Large language models are evolving from single-turn responders into tool-using agents capable of sustained reasoning and decision-making for deep research. Prevailing systems adopt a linear pipeline of plan to search to write to a report, which suffers from error accumulation and context rot due to the lack of explicit control over both model behavior and context. We introduce RhinoInsight, a deep research framework that adds two control mechanisms to enhance robustness, traceability, and overall quality without parameter updates. First, a Verifiable Checklist module transforms user requirements into traceable and verifiable sub-goals, incorporates human or LLM critics for refinement, and compiles a hierarchical outline to anchor subsequent actions and prevent non-executable planning. Second, an Evidence Audit module structures search content, iteratively updates the outline, and prunes noisy context, while a critic ranks and binds high-quality evidence to drafted content to ensure verifiability and reduce hallucinations. Our experiments demonstrate that RhinoInsight achieves state-of-the-art performance on deep research tasks while remaining competitive on deep search tasks.

We present OpenGloss, a synthetic encyclopedic dictionary and semantic knowledge graph for English that integrates lexicographic definitions, encyclopedic context, etymological histories, and semantic relationships in a unified resource. OpenGloss contains 537K senses across 150K lexemes, on par with WordNet 3.1 and Open English WordNet, while providing more than four times as many sense definitions. These lexemes include 9.1M semantic edges, 1M usage examples, 3M collocations, and 60M words of encyclopedic content. Generated through a multi-agent procedural generation pipeline with schema-validated LLM outputs and automated quality assurance, the entire resource was produced in under one week for under $1,000. This demonstrates that structured generation can create comprehensive lexical resources at cost and time scales impractical for manual curation, enabling rapid iteration as foundation models improve. The resource addresses gaps in pedagogical applications by providing integrated content -- definitions, examples, collocations, encyclopedias, etymology -- that supports both vocabulary learning and natural language processing tasks. As a synthetically generated resource, OpenGloss reflects both the capabilities and limitations of current foundation models. The dataset is publicly available on Hugging Face under CC-BY 4.0, enabling researchers and educators to build upon and adapt this resource.

We show that when large language models learn to reward hack on production RL environments, this can result in egregious emergent misalignment. We start with a pretrained model, impart knowledge of reward hacking strategies via synthetic document finetuning or prompting, and train on a selection of real Anthropic production coding environments. Unsurprisingly, the model learns to reward hack. Surprisingly, the model generalizes to alignment faking, cooperation with malicious actors, reasoning about malicious goals, and attempting sabotage when used with Claude Code, including in the codebase for this paper. Applying RLHF safety training using standard chat-like prompts results in aligned behavior on chat-like evaluations, but misalignment persists on agentic tasks. Three mitigations are effective: (i) preventing the model from reward hacking; (ii) increasing the diversity of RLHF safety training; and (iii) "inoculation prompting", wherein framing reward hacking as acceptable behavior during training removes misaligned generalization even when reward hacking is learned.

Large Language Models (LLMs) demonstrate partial forecasting competence across social, political, and economic events. Y et, their predictive ability varies sharply with domain structure and prompt framing. We investigate how forecasting performance varies with different model families on real-world questions about events that happened beyond the model cutoff date. We analyze how context, question type, and external knowledge affect accuracy and calibration, and how adding factual news context modifies belief formation and failure modes. Our results show that forecasting ability is highly variable as it depends on what, and how, we ask.

Recent advancements in Retrieval-Augmented Generation (RAG) have enabled Large Language Models to answer financial questions using external knowledge bases of U.S. SEC filings, earnings reports, and regulatory documents. However, existing work lacks systematic comparison of vector-based and non-vector RAG architectures for financial documents, and the empirical impact of advanced RAG techniques on retrieval accuracy, answer quality, latency, and cost remain unclear. We present the first systematic evaluation comparing vector-based agentic RAG using hybrid search and metadata filtering against hierarchical node-based systems that traverse document structure without embeddings. We evaluate two enhancement techniques applied to the vector-based architecture, i) cross-encoder reranking for retrieval precision, and ii) small-to-big chunk retrieval for context completeness. Across 1,200 SEC 10-K, 10-Q, and 8-K filings on a 150-question benchmark, we measure retrieval metrics (MRR, Recall@5), answer quality through LLM-as-a-judge pairwise comparisons, latency, and preprocessing costs. Vector-based agentic RAG achieves a 68% win rate over hierarchical node-based systems with comparable latency (5.2 compared to 5.98 seconds). Cross-encoder reranking achieves a 59% absolute improvement at optimal parameters (10, 5) for MRR@5. Small-to-big retrieval achieves a 65% win rate over baseline chunking with only 0.2 seconds additional latency. Our findings reveal that applying advanced RAG techniques to financial Q&A systems improves retrieval accuracy, answer quality, and has cost-performance tradeoffs to be considered in production.

