Sign in

Category: Other

  • The Silent Failures in Agentic Data Science

    The Silent Failures in Agentic Data Science

    The Silent Failures in Agentic Data Science

    arXiv:2610.14115v1 Announce Type: new Abstract: Large language models have significantly lowered the barrier to writing code. Naturally, this has also led to the development of data science agents that promise automating the design and execution of data science from task formulation to model development. Existing evaluations of agentic data science (agentic DS) assess downstream predictive performance and code correctness, providing preliminary insight in agentic DS capabilities. We argue that these evaluations overlook the fundamental principles of data science: methodological data science- and domain knowledge. As such, only assessing downstream performance masks methodological failures such as data leakage and inappropriate validation, limiting the development of robust agentic DS systems. In this paper, we evaluate agentic DS beyond accuracy from three different angles: 1) a large-scale analysis of failure modes in common agentic DS frameworks and models across 220 data science tasks, 2) a reusable and extensible test suite with curated data science tasks that test for six specific failures in a controlled manner, and 3) a qualitative assessment of agentic DS pipelines against expert solutions on Kaggle competitions. We find that the majority of agentic solutions contain at least one failure mode despite the complexity of agentic harness or model capacity. Moreover, we identify a positive correlation between the occurrence of data leakage failures and predictive performance, confirming the necessity to evaluate agents beyond accuracy. Our qualitative analysis shows that DS agents generally lack problem solving creativity and domain knowledge, compared to competition-winning data scientists. We believe that principled failure mode analysis, as presented here, should be integral part of agentic DS evaluations, and that the insights we surface will be key in developing trustworthy agentic DS pipelines.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.14115

  • ClawLoop: Self-Improving Agents via Harness-Native Training Loop

    ClawLoop: Self-Improving Agents via Harness-Native Training Loop

    ClawLoop: Self-Improving Agents via Harness-Native Training Loop

    arXiv:2610.14118v1 Announce Type: new Abstract: The rapid advancement of Large Language Models (LLMs) has driven their deployment toward general-purpose harness environments, where LLM-based agents operate in sandbox workspaces and interact directly with file systems and shells. While numerous post-training pipelines exist for tool-use agents, their counterparts for harness-based agents remain scarce and are predominantly one-shot and teacher-dependent: a stronger external model synthesizes tasks and collects trajectories, the target agent is trained once, and evaluation results are consumed by human researchers rather than fed back into the loop. Such pipelines are inherently bounded by the capability of the external model and the scope of human prior, leaving no room for self-improvement. To address these limitations, we propose ClawLoop, a framework that enables self-improving without any external teacher model and with minimal prior dependencies. ClawLoop composes three phases into a self-sustaining cycle: Task Synthesis, which generates a diverse pool of training tasks via two complementary construction routines, applies diagnosis-conditioned difficulty growth followed by both agent-free and agent-based task validation; Training, which updates the agent via SFT and/or RL; and Diagnosis and Feedback, which analyzes the agent's rollout behaviors to produce a capability analysis report that will be used as feedback for task synthesis in the next iteration. Using Qwen3.6-27B as the loop model, ClawLoop yields consistent improvements on SkillsBench, Claw-Eval-Live, and ClawGym-Bench. The iteratively refined tasks are further transferred to smaller-scale Qwen3.5-4B and 9B models with gains across all benchmarks, validating data quality independently of the loop model.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.14118

  • Figma announces new features to define how agents work on its platform

    Figma announces new features to define how agents work on its platform

    Figma announces new features to define how agents work on its platform

    Figma is also releasing its code layers feature in open beta.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: TechCrunch
    Original article: https://techcrunch.com/2026/10/14/figma-announces-new-features-to-define-how-agents-work-on-its-platform/

  • Gudea leverages AI to help organizations prevent social media crises before they erupt

    Gudea leverages AI to help organizations prevent social media crises before they erupt

    Gudea leverages AI to help organizations prevent social media crises before they erupt

    Every day, conversations unfold across social media and websites around the world. A seemingly insignificant post—whether it involves AI-generated misinformation, hate speech, or a damaging rumor—can quickly snowball into a much larger public controversy. Gudea, a company that tracks how stories and rumors spread online that describes itself as the “storm tracker for the internet,” […]

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: TechCrunch
    Original article: https://techcrunch.com/2026/10/14/gudea-leverages-ai-to-help-organizations-prevent-social-media-crises-before-they-erupt/

