Daily Issue
Vol. I — No. 23
02 · 06
Tuesday, 2 June 2026
Generated 2026-06-02 13:01
google/gemini-2.5-flash-lite-preview-09-2025
对未来真正的慷慨，是把一切都献给现在。 — 加缪 51 items · 4 sections
§ 0

The Morning

Local weather 1
This morning in
London
Light drizzle
Today's range
20.1°↓14.8°
currently 17.7°
Feels
15.2°
Rain
100%
Wind
20 km/h
Humid
67%
Rise
04:48
Set
21:09
§ I

US Stocks

Pre-market signal radar 12
US pre-market radar
premarket 2026-06-02
8 Bullish
0 Bearish
4 Neutral
Sector Tape
Compute Mining 4 names
73 Top: WULF · Bullish · RS +1.2% Bullish 4 / Bearish 0 / 5d +15.4%
Servers and Thermal Management 2 names
73 Top: DELL · Bullish · RS +21.3% Bullish 2 / Bearish 0 / 5d +28.3%
Networking Equipment 4 names
69 Top: APH · Neutral · RS -2.8% Bullish 1 / Bearish 0 / 5d +5.7%
Manufacturing 4 names
66 Top: FLEX · Neutral · RS +3.0% Bullish 1 / Bearish 0 / 5d +5.9%
Foundry 2 names
64 Top: TSM · Neutral · RS -6.5% Bullish 0 / Bearish 0 / 5d -0.5%
Hyperscale Cloud 4 names
63 Top: ORCL · Neutral · RS +0.0% Bullish 0 / Bearish 0 / 5d +8.9%
Battery and Energy Storage 3 names
59 Top: EOSE · Neutral · RS +17.4% Bullish 0 / Bearish 0 / 5d +16.4%
Energy Infrastructure 1 names
50 Top: VST · Neutral · RS +3.4% Bullish 0 / Bearish 0 / 5d -1.0%
Ticker Setup Move Score Evidence Quality
DELL Dell Technologies Servers and Thermal Management
Bullish Gap up + news Medium confidence
+1.6% $473.25 5d +57.9%
73 sector positive RS +50.9%

Bullish setup from +1.6% vs previous close, positive sector tape, 3 recent headline(s).

Dell Technologies Stock Rockets 98% With 8-Day Winning Streak - Trefis Weakens if price fades below previous close or sector benchmarks roll over.
quote: delayed fallback news: fresh financials: fresh news: 3
FLEX Flex Ltd Manufacturing
Bullish Gap up + news Medium confidence
+2.0% $150.95 5d +11.7%
72 sector positive RS +8.8%

Bullish setup from +2.0% vs previous close, positive sector tape, 3 recent headline(s).

Norges Bank Purchases Shares of 5,292,218 Flex Ltd. $FLEX - MarketBeat Weakens if price fades below previous close or sector benchmarks roll over.
quote: delayed fallback news: fresh financials: fresh news: 3
IREN IREN Ltd Compute Mining
Bullish Sector tailwind Medium confidence
-0.3% $65.15 5d +15.0%
72 sector positive RS +0.7%

Bullish setup from positive sector tape, 3 recent headline(s).

symbol__ Stock Quote Price and Forecast - CNN Weakens if price fades below previous close or sector benchmarks roll over.
quote: delayed fallback news: fresh financials: fresh news: 3
CLS Celestica Manufacturing
Neutral Gap up + news Medium confidence
+3.9% $443.22 5d +16.1%
69 sector positive RS +13.2%

Watchlist item from +3.9% vs previous close, positive sector tape, 3 recent headline(s).

Celestica: The Quiet Backbone Of The AI Hardware Revolution - Seeking Alpha Needs fresh price/news confirmation before becoming an actionable setup.
quote: delayed fallback news: fresh financials: fresh news: 3
TSM Taiwan Semiconductor Foundry
Neutral Sector tailwind Medium confidence
+0.8% $438.97 5d +7.7%
69 sector positive RS +1.7%

Watchlist item from positive sector tape, 3 recent headline(s).

