One Assistant, Many Memories: Benchmarking Real-World Group Assistance When Recall Is Not Enough Paper • 2611.04867 • Published 18 days ago • 12
On the Opportunities and Challenges of Prefill-to-Autoregressive Cross-Model Transfer Paper • 2611.06976 • Published 16 days ago • 16
HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs Paper • 2610.26770 • Published Oct 19 • 33
OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Models Paper • 2402.06044 • Published Feb 8, 2024 • 2
Large Language Models Fall Short: Understanding Complex Relationships in Detective Narratives Paper • 2402.11051 • Published Feb 16, 2024 • 2
Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States Paper • 2510.11052 • Published Oct 13, 2025 • 52
Pull Requests as a Training Signal for Repo-Level Code Editing Paper • 2602.07457 • Published Feb 7 • 2
Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMs Paper • 2605.30501 • Published May 28 • 27
Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States Paper • 2510.11052 • Published Oct 13, 2025 • 52
Large Language Models Fall Short: Understanding Complex Relationships in Detective Narratives Paper • 2402.11051 • Published Feb 16, 2024 • 2
OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Models Paper • 2402.06044 • Published Feb 8, 2024 • 2
Pull Requests as a Training Signal for Repo-Level Code Editing Paper • 2602.07457 • Published Feb 7 • 2
Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMs Paper • 2605.30501 • Published May 28 • 27