skill, enabling autonomous alignment of LLMs by providing an intelligent, closed-loop data synthesis interf…

This paper systematically analyzes the complex design space of hybrid multi-agent systems combining on-device and cloud AI models, finding that the optimal architecture is highly task-dependent and th…

MemPro introduces a system-level evolution framework that treats the entire memory construction-retrieval pipeline as an evolvable program, significantly improving long-horizon agent performance over…

UniScale proposes a unified framework that jointly optimizes model routing and test-time scaling to achieve a superior, fine-grained quality-cost trade-off for large language model inference.

MLEvolve is a novel self-evolving multi-agent framework that enables LLM agents to discover and optimize machine learning algorithms for complex, long-horizon tasks.

The paper proposes SAGE, a novelty-aware gate that efficiently controls memory updates in agentic LLMs by classifying new facts as clearly novel, clearly redundant, or uncertain, thereby significantly…

The paper introduces CAIAMAR, a multi-agent reasoning framework that achieves context-aware and high-fidelity anonymization of personally identifiable information (PII) in street imagery, significantl…

The paper introduces memorywire, a vendor-neutral JSON-Schema wire format and reference implementation designed to standardize and govern memory operations across disparate agent-memory frameworks.

The paper introduces Grounded Agentic Interaction Synthesis (GAIS), a framework that generates high-quality, diverse, and complex agentic training data by anchoring tasks to real-world protocols, sign…

The paper proposes Meta-Team, an experience-driven framework that enables multi-agent systems (MAS) to collaboratively self-evolve by transforming complex execution experiences into reusable improveme…

The paper proposes FluxMem, a novel connectivity-evolving memory framework that models memory as a dynamic graph to improve LLM agent performance in complex, changing environments.

MOSAIC is a novel scheduling framework that significantly accelerates Mixture-of-Agents (MoA) workloads by jointly optimizing expert placement and utilizing confidence-aware adaptive aggregation.

The paper introduces StreamMA, a streaming multi-agent reasoning system that significantly reduces latency and improves effectiveness by passing reasoning steps to downstream agents as they are genera…

HighTide is an evolving, AI-assisted, open-source benchmark suite for VLSI design, providing a comprehensive and scalable platform for hardware development.

Lodestar is a novel online learning-based request routing system that significantly improves LLM inference efficiency by dynamically assigning incoming requests to the optimal GPU instance to minimize…

The paper proposes BaSE, a multi-armed bandit approach, to optimally allocate a fixed budget of LLM calls across parallel evolutionary search trajectories, significantly improving mean fitness and rel…

The paper introduces OpenWebRL, an open framework that enables training visual web agents using online multi-turn Reinforcement Learning directly on live websites, achieving state-of-the-art performan…

The paper proposes a modular agent framework and novel learning methods to design and optimize practical, cost-effective, and controllable LLM-based agentic systems.