Knowledge catalogue
arXiv:2605.29710v1 Announce Type: new Abstract: Real-world evaluation of vision-language-action (VLA) policies still rests on binary success rate at a fixed timeout with N le 25 rollouts per condition
arXiv:2605.29486v1 Announce Type: cross Abstract: A central bottleneck for phone-use agents is that controllable, reproducible environments covering real mobile behavior are hard to build at scale. Ex
arXiv:2605.30353v1 Announce Type: new Abstract: Are AI agents tools, co-authors, or researchers? We present a quantified case study (N=1): a physicist supervising an AI coding agent (Claude Code, Sonn
pibot is now running fully local, using parakeet for STT, qwen3-tts for TTS, and Qwen 3.6 as the local multi-modal LLM via llama.cpp. The STT and TTS inference engines are Rust/mlx-c based. Ported fro
arXiv:2605.29563v1 Announce Type: new Abstract: Can VLMs predict how each camera move changes the view, and plan many such moves ahead? We call this capability view planning, requiring (1)understandin
arXiv:2605.29299v1 Announce Type: cross Abstract: Evaluations of dental vision-language models remain fragmented across datasets, task definitions and metrics, and often ignore their computational cos
arXiv:2605.30094v1 Announce Type: new Abstract: Poker is a landmark challenge for artificial intelligence. The dominant approach relies on equilibrium solvers built on counterfactual regret minimizati
arXiv:2605.29815v1 Announce Type: new Abstract: The growing number of submitted papers has motivated the exploration of Large Language Models (LLMs) as a means to support and augment the peer review p
arXiv:2605.28873v1 Announce Type: new Abstract: This is a planning-method note with an unpaired pilot audit. We adapt the classical paired-binary sample-size calculation (Miettinen, 1968) to quantizat
arXiv:2605.29631v1 Announce Type: cross Abstract: Randomized controlled trials are a cornerstone of medicine and the social sciences as they enable reliable estimates of causal effects. However, they
arXiv:2509.08194v2 Announce Type: replace Abstract: We address the problem of policy selection in contextual stochastic optimization (CSO), where covariates are available as contextual information and
arXiv:2602.10520v3 Announce Type: replace Abstract: Looped Language Models (LoopLMs) perform multi-step latent reasoning prior to token generation and outperform conventional LLMs on reasoning benchma
arXiv:2605.29172v1 Announce Type: new Abstract: Seasonal climate predictions support planning and risk management by offering early information of the most likely-to-occur climate conditions in the co
arXiv:2605.30284v1 Announce Type: new Abstract: Scientific discovery is an inherently creative and uncertain process, requiring reasoning beyond the recall of known knowledge. While many benchmarks ha
arXiv:2605.29653v1 Announce Type: new Abstract: Given a strategically complex board game, human players can quickly learn to devise strategies after playing a few rounds. Autonomous agents require sim
arXiv:2508.15180v3 Announce Type: replace Abstract: High-quality mathematical and logical datasets with verifiable answers are essential for strengthening the reasoning capabilities of large language
arXiv:2605.30280v1 Announce Type: cross Abstract: Embodied intelligence is often studied through specialized models for individual tasks such as manipulation or navigation, resulting in fragmented cap
arXiv:2605.30029v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) systems expose numerous design choices spanning query rewriting, chunking, retrieval depth, reranking, and context
arXiv:2605.29579v1 Announce Type: new Abstract: While multimodal large language models (MLLMs) have achieved rapid progress in vision-language understanding, they remain prone to multimodal hallucinat
arXiv:2605.29729v1 Announce Type: new Abstract: We introduce scheming honeypot evaluations, a framework for testing whether models will pursue instrumental goals if given the opportunity. Our scheming
arXiv:2605.29114v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models with integrated reasoning have been proposed for end-to-end autonomous driving, assuming a tight coupling between
arXiv:2602.00994v2 Announce Type: replace Abstract: Agentic Reinforcement Learning (ARL) trains large language models to interleave reasoning with external tool execution to solve complex tasks. Most
arXiv:2605.29327v1 Announce Type: new Abstract: Efficient Distillation (EDistill) compresses large language models (LLMs) by structured pruning parameters and tuning lightweight modules with high trai
arXiv:2603.05488v4 Announce Type: replace-cross Abstract: We provide evidence of performative chain-of-thought (CoT) in reasoning models, where a model becomes strongly confident in its final answer,
arXiv:2605.29192v1 Announce Type: new Abstract: Chain-of-thought traces from large reasoning models can span tens of thousands of tokens, yet we lack a vocabulary for describing their internal structu
arXiv:2605.30021v1 Announce Type: new Abstract: Many open-ended instructions have multiple valid answers that users can benefit from seeing, but post-training often narrows an LLM's output space towar
arXiv:2605.29893v1 Announce Type: new Abstract: LLM-based agents have demonstrated strong capabilities in solving complex tasks through multi-step reasoning and tool use. However, existing evaluation
arXiv:2605.29634v1 Announce Type: new Abstract: Transformer hidden states are often interpreted through local or low-order objects: neurons, sparse features, attention heads, residual-stream direction
arXiv:2605.29224v1 Announce Type: cross Abstract: AI agents augment large language models with external tools such as web retrieval, enabling grounded and up-to-date responses. However, incorporating
arXiv:2605.30052v1 Announce Type: cross Abstract: One-shot Program-of-Thought (PoT) emits a Python program that prints a primitive-action plan; a single invalid action silently invalidates the traject
arXiv:2601.21564v2 Announce Type: replace Abstract: Machine unlearning seeks to remove the influence of specific training data from a model, a need driven by privacy regulations and robustness concern
arXiv:2605.29234v1 Announce Type: new Abstract: We study large-scale literature search from two complementary angles: improving the retrieval pipeline, and stress-testing the human reference list as a
arXiv:2605.29401v1 Announce Type: new Abstract: Time-Series Foundation Models (TSFMs) excel at zero-shot unimodal forecasting using numerical data, but unlike LLMs they cannot consume multimodal, non-
arXiv:2605.29028v1 Announce Type: cross Abstract: Conditioned Sequence Models (CSMs) learn policies by treating return-to-go (RTG) as a control signal. However, existing CSMs often treat the RTGs as s
arXiv:2603.27758v2 Announce Type: replace Abstract: Metric Cross-View Geo-Localization (MCVGL) aims to estimate the 3-DoF camera pose (position and heading) by matching ground and satellite images. In
arXiv:2605.28827v1 Announce Type: new Abstract: Open Arabic large language models split into two classes: sub-1B multilingual models that treat Arabic as an afterthought (Qwen2.5-0.5B, Falcon-H1-0.5B)
arXiv:2509.05771v2 Announce Type: replace-cross Abstract: We develop a new classification framework based on the theory of coherent risk measures and systemic risk. The proposed approach is suitable f
arXiv:2605.30326v1 Announce Type: cross Abstract: The ability to reason, adapt, and creatively solve problems under unexpected challenges is essential for robots operating in real-world environments.