  • Ricursive Intelligence is betting on AI-designed chips to help solve the compute crisis

    Ricursive Intelligence is betting on AI-designed chips to help solve the compute crisis

    Ricursive Intelligence is betting on AI-designed chips to help solve the compute crisis

    The founders detailed how their startup is developing AI that can design chips, learn from each iteration, and improve subsequent designs, all with the goal of automating and accelerating the chip design process.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: TechCrunch
    Original article: https://techcrunch.com/2026/10/14/ricursive-intelligence-is-betting-on-ai-designed-chips-to-help-solve-the-compute-crisis/

  • JPMorgan Chase blocks outside AI agents from directly accessing customer accounts

    JPMorgan Chase blocks outside AI agents from directly accessing customer accounts

    JPMorgan Chase blocks outside AI agents from directly accessing customer accounts

    Weeks after the launch of Meta's Muse AI assistant, Jamie Dimon says JPMorgan Chase is not going to allow outside agents to directly access accounts on behalf of retail customers.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: Finextra
    Original article: https://www.finextra.com/newsarticle/48585/jpmorgan-chase-blocks-outside-ai-agents-from-directly-accessing-customer-accounts?utm_medium=rssfinextra&utm_source=finextrafeed

  • NatWest enlists Nvidia to help its AI spending tool understand regional accents

    NatWest enlists Nvidia to help its AI spending tool understand regional accents

    NatWest enlists Nvidia to help its AI spending tool understand regional accents

    NatWest has harnessed AI speech recognition technology from Nvidia to help its new audio-visual spending insights tool understand customers' accents and pronunciations.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: Finextra
    Original article: https://www.finextra.com/newsarticle/48586/natwest-enlists-nvidia-to-help-its-ai-spending-tool-understand-regional-accents?utm_medium=rssfinextra&utm_source=finextrafeed

  • Flock CEO says its microphones detect ‘just gunshots’ — its website says different

    Flock CEO says its microphones detect ‘just gunshots’ — its website says different

    Flock CEO says its microphones detect ‘just gunshots’ — its website says different

    Langley’s comments come amid mounting scrutiny of Flock from privacy advocates, including the ACLU, and members of the public who are concerned about the misuse of its technology.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: TechCrunch
    Original article: https://techcrunch.com/2026/10/14/flock-ceo-says-its-microphones-detect-just-gunshots-its-website-says-different/

  • IEEE Continues Preparations for the Realignment of Its Regions

    IEEE Continues Preparations for the Realignment of Its Regions

    IEEE Continues Preparations for the Realignment of Its Regions

    Progress continues in restructuring IEEE’s geographic regions, as outlined in The Institute’s February 2023 article “ IEEE Is Realigning Its Geographic Regions .” The “Region 1” designation will no longer be used. The new Region 2 will merge what is currently Region 1 (Northeastern U.S.) with the current Region 2 (Eastern U.S.). It will be called Region 2 (Northeastern and Eastern U.S.). The current Region 10 (Asia Pacific) will be divided into two separate regions. The new Region 10 will encompass North Asia, and the new Region 11 will cover South Asia and the Pacific. The restructuring is defined in the image of the redrawn map in this article. What’s underway Although the new regional alignment will not officially take place until 1 January 2028, several activities have begun within IEEE Member and Geographic Activities (MGA) and across other IEEE organizational units. Within MGA, volunteers and staff have been actively addressing system enhancements, director/director-elect elections , governance updates, communications, and regional finances and offerings. No changes to membership Work will continue from now until the effective date of realignment in 2028. The change will not affect your IEEE membership, nor will it change either your local IEEE section or chapter. If you have any questions regarding the realignment, contact Reg-Realignment@ieee.org .

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: IEEE Spectrum
    Original article: https://spectrum.ieee.org/realignment-ieee-regions

  • Apate sends AI agents undercover to get scammed so they can gather fraud intelligence

    Apate sends AI agents undercover to get scammed so they can gather fraud intelligence

    Apate sends AI agents undercover to get scammed so they can gather fraud intelligence

    Most companies use AI agents to ship products faster or speed up workflows. Apate.ai sends them undercover to get scammed.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: TechCrunch
    Original article: https://techcrunch.com/2026/10/14/apate-sends-ai-agents-undercover-to-get-scammed-so-they-can-gather-fraud-intelligence/