Selecting Long-Horizon Trajectories for Reliable and Efficient Terminal-Agent Training
Research
Research News
New papers, breakthroughs and academic AI research
Off-Policy Merging Beats On-Policy Self-Distillation for Continual Learning
Research
Reward-DAgger: Robot-Gated Interactive Imitation Learning with General-Purpose Progress-Based Reward Models
Research
Agentic Resource Allocation for Batch Multi-Objective Bayesian Optimization in Autonomous Materials Discovery
Research
Solving VeriContest with a Lean-Backed Rust Verifier
Research
Language Model Fingerprinting Requires Rethinking Watermark Teachers
Research
StagQ: Constraint-Driven Multi-Precision Weight Quantization for LLMs
Research
Risk-Calibrated Proposal Transport for Finite-Particle Diffusion Steering
Research
A study on human-agent teaming through spoken interaction: the impact of human individual traits and agent characteristics
Research
Agent Reliability Profiles in Financial Services
Research
Investigating Query-Insensitive Behavior in Spatio-Temporal Video Grounding
Research
FlexCast: Adaptive Weather Forecasting from Arbitrary Field Sets
Research