DataBubble·

AI Intelligence Feed

68,685 articles

Filters69k

arxiv6h ago

Bringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning

Credit assignment is a central challenge in reinforcement learning (RL). Classical actor-critic methods address this challenge through fine-grained advantage estimation based on a learned value function. However, learned value models are ofte

Read on arxiv →

arxiv6h ago

Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks

How can language model agents effectively leverage libraries of reusable knowledge to solve long-horizon tasks? Recent work has increasingly focused on agent skills: reusable capabilities represented as skill packages, i.e., multi-file bundles containi

Read on arxiv →

arxiv6h ago

Distribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts

Mixture-of-Experts (MoE) architectures have emerged as a powerful paradigm for scaling model capacity while preserving efficient inference in large foundation models. However, most MoE models use a fixed top-$k$ expert selection policy, assigning the

Read on arxiv →

arxiv6h ago

In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning

Retrieval-augmented generation (RAG) grounds a language model in retrieved documents, which reduces hallucination but creates a new attack surface: if retrieved text is tampered with, the model may repeat the falsehood. We study how much a small quan

Read on arxiv →

arxiv6h ago

FrontierChallenge: Evaluating Scientific Workflow Completion

Scientific agents increasingly analyze data, execute code, and produce research artifacts, yet most benchmarks emphasize final answers, isolated programs, or a single domain. We introduce FrontierChallenge, a cross-domain benchmark comprising 300 e

Read on arxiv →

arxiv6h ago

IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model Identifier

Enterprises deploy systems, not checkpoints. Usable capability depends jointly on weights, serving route, precision, output contract, and harness, yet all 18 audited benchmarks score advertised model identifiers. We treat this as measurement error an

Read on arxiv →

arxiv6h ago

AgenticGen: Reward-Guided Agentic Video Generation for Advertising

Advertising video generation is not only a video synthesis task, but also a product-conditioned reasoning problem whose success is measured by online business metrics. Recent video foundation models can generate realistic clips from multimodal condit

Read on arxiv →

arxiv6h ago

Strangers to Themselves: What Language Models Say About Themselves Is Generic

Language models can fluently describe how they would behave: whether they would cave to pushback, misuse a tool, or lie under pressure. Is that description actually about the model speaking? We turn self-knowledge into a prediction test. Across nine

Read on arxiv →

arxiv6h ago

Omni Interaction Agent Technical Report

In this work, we present Gander, an end-to-end model that unifies omni perception, realtime interaction, and agentic capabilities within a single framework. In contrast to turn-based conventional paradigms, Gander continuously receives stream

Read on arxiv →

arxiv6h ago

CoGReV: A Confidence-Gated Post-Hoc Non-Monotonic Belief Revision Framework for Phishing Website Classification

In phishing detection, machine learning classifiers act as a first line of defense, but the false positives they produce are triaged by human analysts. The excessive false alarms cause alert fatigue that erodes human oversight. We propose CoGReV, a

Read on arxiv →

arxiv6h ago

Bit-Flip Attacks on Vision-Language-Action Models: Action-Decoding Architecture Shapes the Vulnerability

Quantized Vision-Language-Action (VLA) models expose a weight-fault surface: Rowhammer-style faults can corrupt deployed INT8 bits. We present the first bit-flip attack on a VLA: a few gradient-selected flips reduce closed-loop success to $0\

Read on arxiv →

arxiv6h ago

Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization

The growing complexity of content moderation policies presents a critical challenge for their consistent operationalization. While foundation models possess the basic capabilities needed to confront this challenge, whether they can reliably moderate

Read on arxiv →

arxiv6h ago

RiLM: Parameter-Efficient Language Modeling via Geodesic Decoding

Language models under one million parameters matter for edge deployment, domain adaptation, and reproducible research, yet a two-layer LSTM or Transformer at embedding width d = 128 still spends roughly one third of its capacity on the output matrix

Read on arxiv →

arxiv6h ago

Tracing Computation Density in LLMs

Transformer-based large language models (LLMs) are comprised of billions of parameters arranged in deep and wide computational graphs, but it is not clear that they exploit their full capacity for all inputs. We introduce the s-Trace method t

Read on arxiv →

arxiv6h ago

Cultural Binding Heads in Language Models

LLMs often default to equal treatment across cultural groups, even though context warrants differentiation: this is a lack of difference awareness. Using mechanistic interpretability and a factorial design on the N4 cultural appropriation benchmark

Read on arxiv →

arxiv6h ago

Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training

LLM agents for sequential decision tasks are often post-trained with trajectory-level outcome labels, but such labels provide little supervision for preserving multiple successful branches from the same decision state. We study this problem as succes

Read on arxiv →

arxiv6h ago

Left-Branching Transformers Excel at Right-Branching Languages: Data Shapes Word Order Preferences in Language Models

We systematically compare word order preferences in decoder-only language models across 192 artificial languages and typologically diverse natural languages. On artificial languages, models exhibit a left-branching preference that aligns with

Read on arxiv →

arxiv6h ago

Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning

Palmyra x6 is a large language model optimized for use with enterprise-oriented agentic tasks. The model was built by post-training a Mixture-of-Experts base model with Anchored Supervised Fine-Tuning on a compact corpus of verified, syntheti

Read on arxiv →

arxiv6h ago

'Ghaib in Translation' aka Unseen Harm: Measuring Cross-Script Safety Inconsistency with 'Missed-in-Urdu' Scores in LLM Hate Speech Detection

Urdu, the world's tenth most spoken language with 246 million speakers, remains almost entirely absent from mainstream LLM safety evaluation and nine years of WOAH proceedings. To investigate whether this absence has measurable consequences f

Read on arxiv →

arxiv6h ago

DexterSQL: Deep Schema Exploration and Rule-based Correction for Text-to-SQL Generation

Prompting-based (i.e., non-fine-tuning) Text-to-SQL methods, where underlying large language model parameters are not changed for the task, face three problems: (i) relying on coarse-grained schema information that may not reveal the fine-gra

Read on arxiv →