Goto

Collaborating Authors

 strategist


Exclusive: Voters of Color Were 'Driving Force' Behind Midterm Rout, Say Key Strategists

TIME - Tech

Follow this section to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. Follow this tag to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW?


In Maine, a Toss-Up Senate Race Is About the Incumbent and Not Much Else

TIME - Tech

Follow this section to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. Follow this tag to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW?


Yen becoming more favorable hedge against AI market shock, says Goldman Sachs

The Japan Times

The exchange rate of the U.S. dollar against the yen is displayed outside a securities firm in Tokyo on Monday. The yen is becoming less vulnerable when global yields move higher, according to Goldman Sachs. The yen is becoming a more effective hedge against an artificial intelligence-driven market shock as changes in Japan's policy backdrop reduce the risk of the currency weakening sharply when global yields rise, according to Goldman Sachs. "The yen now looks like a more attractive hedge for procyclical portfolios than it has been over recent years, despite the global backdrop still arguing for further JPY weakness," strategists including Kamakshya Trivedi wrote in a note dated Friday. The call comes after the yen showed renewed signs of its traditional haven characteristics during last week's global technology stock rout.


The Biggest Pro-AI Super PAC Network Has Poured Millions Into Nevada Shell Companies

WIRED

Backed by Silicon Valley titans, Leading the Future has raised huge sums to promote pro-AI candidates on both side of the aisle. The Spanish Springs shopping center in Sparks, Nevada, hosts many businesses, including a Spirit Halloween, a hearing aid supplier, and a Vietnamese restaurant. It's also home to a consulting agency that's received millions of dollars from one of the biggest pro-AI super PAC networks ahead of November's midterm elections . The problem is that the company--Lantern Production Consultants LLC--doesn't seem to exist anywhere beyond a post office box in the Spanish Springs shopping complex. Lantern Production Consultants has been paid around $20 million since last year by Think Big, part of a network of pro-AI super PACs funded by the Leading the Future PAC, for a wide array of services, including polling, digital advertising, research, and strategy, according to federal campaign finance records reviewed by WIRED.


US stock market hits all-time high as investors bet big on AI

Al Jazeera

The United States stock market has hit an all-time high as excitement around artificial intelligence continues to fuel a buying frenzy on Wall Street. The S&P 500, the benchmark stock index, closed 0.58 percent higher on Tuesday, topping the previous peak reached in mid-August. Tech stocks were among the top performers, with each of the "Magnificent Seven" apart from Meta closing higher. Amazon led the pack with a 1.95 percent gain, followed by Microsoft and Tesla, which rose 0.78 percent and 0.51 percent, respectively. Apple and Alphabet both rose 0.22 percent, while Nvidia gained 0.14 percent.


Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLMPlanning with Multifaceted Constraints

Neural Information Processing Systems

Unlike reasoning, which often entails a deep sequence of deductive steps, complex real-world planning is characterized by the need to synthesize a broad spectrum of parallel and potentially conflicting information and constraints. For example, in travel planning scenarios, it requires the integration of diverse real-world information and user preferences.


Genesis: Evolving Attack Strategies for LLM Web Agent Red-Teaming

arXiv.org Artificial Intelligence

As large language model (LLM) agents increasingly automate complex web tasks, they boost productivity while simultaneously introducing new security risks. However, relevant studies on web agent attacks remain limited. Existing red-teaming approaches mainly rely on manually crafted attack strategies or static models trained offline. Such methods fail to capture the underlying behavioral patterns of web agents, making it difficult to generalize across diverse environments. In web agent attacks, success requires the continuous discovery and evolution of attack strategies. To this end, we propose Genesis, a novel agentic framework composed of three modules: Attacker, Scorer, and Strategist. The Attacker generates adversarial injections by integrating the genetic algorithm with a hybrid strategy representation. The Scorer evaluates the target web agent's responses to provide feedback. The Strategist dynamically uncovers effective strategies from interaction logs and compiles them into a continuously growing strategy library, which is then re-deployed to enhance the Attacker's effectiveness. Extensive experiments across various web tasks show that our framework discovers novel strategies and consistently outperforms existing attack baselines.


Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraints

arXiv.org Artificial Intelligence

Unlike reasoning, which often entails a deep sequence of deductive steps, complex real-world planning is characterized by the need to synthesize a broad spectrum of parallel and potentially conflicting information and constraints. For example, in travel planning scenarios, it requires the integration of diverse real-world information and user preferences. While LLMs show promise, existing methods with long-horizon thinking struggle with handling multifaceted constraints, leading to suboptimal solutions. Motivated by the challenges of real-world travel planning, this paper introduces the Multiple Aspects of Planning (MAoP), empowering LLMs with "wide-horizon thinking" to solve planning problems with multifaceted constraints. Instead of direct planning, MAoP leverages the strategist to conduct pre-planning from various aspects and provide the planning blueprint for planners, enabling strong inference-time scalability by scaling aspects to consider various constraints. In addition, existing benchmarks for multi-constraint planning are flawed because they assess constraints in isolation, ignoring causal dependencies within the constraints, e.g, travel planning, where past activities dictate future itinerary. To address this, we propose Travel-Sim, an agent-based benchmark assessing plans via real-world simulation, thereby inherently resolving these causal dependencies. This paper advances LLM capabilities in complex planning and offers novel insights for evaluating sophisticated scenarios through simulation.


Hound: Relation-First Knowledge Graphs for Complex-System Reasoning in Security Audits

arXiv.org Artificial Intelligence

Hound introduces a relation-first graph engine that improves system-level reasoning across interrelated components in complex codebases. The agent designs flexible, analyst-defined views with compact annotations (e.g., monetary/value flows, authentication/authorization roles, call graphs, protocol invariants) and uses them to anchor exact retrieval: for any question, it loads precisely the code that matters (often across components) so it can zoom out to system structure and zoom in to the decisive lines. A second contribution is a persistent belief system: long-lived vulnerability hypotheses whose confidence is updated as evidence accrues. The agent employs coverage-versus-intuition planning and a QA finalizer to confirm or reject hypotheses. On a five-project subset of ScaBench[1], Hound improves recall and F1 over a baseline LLM analyzer (micro recall 31.2% vs. 8.3%; F1 14.2% vs. 9.8%) with a modest precision trade-off. We attribute these gains to flexible, relation-first graphs that extend model understanding beyond call/dataflow to abstract aspects, plus the hypothesis-centric loop; code and artifacts are released to support reproduction.


MIND: Towards Immersive Psychological Healing with Multi-agent Inner Dialogue

arXiv.org Artificial Intelligence

Mental health issues are worsening in today's competitive society, such as depression and anxiety. Traditional healings like counseling and chatbots fail to engage effectively, they often provide generic responses lacking emotional depth. Although large language models (LLMs) have the potential to create more human-like interactions, they still struggle to capture subtle emotions. This requires LLMs to be equipped with human-like adaptability and warmth. To fill this gap, we propose the MIND (Multi-agent INner Dialogue), a novel paradigm that provides more immersive psychological healing environments. Considering the strong generative and role-playing ability of LLM agents, we predefine an interactive healing framework and assign LLM agents different roles within the framework to engage in interactive inner dialogues with users, thereby providing an immersive healing experience. We conduct extensive human experiments in various real-world healing dimensions, and find that MIND provides a more user-friendly experience than traditional paradigms. This demonstrates that MIND effectively leverages the significant potential of LLMs in psychological healing.