What's Going On With Taiwan Semiconductor Stock Tuesday? - Benzinga Needs fresh price/news confirmation before becoming an actionable setup.
quote: delayed fallback news: fresh financials: fresh news: 3
ANET Arista Networks Networking Equipment
Neutral Sector tailwind Low confidence
-0.1% $170.60 5d +10.8%
67 sector positive RS +2.3%

Watchlist item from positive sector tape, 3 recent headline(s).

How To Earn 12% While Waiting For Arista Stock To Fall - Trefis Needs fresh price/news confirmation before becoming an actionable setup.
quote: delayed fallback news: fresh financials: fresh news: 3
quotes: nasdaq 24 24/24news: google_news_rss 24 24/24filings: sec 24 24/24, fallback 24

Generated from public market data and news for research and education. Not financial advice; data may be delayed, incomplete, or wrong.

§ II

From the arXiv

arXiv preprints 10 of 20
cs.AIarxiv:2606.02372v1Lead article

COMAP: Co-Evolving World Models and Agent Policies for LLM Agents

Youwei Liu, Jian Wang, Hanlin Wang, Wenjie Li

OMAP proposes a novel framework where textual world models and agent policies co-evolve through closed-loop interaction. The agent uses the world model to predict future states for candidate actions and refines its choice based on the predicted feedback's estimated reliability. This process leverages on-policy trajectories to update the world model via self-distillation, ensuring it remains aligned with the agent's evolving behavior.

Read abstract →Full PDFLINNET · SCORE10RELEVANCE
Conceptual illustration of the co-evolution of world models and agent policies for LLM Agents.
Conceptual illustration of the co-evolution of world models and agent policies for LLM Agents.
Prevalence of food-noise categories across models ( G : Gemma-2-9B-Instruct , L : Llama-3.1-8B-Instruct , and Q : Qwen-2.5-7B-Instruct ) and context–request risk conditions ( NN , NR , RN and RR ). Each cell reports the percentage of replies containing at least one lexical match from the corresponding category, with darker colours indicate higher prevalence. We report statistical comparisons between the NN and RR conditions in Tab. ˜ 16 , and a full breakdown in § ˜ G.2 .
Prevalence of food-noise categories across models ( G : Gemma-2-9B-Instruct , L : Llama-3.1-8B-Instruct , and Q : Qwen-2.5-7B-Instruct ) and context–request risk conditions ( NN , NR , RN and RR ). Ea…
cs.AIarxiv:2606.02444v1

Food Noise & False Safety: A Systematic Evaluation of How LLMs Fail to Adapt to Eating Disorder Queries with Clinician Feedback

Giulia Pucci, Emily Hemendinger et al.

This paper systematically evaluates how Large Language Models (LLMs) respond to eating disorder (ED) queries, focusing on the risk of models uncritically adapting to unsafe user requests. By consulting with clinical experts, the authors identify specific lingu…

abstractpdfLINNET · SCORE9RELEVANCE
cs.AIarxiv:2606.02449v1

HLL: Can Agents Cross Humanity's Last Line of Verification?

Xinhao Song, Su Su et al.

This paper introduces **HLL (Humanity's Last Line of Verification)**, a controlled benchmark designed to test whether multimodal AI agents can successfully navigate and solve interactive CAPTCHAs, which serve as a critical defense against automation. The core …

abstractpdfLINNET · SCORE9RELEVANCE
CAPTCHA as the final frontier: securing web services by testing interactive, human-level reasoning against automated agents.
CAPTCHA as the final frontier: securing web services by testing interactive, human-level reasoning against automated agents.
Iteris agent
Iteris agent
cs.AIarxiv:2606.02484v1

Iteris: Agentic Research Loops for Computational Mathematics

Leheng Chen, Zihao Liu et al.