arXiv:2605.29068v1 Announce Type: new Abstract: Maintaining the safety of large language models (LLMs) is crucial as they are increasingly deployed in real-world applications. Existing safety guardrai
arXiv:2602.11065v2 Announce Type: replace-cross Abstract: Human conversation is organized by an implicit chain of thought and manifests as temporally structured conversational behaviors. Capturing thi
arXiv:2605.29796v1 Announce Type: new Abstract: Agentic search enables LLMs to solve complex multi-hop questions through iterative reasoning and external search. Despite the effectiveness, these syste
arXiv:2509.23694v5 Announce Type: replace Abstract: Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information. However, this also introduces a new thr
arXiv:2507.09266v2 Announce Type: replace Abstract: Gloss-free Sign Language Translation (SLT) has advanced rapidly, achieving strong performances without relying on gloss annotations. However, these
Salesforce published a detailed writeup on going agentic with Claude Code. A couple things jumped out. A migration they'd scoped at 231 days shipped in 13. One PR delivered 21 endpoints at 100% test c
arXiv:2605.29084v1 Announce Type: cross Abstract: A retrieval-augmented generation (RAG) system deployed over a multi-author institutional corpus can give a different answer to the same question depen
arXiv:2605.30056v1 Announce Type: cross Abstract: Recent advances in reinforcement learning (RL) have achieved great successes by leveraging the multimodality and exploration capability of diffusion p
arXiv:2605.29682v1 Announce Type: new Abstract: Agent harnesses increasingly determine the performance of language-model systems by deciding how models call tools, receive feedback, verify intermediat
arXiv:2605.29358v1 Announce Type: new Abstract: We demonstrate that sparse autoencoders can extract interpretable features from Claude 3 Sonnet, a production-scale language model, addressing the open
arXiv:2605.29059v1 Announce Type: cross Abstract: Smart contract decompilation aims to recover high-level source code from bytecode, but evaluating decompilers remains difficult because existing studi
arXiv:2605.29468v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to support scientific work, but it is unclear whether they uphold responsible conduct of research (
arXiv:2512.15374v2 Announce Type: replace Abstract: Large Language Model (LLM) agents are increasingly deployed in environments that generate massive, dynamic contexts. However, a critical bottleneck
arXiv:2603.12588v2 Announce Type: replace Abstract: Cross-modal ship re-identification (ReID) between optical and synthetic aperture radar (SAR) imagery is fundamentally challenged by the severe radio
arXiv:2605.29916v1 Announce Type: cross Abstract: The Random Gradient hyper-heuristic was recently shown to be able to learn the optimal neighbourhood size when optimizing the LeadingOnes benchmark vi
arXiv:2605.30087v1 Announce Type: new Abstract: Emerging personal AI agents are moving toward persistent, multi-source memory. This creates an evaluation problem: systems must decide how to use confli
arXiv:2605.29402v1 Announce Type: cross Abstract: Understanding long-form egocentric videos remains challenging for multimodal large language models (MLLMs) due to limited context length and insuffici
arXiv:2605.28909v1 Announce Type: new Abstract: We develop a comprehensive mathematical and computational framework for sequential surrogate modeling of three-phase black-oil reservoir dynamics using
arXiv:2605.28837v1 Announce Type: cross Abstract: While Large Language Models (LLMs) have demonstrated remarkable capabilities, their reliability is significantly compromised by hallucinations. Existi
arXiv:2602.01869v3 Announce Type: replace Abstract: LLM-driven agents excel at sequential decision-making but often rely on on-the-fly reasoning, re-deriving solutions even in recurring scenarios. Thi
arXiv:2605.29794v1 Announce Type: new Abstract: LLM agents now draw on growing skill libraries to handle complex tasks. However, injecting more skills does not always improve task completion and can e
arXiv:2605.29726v1 Announce Type: new Abstract: In the context of resource-constrained environments such as embedded systems, adapting reduced-size foundation models to downstream tasks has become inc