Latest

Every published item, in order · 126 items
Nov 6
Oct 19
ModelsBuildersMulti-sourceSelected20:37
Google Research releases Harness² framework for agent self-improvement

The implication is that harness scaffolding, not model weights, is a lever for gains on unseen tasks, with a frozen model still improving when its surrounding code is edited. Developers building agent systems can apply the editor-composer-reflector pattern to their own pipelines. Code and the arXiv paper (2610.14224) are public, so teams can reproduce the benchmark setup directly.

Event
Philipp Schmid@_philschmid5 sourcesSource
Oct 16
PapersBuildersSelected00:20
Google Paper Introduces Harness^2 for Self-Improving Agent Harnesses

The non-obvious finding is that recursive self-improvement can work without a verifier by letting candidate harness edits compete against each other, which sidesteps a common bottleneck in agent reliability. Builders of agent pipelines can test whether carrying evolved harnesses across tasks beats memory-based baselines like ReasoningBank in their own stacks. Readers can follow the linked arXiv paper and DAIR.AI's chat-with-paper tool to dig into the setup.

elvis@omarsar0Source
Oct 4
PapersBuildersSelected19:44
Google's VeriHarness Turns Agent Rollout Agreement Into Verification

Agreement among multiple rollouts is widely treated as a reliability signal, but this work shows it can mask correlated errors — a finding that affects how anyone builds best-of-n selection for agents. The verification-and-revision loop is practical to apply with existing frontier models, as the Gemini 3.5 Flash and Claude Opus 4.8 gains show. Teams building long-horizon agent pipelines can start from the released 26,000-rollout dataset.

Event
elvis@omarsar02 sourcesSource
Oct 3
Sep 24
PapersBuildersMulti-sourceSelected73°04:37
Google Paper Shows RRSI Stops Agent Harness Evolution Overfitting

Optimizing an agent's harness against a benchmark can inflate eval scores while degrading real-world performance, and this paper quantifies that gap with held-out numbers. Builders running automated prompt or harness optimization should add critic and pruning loops like RRSI's to protect out-of-distribution performance. The paper and a chat-with-paper interface are available via arXiv and dair.ai.

Event
elvis@omarsar03 sourcesSource
Sep 17
AITOP16:09
Anthropic拟10月在新加坡设亚太第五个办事处 开...

Anthropic拟10月在新加坡设亚太第五个办事处 开放本地招聘 数据显示,按人口比例计算,新加坡的Claude.ai使用水平在121个国家中排名第二。 我们观察到,人工智能公司Anthropic计划于10月在新加坡设立其亚太地区的第五…

AITOPRead
Aug 15
Aug 13
Aug 9
Aug 7
AITOP17:04
出口结构剧变:中国卖给世界的,不再是产品而是解法

中国出口"新新三样":从打火机到爬墙机器人,世界不再只是买便宜货 我们观察到一组清晰的数据信号:中国出口的"新新三样"已经从过去的服装、家具、家电,换成机器人、AI模型和创新药物。这不是产业升级的修辞游戏,而是发生在澳大利亚和巴西的实证样…

AITOPRead
Aug 2
Aug 1
Jul 25
Jul 24
Jul 23
ProductsMulti-sourceSelected76°02:33
Chinese contentGemini 3.6 Flash成为Gemini Managed Agents新默认模型

Google 把 Gemini 3.6 Flash 设成托管智能体的默认模型了,不用改代码就能自动升级,还能随时切回旧版。想看看金融多智能体怎么玩?去 AI Studio 试试那个 TICKR 应用吧。

Event
Philipp Schmid@_philschmid11 sourcesSource
Jul 22