Jul 28, 2026
LLM-SoccerArena: Benchmarking LLMs on Real-World Predictions in Sports
LLM-SoccerArena: Benchmarking LLMs on Real-World Predictions in Sports Large language models are increasingly used to help make decisions about the future, b...
Jul 28, 2026
DSCH-Loss: A Dynamic Semantic Channel Objective for Deep Semantic Hashing
Deep learning-based semantic hashing is a powerful technique for organizing high-dimensional data into short binary codes, enabling fast and efficient search...
Jul 28, 2026
Eviction as Estimation: A Fixed-Lag Smoothing View of Test-Time Memory, and When Measuring Beats Accumulating
Eviction as Estimation: A Fixed-Lag Smoothing View of Test-Time Memory, and When Measuring Beats Accumulating Language models with limited memory must consta...
Jul 28, 2026
Efficiency Matters in Autonomous Research
Efficiency Matters in Autonomous Research AI-driven autonomous research (AR) systems are increasingly used to solve complex problems in science and engineeri...
Jul 27, 2026
SceneActBench: Can Agents Act on the 3D Scenes They See?
SceneActBench: Can Agents Act on the 3D Scenes They See? Vision-language model (VLM) agents are increasingly being used to interact with 3D environments rath...
Jul 27, 2026
A Roadmap to Impactful Pluralistic Alignment Research
A Roadmap to Impactful Pluralistic Alignment Research argues that while the field of pluralistic AI—the effort to make models that reflect diverse human valu...
Jul 27, 2026
IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation
IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation Large Language Models (LLMs) are increasingly used to assist in scientific discovery,...
Jul 27, 2026
The Regression Tax: Decomposing Why Skills Help and Hurt LLM Agents
The Regression Tax: Decomposing Why Skills Help — and Hurt — LLM Agents This paper investigates a hidden cost in AI development: the tendency for "procedural...
Jul 27, 2026
Do Agent Benchmarks Measure Capability? Protocol Validity in the Age of Agentic AI
This paper investigates whether current AI agent benchmarks actually measure the capabilities they claim to test.
Jul 27, 2026
Learning Structural Convergence: A Neuro-Symbolic Benchmark for Temporal Reasoning
Learning Structural Convergence: A Neuro-Symbolic Benchmark for Temporal Reasoning introduces TRACTA, a new synthetic benchmark designed to test how AI syste...
...