Skip to content
AI NEWS JOURNAL
AI, IN PERSPECTIVE

Search AI news

Search headlines, summaries and articles to connect the dots.

Newest first

CiteAnchor: Source-Aware Grounding for Hallucinated Citation Detection and Resolution

arXiv:2610.30355v1 Announce Type: new Abstract: Hallucinated citations make it harder to trace sources and verify the evidence behind scientific claims. Detecting them is difficult because bibliographic records can be incomplete or differ across source types and publication versions. A plausible match alone neither validates the citation nor establishes its underlying source. We introduce CiteResolve, a benchmark of 423 real-world hallucinated citations annotated for source recoverability. We further propose CiteAnchor, a source-aware grounding framework that adapts retrieval and field-level verification to each source type and separately determines citation validity and whether a unique source can be recovered. On an existing detection benchmark, CiteAnchor achieves 0.841 F1 with GPT-5.6

CiteAnchor: Source-Aware Grounding for Hallucinated Citation Detection and Resolution
Timeline and related coverage

The study proposes a new metric, RCG, to assess the coverage of synthetic survey respondents generated by LLMs.

The paper, published on October 24, 2026, on arXiv (ID 2610.30900v1), introduces a new evaluation metric called “Respondent Coverage Gap” (RCG) to assess the extent to which synthetic survey respondents generated by large language models (LLMs) cover the full response-profile space of real human respondents.

Silicon Samples Match the Answers but Not the Respondents

Why it matters:Existing evaluation methods focus solely on the distribution of individual item responses or inter-item correlations, failing to detect whether LLM-generated responses replicate answer combinations that actually exist in the real population. RCG is the first to quantify coverage gaps by analyzing the full response profile, and empirical evidence from two U.S. social survey datasets reveals that all tested LLMs exhibit significant undercoverage of certain population groups, performing worse than both a simple marginal sampling baseline and a Gaussian copula model.

Timeline and related coverage

New research introduces the ReflectPO framework, enhancing the autonomous error-correction capabilities of large language model agents in long-term tasks.

On October 24, 2026, arXiv published a research paper titled “ReflectPO: Reflection-Guided Policy Optimization for Long-Horizon LLM Agents” (ID 2610.30933v1), introducing a reinforcement learning framework called ReflectPO, designed to enhance the autonomous error-recovery capabilities of tool-augmented large language model agents in complex, multi-step, state-dependent tasks.

ReflectPO: Reflection-Guided Policy Optimization for Long-Horizon LLM Agents

Why it matters:This paper is a cutting-edge AI study recently published, focusing on a key bottleneck in the real-world deployment of LLM-based agents: the cumulative effect of early errors in long‑term tasks. Its proposed dual-component design—Reflection‑Guided Sampling and Tree‑Structured Credit Assignment—features methodological innovation and empirically outperforms multiple baselines across two benchmarking scenarios, making it a valuable technical reference.

Timeline and related coverage

Learning What to Ask for Tomorrow: Active Preference Acquisition for Long-Term Personalized Web Agents

arXiv:2610.31107v1 Announce Type: new Abstract: Web agents increasingly serve the same user across repeated online tasks such as booking travel, shopping, and scheduling, so their long-term usefulness depends on how well they know the user's preferences. Passive memory and personalization methods cannot obtain preferences the user never reveals, and clarification methods that value a question by its benefit to the current task overlook the benefit of reusing the answer in later tasks. We study Active Preference Acquisition (APA): which missing preferences are worth the cost of asking? We define the Prospective Personalization Value (PPV) of a missing preference as its expected cumulative utility gain over future tasks minus the effort and disclosure-risk cost of asking, and select question

Learning What to Ask for Tomorrow: Active Preference Acquisition for Long-Term Personalized Web Agents
Timeline and related coverage

Introducing Kimi K3.1 Pro

Introducing Kimi K3.1 Pro Kimi K3.1 Pro landed on the Kimi API today - it's not yet open weights, but Moonshot promise "Full model weights will be released by Nov 4, 2026". They're also offering a "Highspeed" version that's 2-3x faster, at twice the price (except for input token cache hits, which are priced the same). The US dollar pricing is $2.00/million tokens for input and $10/million for output - the same as GPT-6.1 Sol and half the price of Claude Opus 5.5. Moonshot's own benchmarks show Kimi as approximately level with Opus 5.5 and GPT-6 Astra - beating them on a few benchmarks, coming close on others. Artificial Analysis scored Kimi at 55 - ahead of Claude Fable 5.1, GPT-6 Astra, and Gemini 4 Argon (all at 53) and behind only Claude Opus 5.5 (58). This is the first time a (soon-to-

Timeline and related coverage

Amazon SageMaker AI has launched a Multi-Step Reinforcement Learning (MTRL) framework, supporting end-to-end training of agents to accomplish multi-step tasks.

