Notes on swe-bench

Showing notes about swe-bench

Topics

1 note on this topic

swe-bench (1)ai (21)agents (14)models (9)memory (7)architecture (6)research (4)scaling (4)systems (4)

Show 65 more topics

trajectories (4)efficient-models (3)forecasting (3)hugging-face (3)infrastructure (3)open-source (3)physics (3)alignment (2)compute (2)image-generation (2)local-ai (2)open-weights (2)oxygen-ai (2)papers (2)reasoning (2)self-hosting (2)verification (2)agency (1)ai-infrastructure (1)attention (1)coding (1)commons (1)cryptography (1)css (1)decentralization (1)desktop (1)developer-tools (1)diffusion (1)efficiency (1)frontend (1)gemma (1)geometry (1)hardware (1)hermes (1)image-editing (1)inference (1)interfaces (1)introduction (1)kwaipilot (1)learning (1)llm (1)long-context (1)microsoft (1)minimax (1)multimodal (1)neuroscience (1)nextjs (1)nous-research (1)on-device (1)ornith (1)plugins (1)policy (1)privacy (1)react (1)recursive-self-improvement (1)reinforcement-learning (1)safety (1)security (1)singularity (1)swarms (1)tools (1)trust (1)tutorial (1)ui (1)vision (1)

aiagentscoding

KAT-Coder-V2.5: Infrastructure Beats Scale for Agentic Coding

KwaiKAT’s KAT-Coder-V2.5 comes within a few points of Opus 4.8 on repository SWE, tops PinchBench, and the open KAT-Coder-V2.5-Dev (35B MoE / 3B active) leads same-scale peers. The paper’s real story is environments, trajectories, and harness-aware RL—not parameter count.

01 · Jul 26, 2026Read