6
IdeaTrail: Full-Process Agent Trajectories for Scientific Ideation
IdeaTrail is a new dataset designed to capture the complete, multi-stage workflow of AI agents performing scientific ideation and research tasks.
6
MemDecay: Region-Aware KV Cache Eviction for Efficient LLM Agent Inference
MemDecay is a new memory management technique that optimizes LLM agent inference by using region-aware KV cache eviction based on semantic structure.
6
Gefen: Optimized Stochastic Optimizer
The proposed Gefen optimizer reduces the memory footprint of large-scale model training by sharing second-moment estimates and quantizing first-moment states.
6
Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models
Embodied-R1.5 is a new foundation model designed to unify embodied reasoning and physical intelligence using a large-scale dataset of 15 billion tokens.
6
Robust, Scalable Detection of Text Containment in Large Web-Crawled Corpora
Researchers released FindMyText, an open-source Python package designed to detect near-verbatim text containment within large web-crawled datasets using document fingerprinting.
6
Edge Physical AI Deployment of Vision Transformers on Heterogeneous Edge GPU Targeting Autonomous Vehicles
A new scheduling method for heterogeneous edge GPUs aims to improve the efficiency and throughput of vision transformer models in autonomous vehicle applications.
6
Unlocking Parallelism in Autoregressive Language Models via Speculative Decoding with Progressive Tree Drafting
Researchers propose a new speculative decoding method that improves large language model inference speed by utilizing progressive tree drafting to better exploit parallel processing.
6
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning
GrandCode is a new multi-agent reinforcement learning system that aims to achieve competitive programming performance at the level of human grandmasters.
6
Measuring AI Ability to Complete Long Software Tasks
A new metric called the 50%-task-completion time horizon has been proposed to better compare AI performance against human capabilities in software development tasks.
6
The Ebb and Flow of Multimodal Focus: Scheduling Visual Relay Windows for Grounded VLM Reasoning
This study analyzes the internal attention dynamics of vision-language models to explain why visual grounding degrades and proposes scheduling visual relay windows to stabilize reasoning.
6
Valid $\ne$ Necessary: Diagnosing Latent Inefficiency in Chain-of-Thought
The study identifies a critical inefficiency in Chain-of-Thought prompting where models generate redundant but logically valid reasoning steps that current evaluators fail to penalize.
6
The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomy
This paper outlines a deployment-focused pathway for transitioning medical AI agents from simple assistants to autonomous clinical systems.
6
Mako: A Self-Evolving Agentic Operating System (SE-AOS) for Autonomous Web Exploitation
The Mako project introduces a self-evolving agentic operating system capable of autonomously synthesizing and testing new security exploits.
6
Are LLMs Ready for Scientific Discovery? A Capability-Oriented Benchmark for AI Scientists
Researchers have introduced SDABench, a new benchmark designed to evaluate the scientific data analysis capabilities of large language models across six distinct areas.
6
Agentic-DPO: From Imitation to Agentic Policy Optimization on Expert Trajectories
Agentic-DPO is a new training framework designed to optimize AI agent policies on expert trajectories by teaching them to avoid plausible mistakes rather than just imitating sequences.
6
A Theory of Least Autonomy in AI
Researchers propose a formal theory of least autonomy as a security principle to constrain the permissions and workflow capabilities of agentic AI systems.
6
SWE-MERA: A Dynamic Benchmark for Agenticly Evaluating Large Language Models on Software Engineering Tasks
The authors introduce SWE-MERA, a dynamic benchmark designed to mitigate data contamination and improve the evaluation of LLMs on software engineering tasks.
6
HCRMap: Pressure-Aware Hot-Expert Residency Mapping for 3.5D MoE Chiplet Inference
The paper introduces HCRMap, a mapping framework designed to mitigate compute and communication imbalances caused by uneven expert activation in Mixture-of-Experts models on multi-chiplet systems.
6
ReflectWorld-MM: An Entity-Oriented Multi-Media Memory System for Open-Ended Video Streams
Researchers developed ReflectWorld-MM, a multimedia memory system that organizes long-term video stream data around persistent entities rather than individual frames.
6
The Ramanujan Challenge For AI
Researchers have introduced a new benchmark dataset of mathematical constant formulas to evaluate the advanced mathematical reasoning capabilities of AI systems.
6
Model Collapse: On Recursion, Noise, and Uncharted Machine Visions
This paper examines the phenomenon of model collapse from both engineering and creative perspectives, exploring how recursive training on AI-generated data affects model output.
6
Knowledge Graphs Meet Graph Neural Networks: A Comprehensive Survey
This paper provides a comprehensive survey and a new two-level taxonomy of Graph Neural Network methodologies applied across knowledge graph technologies.
6
Remembering Distinct Items, Not Tokens: A Learnable Dirichlet-Process Cache Between State-Space Models and Attention
This paper proposes a learnable Dirichlet-process cache that stores only novel inputs to bridge the gap between state-space models and attention mechanisms.
6
FARS: A Fully Automated Research System Deployed at Scale
The authors introduce FARS, a fully automated system that enables AI agents to conduct research, generate hypotheses, and write manuscripts at scale.