arXiv AI
Jul 1
Emergent Culture in Minimal LLM Systems
arXiv:2606. 30668v1 Announce Type: cross Abstract: What happens when LLM agents operate with no context outside a turn, minimal prompting, and simple tools?
Large language models
Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv Machine Learning
Jul 1
Multipole Semantic Attention: A Fast Approximation of Softmax Attention for Pretraining
arXiv:2509. 10406v4 Announce Type: replace Abstract: Pretraining transformers on long sequences (entire code repositories, collections of related documents) is bottlenecked by quadratic attention costs.
arXiv AI
Jul 1
RigorBench: Benchmarking Engineering Process Discipline in Autonomous AI Coding Agents
arXiv:2606. 22678v2 Announce Type: replace-cross Abstract: Agentic coding harnesses - such as Agent-Skills, Superpowers, and Agent-Rigor - are increasingly deployed to augment underlying LLMs for real-world software engineering tasks.
arXiv AI
Jul 1
Visual Semantic Entropy: Do Vision Language Models Recognize Visual Ambiguity?
arXiv:2606. 31407v1 Announce Type: cross Abstract: Vision-language models can produce confident answers on visually ambiguous inputs, resulting in biased predictions.
arXiv AI
Jul 1
ShopX: A Foundation Model for Intent-to-Item Fulfillment in Agentic Shopping
arXiv:2606. 31693v1 Announce Type: cross Abstract: The wave of AI-native applications is moving shopping beyond page- and feed-based browsing toward intent-driven experiences orchestrated by LLM agents.
arXiv Machine Learning
Jul 1
Surrogate Fidelity: When Can Open LLMs Explain Closed Ones?
arXiv:2606. 32008v1 Announce Type: new Abstract: Mechanistic interpretability (MI) requires full access to model internals, yet the APIs for most widely deployed language models at best expose log-probabilities over output tokens.
arXiv AI
Jul 1
CHERRY: Compressed Hierarchical Experts with Recurrent Representational Yield
arXiv:2606. 31796v1 Announce Type: cross Abstract: We study three complementary techniques for training compute-efficient language models.
arXiv AI
Jul 1
CoReLIN: Constraint-based Reasoning for Zero-shot Lifelong Interactive Navigation
arXiv:2602. 20055v2 Announce Type: replace-cross Abstract: Robot navigation typically assumes an obstacle-free path exists between start and goal.
arXiv AI
Jul 1
Seeing Through Multiple Views: Parameter-Efficient Fine-Tuning via Selective Neurons for Consistent Radiology Report Generation
arXiv:2606. 31099v1 Announce Type: cross Abstract: Recent years have seen substantial advances in radiology report generation (RRG), yet existing approaches predominantly adopt direct feature fusion when handling multi-view X-ray images.
arXiv AI
Jul 1
AxDafny: Agentic Verified Code Generation in Dafny
arXiv:2606. 32007v1 Announce Type: new Abstract: We study agentic code generation in Dafny, where a model must generate both executable code and the proof artifacts for verification.
arXiv AI
Jul 1
PPT-Eval: A Benchmark for Computer-Use Agents on PowerPoint Tasks
arXiv:2606. 31154v1 Announce Type: cross Abstract: Creating and editing slides is a rich, multimodal activity that is ubiquitous in professional and educational settings, making it an ideal testbed for real-world computer-use agents.
arXiv AI
Jul 1
Calibrating the Evaluator: Does Probability Calibration Mitigate Preference Coupling in LLM Agent Feedback Loops?
arXiv:2606. 31371v1 Announce Type: cross Abstract: When large language model (LLM) agents adapt their behavior through evaluator feedback, systematic evaluator biases propagate into the agent's learned strategy distribution - a phenomenon termed evaluator preference coupling.
arXiv Machine Learning
Jul 1
Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers
arXiv:2606. 31779v1 Announce Type: new Abstract: Language models typically reason via explicit chain-of-thought (CoT), generating intermediate steps token-by-token.
arXiv AI
Jul 1
When Reranking Hurts: Uncertainty-Based Gating for Few-Shot Reranking
arXiv:2606. 31087v1 Announce Type: cross Abstract: Few-shot selection typically assumes that reranking retrieved examples always improves performance.
arXiv AI
Jul 1
Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
arXiv:2606. 31184v1 Announce Type: cross Abstract: Adaptive experiments for average treatment effects (ATE) require randomized allocations balancing valid inference with statistical efficiency.
arXiv AI
Jul 1
DPPE: Rethinking Camera-Based Positional Encoding for Scaling Multi-View Transformers
arXiv:2606. 31585v1 Announce Type: cross Abstract: The remarkable scalability of Transformers has expanded their application to 3D computer vision, where camera-aware positional encoding is crucial for providing spatial cues in multi-view geometry.
arXiv Machine Learning
Jul 1
CoMet: Context and Multiplicity Decomposition for Multimodal Uncertainty Estimation
arXiv:2606. 32012v1 Announce Type: new Abstract: Uncertainty estimation has been a long-standing challenge in AI models; it amounts to "knowing what you don't know," and metacognition is notoriously difficult even for humans (cf.
arXiv AI
Jul 1
Protein contacts are already in the attention: a single-forward-pass alternative to the Categorical Jacobian
arXiv:2606. 21876v2 Announce Type: replace-cross Abstract: The Categorical Jacobian of Zhang et al.
arXiv AI
Jul 1
The Geometry of Refusal: Linear Instability in Safety-Aligned LLMs
arXiv:2606. 22686v2 Announce Type: replace-cross Abstract: Modern Large Language Models (LLMs) rely on extensive safety alignment, yet the mechanistic basis of refusal remains opaque.
arXiv AI
Jul 1
RARE: Redundancy-Aware Retrieval Evaluation Framework for High-Similarity Corpora
arXiv:2604. 19047v2 Announce Type: replace-cross Abstract: Existing QA benchmarks typically assume distinct documents with minimal overlap, yet real-world retrieval-augmented generation (RAG) systems operate on corpora such as financial reports, legal codes, and patents, where information is highly redundant and documents exhibit strong inter-document similarity.