AWS has launched the Multi-Turn Reinforcement Learning (MTRL) feature, enabling users to train large‑model agents on SageMaker AI using full task trajectories and final outcome feedback, without requiring step‑level annotations. A end-to-end demonstration is provided using Wordle as an example, covering AgentCore deployment, data preparation, GRPO training, reward design, and cost analysis.

Timeline and related coverage

AWS CDK builds reusable constructs to resolve the blocking issue during SageMaker endpoint scaling updates.

When a SageMaker real-time AI endpoint has Application Auto Scaling enabled, attempting to update its configuration—such as instance type or count—directly via AWS CDK or CloudFormation will fail. This paper proposes a CDK construct based on custom resources that leverages strict dependency orchestration to achieve atomic updates of both the endpoint’s configuration and its scaling policies, eliminating the need for manual intervention.

Timeline and related coverage

Amazon SageMaker launches the Training Session API: users can write custom training loops for large models without managing GPUs.

Amazon SageMaker has released the Training Sessions API, enabling users to implement custom large-model training workflows—such as SFT, RLHF, GRPO, and KTO—using pure Python scripts. GPU resource scheduling, fault tolerance, distributed execution, and checkpoint management are all handled by the service.

Timeline and related coverage

Switch 2 exploited by old games and AI to achieve jailbreaking; a modder showcases a custom character for “Mario Kart World”

According to The Verge, well-known modder Sammy Hajhamid (online alias pepsipu) claims to have successfully jailbroken the Nintendo Switch 2. His tool, ‘ns2jb,’ was developed with assistance from OpenAI Codex and exploited a vulnerability triggered by an older game. A demonstration video shows “Mario Kart World” running a modified version that includes unofficial characters such as Cinnamoroll, the red Angry Birds, Peter Griffin, and Minecraft’s Steve.

Timeline and related coverage

Several European institutions have deployed the NVIDIA Earth-2 open-source model to advance localized weather and climate prediction applications.

NVIDIA has released the Earth-2 open-source AI model family for Europe, including the region-specific nowcasting model StormScope EU, and is collaborating with organizations such as AXA, Vaisala Xweather, the University of Manchester, and TotalEnergies to conduct real-world validation, covering tasks like storm risk assessment, air quality modeling, solar power generation forecasting, and radar terrain inversion.

Timeline and related coverage

Walmart launches an AI-powered shopping gateway, supporting autonomous shopping workflows and enhancing user control.

Walmart has officially launched Agent Gateway (an AI agent gateway) along with its accompanying Agent Profiles feature, enabling authorized AI agents—such as ChatGPT, Gemini, Meta Muse, and others—to perform searches and place orders on behalf of users across Walmart and Sam’s Club platforms. User control over agent activities is ensured through mechanisms like independent account configuration, transaction approvals, and spending limits. This move stands in stark contrast to Amazon’s recent ban on AI‑powered shopping agents.

Timeline and related coverage

Pixels to Tokens: Token Space Efficient Active Learning for Low-Budget Semantic Segmentation

While foundation models and vision transformers (ViTs) have redefined visual representations, current active learning (AL) strategies for these backbones largely operate at the patch or region level, where annotation requirements remain high due to extensive pixel labeling. Extending ViT-based AL to the pixel-level, low-budget regime is uniquely challenging: with as little as one pixel query per image, a method must simultaneously identify the most informative locations and train a reliable decoder head from an extremely sparse signal. We introduce TEAL (Token-space Efficient Active Learning)…

AWS releases a technical preview: Amazon Quick and Bedrock AgentCore enable the construction of governable, conversational supply chain intelligence systems.

AWS has launched a modular agent architecture based on the Model Context Protocol (MCP), leveraging AgentCore to standardize enterprise‑level tool interfaces. Amazon Quick provides a natural‑language interaction interface for business users, enabling real‑time, approval‑driven supply chain decision support across ERP, procurement, monitoring, and other systems. This solution is currently in technical preview and is not guaranteed to be production‑ready or available for customer deployment.

Timeline and related coverage

Postgres wait events, now in Query Insights

Query Insights for ClickHouse Managed Postgres now shows what active sessions are waiting on, with wait event breakdowns, blocked-session and lock-wait charts, and the same metrics in Prometheus.