Running 59 Don't Train the Model, Evolve the Harness 🌿 59 Evolving an agent's harness, not its model, on Harvey's LAB
Mutual Enhancement of Large and Small Language Models with Cross-Silo Knowledge Transfer Paper • 2312.05842 • Published Dec 10, 2023 • 1
ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning Paper • 2505.04881 • Published May 8, 2025 • 1
Rethinking the Role of Efficient Attention in Hybrid Architectures Paper • 2606.15378 • Published Jun 13 • 20
δ-mem: Efficient Online Memory for Large Language Models Paper • 2605.12357 • Published May 12 • 133
Rethinking the Role of Efficient Attention in Hybrid Architectures Paper • 2606.15378 • Published Jun 13 • 20
ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning Paper • 2505.04881 • Published May 8, 2025 • 1