Iteris is an agentic research system specifically designed to tackle open problems in computational mathematics, which require a mix of proof, numerical experimentation, and algorithm design. The core method involves creating an autonomous loop where the AI ge…

abstractpdfLINNET · SCORE9RELEVANCE
cs.AIarxiv:2606.02470v1

MCP-Persona: Benchmarking LLM Agents on Real-World Personal Applications via Environment Simulation

Wenhao Wang, Peizhi Niu et al.

This paper introduces **MCP-Persona**, the first benchmark specifically designed to evaluate LLM agents using **Model Context Protocol (MCP)** tools in real-world, personalized application settings (e.g., social media, collaboration suites). The core method in…

abstractpdfLINNET · SCORE9RELEVANCE
System overview of MCP-Persona, which is built upon the interaction of Tools , Contexts , and Tasks . For each component, we introduce a dedicated method, described in detail as Tool-Traverse (§ 3.1 ), Context-Tree (§ 3.2 ), and Persona-Gen (§ 3.3 ).
System overview of MCP-Persona, which is built upon the interaction of Tools , Contexts , and Tasks . For each component, we introduce a dedicated method, described in detail as Tool-Traverse (§ 3.1 )…
№06
cs.AI
9

Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling

Seojeong Park, Jiho Choi et al.

This paper addresses **Perceptual Judgment Bias** in multimodal LLM judges, where models favor plausible text over correct visual evidence. The core method involves creating a **Pe…

abstractpdf
№07
cs.AI
9

MOC: Multi-Order Communication in LLM-based Multi-Agent Systems

Yao Guan, Lin Wang et al.

This paper introduces the **Multi-Order Communication (MOC)** scheme to improve message exchange in LLM-based multi-agent systems. MOC addresses the limitations of simple neighbor …

abstractpdf
№08
cs.AI
9

Policy and World Modeling Co-Training for Language Agents

Ning Lu, Baijiong Lin et al.

This paper introduces PaW, a Policy and World Modeling co-training framework that integrates world model supervision directly into the standard reinforcement learning (RL) process …

abstractpdf
№09
cs.AI
9

Repurposing Adversarial Perturbations for Continual Learning: From Defense to Active Alignment

Ran Liu, Min Yu et al.

This paper introduces **AdvCL**, a continual learning method that repurposes adversarial perturbations as a geometric control signal for stable adaptation. It employs three plug-in…

abstractpdf
№10
cs.AI
9

SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment

Hao Li, Jingkun An et al.

SafeSteer addresses the alignment tax by proposing localized on-policy distillation, focusing only on safety-critical tokens. It first creates a safety teacher via activation steer…

abstractpdf
See all 20 papers →
§ III

The Town Square

Hacker News 10
1922
pts
Top story
The newest Instagram “exploit” is the goofiest I've seen

A recent, unusual Instagram "exploit" involved a bizarre account takeover process that Meta's security team mishandled, leading to a confusing fiasco.

0xsid.com1 Jun discuss on HN →
503
Anthropic confidentially submits draft S-1 to the SEC
anthropic.com1 Jun
438
AI Agent Guidelines for CS336 at Stanford
github.com1 Jun
303
DuckDuckGo makes its 'no-AI' search engine easier to access as its traffic booms
techcrunch.com1 Jun
247
Florida sues OpenAI and Sam Altman over AI risks
politico.com1 Jun
217
Alphabet announces $80B equity capital raise to expand AI infra and compute
abc.xyz1 Jun
208
Ask HN: Who is hiring? (June 2026)
1 Jun
171
Adafruit Receives Demand Letter from Fenwick Legal Counsel on Behalf of Flux.ai
blog.adafruit.com2 Jun
148
Nvidia Cosmos 3
developer.nvidia.com1 Jun
127
Ask HN: Who wants to be hired? (June 2026)
1 Jun
compiled overnight by google/gemini-2.5-flash-lite-preview-09-2025 · end of issue no. 23 · thank you for reading