The capacity for highly complex, evidence-based, and strategically adaptive persuasion remains a formidable great challenge for artificial intelligence. Previous work, like IBM Project Debater, focused on generating persuasive speeches in simplified and shortened debate formats intended for relatively lay audiences. We introduce DeepDebater, a novel autonomous system capable of participating in and winning a full, unmodified, two-team competitive policy debate. Our system employs a hierarchical architecture of specialized multi-agent workflows, where teams of LLM-powered agents collaborate and critique one another to perform discrete argumentative tasks. Each workflow utilizes iterative retrieval, synthesis, and self-correction using a massive corpus of policy debate evidence (OpenDebateEvidence) and produces complete speech transcripts, cross-examinations, and rebuttals. We introduce a live, interactive end-to-end presentation pipeline that renders debates with AI speech and animation: transcripts are surface-realized and synthesized to audio with OpenAI TTS, and then displayed as talking-head portrait videos with EchoMimic V1. Beyond fully autonomous matches (AI vs AI), DeepDebater supports hybrid human-AI operation: human debaters can intervene at any stage, and humans can optionally serve as opponents against AI in any speech, allowing AI-human and AI-AI rounds. In preliminary evaluations against human-authored cases, DeepDebater produces qualitatively superior argumentative components and consistently wins simulated rounds as adjudicated by an independent autonomous judge. Expert human debate coaches also prefer the arguments, evidence, and cases constructed by DeepDebater. We open source all code, generated speech transcripts, audio and talking head video here: https://github.com/Hellisotherpeople/DeepDebater/tree/main

By automating knowledge discovery, boosting hypothesis creation, integrating transdisciplinary insights, and enabling coope ration within innovation ecosystems, LLMs dramatically improve the efficiency and effectiveness of research processes. Through extensive analysis of scientific literature, patent databases, and experimental data, these models enable more flexible and infor med R&D workflows, ultimately accelerating innovation cycles and lowering time - to - market for breakthrough ideas.

Many sequential decision settings in healthcare feature funnel structures characterized by a series of stages, such as screenings or evaluations, where the number of patients who advance to each stage progressively decreases and decisions become increasingly costly. For example, an oncologist may first conduct a breast exam, followed by a mammogram for patients with concerning exams, followed by a biopsy for patients with concerning mammograms. A key challenge is that the ground truth outcome, such as the biopsy result, is only revealed at the end of this funnel. The selective censoring of the ground truth can introduce statistical biases in risk estimation, especially in underserved patient groups, whose outcomes are more frequently censored. We develop a Bayesian model for funnel decision structures, drawing from prior work on selective labels and censoring. We first show in synthetic settings that our model is able to recover the true parameters and predict outcomes for censored patients more accurately than baselines. We then apply our model to a dataset of emergency department visits, where in-hospital mortality is observed only for those who are admitted to either the hospital or ICU. We find that there are gender-based differences in hospital and ICU admissions. In particular, our model estimates that the mortality risk threshold to admit women to the ICU is higher for women (5.1%) than for men (4.5%).

Machine unlearning, which selectively removes harmful knowledge from a pre-trained model without retraining from scratch, is crucial for addressing privacy, regulatory compliance, and ethical concerns in Large Language Models (LLMs). However, existing unlearning methods often struggle to thoroughly remove harmful knowledge, leaving residual harmful knowledge that can be easily recovered. To address these limitations, we propose Knowledge Density-Guided Unlearning via Blocks Reinsertion (KUnBR), a novel approach that first identifies layers with rich harmful knowledge and then thoroughly eliminates the harmful knowledge via re-insertion strategy. Our method introduces knowledge density estimation to quantify and locate layers containing the most harmful knowledge, enabling precise unlearning. Additionally, we design a layer re-insertion strategy that extracts and re-inserts harmful knowledge-rich layers into the original LLM, bypassing gradient obstruction caused by cover layers and ensuring effective gradient propagation during unlearning. Extensive experiments conducted on several unlearning and general capability benchmarks demonstrate that KUnBR achieves state-of-the-art forgetting performance while maintaining model utility.

The internet has become the main source of data to train modern text-to-image or vision-language models, yet it is increasingly unclear whether web-scale data collection practices for training AI systems adequately respect data owners' wishes. Ignoring the owner's indication of consent around data usage not only raises ethical concerns but also has recently been elevated into lawsuits around copyright infringement cases. In this work, we aim to reveal information about data owners' consent to AI scraping and training, and study how it's expressed in DataComp, a popular dataset of 12.8 billion text-image pairs. We examine both the sample-level information, including the copyright notice, watermarking, and metadata, and the web-domain-level information, such as a site's Terms of Service (ToS) and Robots Exclusion Protocol. We estimate at least 122M of samples exhibit some indication of copyright notice in CommonPool, and find that 60\% of the samples in the top 50 domains come from websites with ToS that prohibit scraping. Furthermore, we estimate 9-13\% with 95\% confidence interval of samples from CommonPool to contain watermarks, where existing watermark detection methods fail to capture them in high fidelity. Our holistic methods and findings show that data owners rely on various channels to convey data consent, of which current AI data collection pipelines do not entirely respect. These findings highlight the limitations of the current dataset curation/release practice and the need for a unified data consent framework taking AI purposes into consideration.