Žinutės

HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?

As agents move from research prototypes to deployed tools, their capability increasingly depends on model-external execution infrastructure, commonly termed the agent harness. Changing this harness while holding model weights fixed can substantially alter task performance. Current agent evaluations typically report downstream performance under a chosen harness, leaving a model's ability to develop the harness itself comparatively underexplored. We introduce HarnessDev, a benchmark that shifts the unit of evaluation from task outputs to runnable infrastructure. HarnessDev covers two stages. In Creation, the agent starts from a minimal seed and a small number of cases, then builds a complete execution system. In Evolution, it starts from its own created harness and iteratively revises it using downstream execution feedback, with the goal of improving benchmark performance. We then evaluate each constructed harness on capability (task success on held-out benchmarks) and efficiency (execut

arXiv.orgPerskaityta 2026-09-09 15:01

Portal by Spotify cut my Claude Code token usage by 90% | Spotify Engineering

Most of what an AI coding agent does for me isn't thinking. It's I/O.

Spotify EngineeringPerskaityta 2026-09-09 19:01

Cloudflare Status

Real-time status and incident history for Cloudflare services, network locations, and scheduled maintenance.

Cloudflare StatusPerskaityta 2026-09-09 19:01

Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse

Production deployments often swap between different-sized models in a family for cost-quality cascading, mid-conversation switching, and routing, and each swap forces the receiver to repay the prefill from scratch. We propose cross-model KV cache transfer, where the receiver reuses the source's KV cache, skipping prefill. We find that cross-model KV has substantial linear structure across matched-KV pairs, where source and target share KV head count and per-head dimension. On Qwen3 14B- 32B, one source layer explains 56% of variance in the target's keys and 32% in values, rising to 79% and 65% with multiple source layers. Building on this, we design a closed-form ridge mapper that operates per head and proceeds in three steps. First, for each target layer we select the top-k most predictive source layers and concatenate their KV as input. Second, we strip RoPE from the keys before mapping, so the fit is position-free and reusable across context lengths. Third, we fit ridge regression o

arXiv.orgPerskaityta 2026-09-09 19:01

Get Your Tickets | Startup Fair in Vilnius

Secure your spot at Startup Fair – the Baltics’ top startup event. Choose your ticket and join investors, founders, and innovators in Vilnius!

Startup FairPerskaityta 2026-09-09 23:01