Toward Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability Paper • 2608.06503 • Published Aug 6 • 2
StateM: Reaching 95.3% Raw Accuracy, or a \$15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling Paper • 2608.15089 • Published Aug 15 • 136
CHIMERA Collection The collection for the Paper "CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning" • 5 items • Updated 4 days ago • 3
GIST: Targeted Data Selection for Instruction Tuning via Coupled Optimization Geometry Paper • 2602.18584 • Published Feb 20 • 1
GIST: Targeted Data Selection for Instruction Tuning via Coupled Optimization Geometry Paper • 2602.18584 • Published Feb 20 • 1
CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning Paper • 2603.00889 • Published Mar 1 • 57
SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens Paper • 2510.24940 • Published Oct 28, 2025 • 18