Latest

Every published item, in order · 21 items

Blogs News Posts Papers Papers →

Oct 23

Papers Policy18:46

Chinese content研究称 Claude Opus 4.8 生成的论文评审已全面优于人类专家

Anthropic 的 Opus 4.8 写的论文评审，在所有指标上赢过了期刊公认的高质量人类专家评审，同行评审要变天了。

#Claude #Opus 4.8 #AI安全 #学术论文

Event

Teortaxes@teortaxesTex2 sourcesSource

Papers Policy16:04

Chinese content哈佛研究：Claude Opus 4.8 写的论文评审全面超过人类专家

哈佛用 1124 篇论文做了盲测，Claude Opus 4.8 写的评审错误率只有人类的三分之一，做科研的可以看看这套流程。

#Claude #GPT-5.5 #peer review #AI安全

rohanpaul_ai@rohanpaul_aiSource

PapersMulti-source12:18

Chinese content研究：Claude Opus 4.8 在同行评审中表现匹敌人类专家

有人拿 124 篇哈佛论文测试 Opus 4.8 当审稿人，结果和人类专家打平，搞科研的朋友可以看看细节。

#Claude #Opus 4.8 #同行评审 #科研

Event

Ethan Mollick@emollick11 sourcesSource

Oct 21

Papers BuildersSelected22:35

Simular's Agent S4 evolves agent interfaces to boost OSWorld scores

Automated interface design shifts the bottleneck in computer-use agents from model quality to environment design, letting a small open model beat frontier systems on cost-adjusted performance. Builders of agent pipelines can apply the same trajectory-driven tool synthesis and population-based selection pattern to their own harnesses. The open-source release makes the method directly reproducible without proprietary APIs.

#Agent S4 #Simular #OSWorld #agents

Event

DAIR.AI@dair_ai2 sourcesSource

Papers BuildersMulti-sourceSelected74°10:11

Agent S4 Evolves Its Own Computer-Use Interfaces

Interface design itself becomes a learnable, evolving capability, meaning smaller open models can beat frontier systems on computer-use tasks at a fraction of the cost. Builders working on agents can reuse the open-source repository and apply the evolution loop to their own workflows. The results set a concrete cost-performance benchmark against GPT-5.5 and Claude Opus 4.8 that teams choosing an agent stack can weigh directly.

#Agent S4 #Qwen3.8-27B #computer-use agents #open-source models

Event

arXiv cs.AI@Saaket Agashe et al. (8)3 sourcesSource

Oct 20

Papers Builders09:27

Chinese contentReTRACE：用 LLM 智能体做逆合成路线规划

一篇把 Claude Opus 4.8 变成合成化学助手的论文，逆合成路线三成基准过审率超 87%，还做了湿实验验证。

#ReTRACE #Claude Opus 4.8 #逆合成 #LLM 智能体

arXiv cs.AI@Jinxiang Xie et al. (5)Source

Oct 18

Papers BuildersMulti-sourceSelected16:22

Google Research open-sources Harness², a recursive agent harness optimisation framework

The non-obvious move here is replacing score-based feedback with same-task A/B behavioural comparisons, which sidesteps the missing-verifier problem that blocks most self-improvement systems. Engineers building agent scaffolds can study the Propose–Probe–Compose loop and reuse its evidence-gated lesson library design in their own stacks. As an open-source release from Google Research, it is directly comparable to other RSI and agent-tuning frameworks that depend on task-specific verifiers.

#Harness² #Google Research #agents #open-source models

Event

shao__meng@shao__meng6 sourcesSource

Oct 16

Papers Builders09:42

Chinese contentiPhone 定位数据解析研究：LLM 直接逆向不可靠，写工具却好用

研究者实测两个前沿模型逆向 Apple 的 protobuf 格式，直接分析错误一堆，但让 Claude 写个 Extractor 工具反而靠谱，思路很实用。

#Claude Opus 4.8 #Codex GPT Sol 5.6 #iOS #逆向工程

arXiv cs.AI@Douglas LeithSource

Oct 15

Papers Builders12:41

Chinese contentAesCode 用图像引导强化学习提升代码生成的视觉质量

做幻灯片、海报生成的朋友看看这篇：代码模型配上参考图做 RL，8B 小模型的视觉分数追上了 GPT-5.5，方法拆得很细。

#AesCode #Qwen3-VL #GPT-5.5 #强化学习

arXiv cs.AI@Xin Gao et al. (16)Source

Oct 4

Papers BuildersSelected19:44

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.

#VeriHarness #Gemini 3.5 Flash #Claude Opus 4.8 #agents

Event