CliffCompaction: Cost-Efficient Compaction for Long-Horizon Coding Agents
Carnegie Mellon University; Bosch Center for AI
SWE-Serve: Benchmarking Agentic Engineering For Production Inference Serving
NVIDIA; University of California, Berkeley
Grow the Harness, Not the Context: From Strategy-Free Scaffolds to Reusable Specialist Agents
Chinese Academy of Sciences; University of Chinese Academy of Sciences; Shenzhen University of Advanced Technology; University of Macau
Type-Safe Is Not Error-Free: A Constrained Decision Head Follows the Option Name, Not the Rubric Bound to It
National University of Singapore; Fudan University
The Delegation Blind Spot: Auditing Product Decisions from Agent Choices
Independent Research
Quantum-Aided Active Device Detection in Energy-Harvesting Symbiotic Radio Networks
Polytechnique Montréal
Neutral-Atom-based Quantum Optimization for Resource Allocation in NOMA Networks
Polytechnique Montréal; Thales cortAIx Labs
JEV-as-a-Judge: Accept When Confident, Escalate When Unsure
Carnegie Mellon University
REFLEX with Jev for Efficient Selective Control in LLM Agents
Nanyang Technological University
Reproducible AI Requires Reproducible Randomness
Université Clermont Auvergne; Clermont Auvergne INP; CNRS; LIMOS
Recursive self-improvement of AI research agents
Weco AI
The Source of Disturbance Matters: External, Internal, and Control-Generated Noise in Adaptive Regulation
Critical Attention Systems
Reliability Theory for AI Control
Dual-Frontier: When Can an Agent Trust Its World Model?
Central South University; The Hong Kong University of Science and Technology; Xiangjiang Laboratory; University of Sydney; University of Science and Technology of China
FISSION: Label Augmentation for Bot Detection
Yale University; IC3; Staples High School
Decoupling Is Not Identification: Supervised Evidential Learning in Next-Token Prediction
Rensselaer Polytechnic Institute
Coding Agents are Strong Prompt Optimizers
Microsoft
A Multi-Timestep LSTM Ensemble regressor for Enhanced Short-Term Runoff Prediction
University of Birjand; Clemson University
A Hybrid AI Framework for Academic Advising: Integrating Ensemble-Based Grade Prediction and a Rule-Based Expert System
University of Birjand
Improved Multiplayer Bandit Algorithm for Bernoulli Rewards
University of California, Los Angeles
