Chaining Skills to Hijack LLM Agents
arXiv:2610.01564v1 Announce Type: cross Abstract: LLM agents use skills to improve performance on specialized tasks. To complete a user request, an agent may invoke several skills in sequence, allowin
Knowledge catalogue
arXiv:2610.01564v1 Announce Type: cross Abstract: LLM agents use skills to improve performance on specialized tasks. To complete a user request, an agent may invoke several skills in sequence, allowin
arXiv:2610.00431v1 Announce Type: cross Abstract: Continual parameter-efficient fine-tuning for large language models (LLMs) must balance retention of previously acquired knowledge, adaptation to new
arXiv:2610.00047v1 Announce Type: new Abstract: Diversity collapse in parallel chain-of-thought has motivated inference-time interventions built on a natural design: when a process reward model (PRM)
arXiv:2606.15396v2 Announce Type: replace-cross Abstract: Malicious content generated from large language models (LLMs) could pose severe safety risks and ethical concerns. While existing LLM safety g
arXiv:2410.22046v4 Announce Type: replace-cross Abstract: Chord progressions encapsulate important information about music, pertaining to its structure and conveyed emotions. They serve as the backbon
arXiv:2610.01856v1 Announce Type: new Abstract: Vision-language-action (VLA) models unify visual perception, language understanding, and action generation, offering new opportunities for automation in
arXiv:2610.01166v1 Announce Type: cross Abstract: Cardiovascular magnetic resonance (CMR), including cine imaging, is a reference standard for the noninvasive assessment of cardiac morphology and vent
arXiv:2610.01331v1 Announce Type: new Abstract: Continual personalization of text-to-image diffusion models requires sequentially acquiring new concepts while retaining previously learned ones. Howeve
arXiv:2610.01141v1 Announce Type: cross Abstract: Morohoshi, Nakayama, Manabe, and Mitarai proposed a physically motivated quantum machine learning problem in which the goal is to predict quantities o
arXiv:2610.00174v1 Announce Type: new Abstract: Breast cancer is a significant contributor to female mortality across the world, displaying one of the highest oc currence rates among the various cance
Anthropic's Claude hillclimb loop designs evals and improves agents one change at a time. Here's how to run that loop against production traces in Arize AX. The post Claude’s hillclimb loop for AI age
Clef Decision Models are now on @ollama introducing 𝚌𝚕𝚎𝚏: our first models trained by @cloudflare's workers ai team. today, we're releasing two fast and accurate decision models that top the benchmark
arXiv:2610.01322v1 Announce Type: new Abstract: We introduce the Clifford Sheaf Neural Network (CSNN), an equivariant sheaf neural network for geometric graphs that places a Clifford algebra on each s
arXiv:2610.00894v1 Announce Type: new Abstract: Recent works on continuous diffusion for discrete data have demonstrated performance on par with comparable discrete diffusion models. However, these co
arXiv:2610.00992v1 Announce Type: cross Abstract: Learning-based driving planners are usually trained and evaluated in open loop against logged trajectories. In closed loop, a trajectory with small di
arXiv:2610.01927v1 Announce Type: new Abstract: Feedforward foundation models have recently shown remarkable 3D reconstruction capabilities. However, existing models exhibit large tracking drift in lo
arXiv:2610.00673v1 Announce Type: cross Abstract: Looped language models increase effective depth by repeatedly applying a shared block of layers, but existing large-scale recipes require multi-stage
arXiv:2610.01834v1 Announce Type: new Abstract: Judgment models such as jev{} return, in a single call and without reasoning text, a probability for each described option. This makes them attractive a
arXiv:2610.00425v1 Announce Type: cross Abstract: Code generation has emerged as a central capability of large language models, with coding agents now able to produce functionally correct software pro
arXiv:2610.01773v1 Announce Type: cross Abstract: The central challenge in de novo protein design is generating plausible, mutually compatible structures and sequences, such that each designed sequenc
arXiv:2610.01710v1 Announce Type: new Abstract: Visual grounding localizes an object described by language with a bounding box. Most multimodal grounding models compress target identification, spatial
arXiv:2610.01754v1 Announce Type: cross Abstract: Video Anomaly Detection (VAD) aims to temporally localize abnormal events in videos. Most existing approaches rely on dataset-specific training and cu
arXiv:2610.01258v1 Announce Type: new Abstract: Autonomous colonoscopic navigation can reduce operator burden and the risk of loop formation or tissue trauma, but remains challenging due to deformable
arXiv:2610.01191v1 Announce Type: new Abstract: An optical character recognition(OCR) system can scan paper and extract text, making people's jobs easier. While numerous OCR systems are accessible in
arXiv:2610.00197v1 Announce Type: new Abstract: We investigate automated rewards for training language models in conversational humor, focusing on reward exploits and countermeasures. Two approaches a
arXiv:2610.00418v1 Announce Type: new Abstract: Scaling Transformers to long contexts is constrained by the quadratic cost of self-attention and the linear growth of key-value cache memory transfer. S
arXiv:2610.01994v1 Announce Type: new Abstract: Wildfires pose severe risks to human life, ecosystems, and property. This study presents a machine learning approach for wildfire detection from GOES AB
arXiv:2610.01559v1 Announce Type: cross Abstract: World Action Models (WAMs) predict visual futures and robot actions, yet they remain susceptible to task-incomplete imagination, where plausible, acti
arXiv:2610.00636v1 Announce Type: new Abstract: Evaluating AI agents on scientific research tasks is constrained by the time and resources required for the underlying experiments or calculations. In c
arXiv:2610.00237v1 Announce Type: cross Abstract: Spacecraft thermal design requires repeated evaluation of how variations in the number and spatial arrangement of heat-generating components and in th
arXiv:2610.00973v1 Announce Type: new Abstract: Science teachers frequently search for documentary excerpts not by describing what appears on screen, but by querying the abstract concepts they intend
arXiv:2610.00234v1 Announce Type: new Abstract: 'Train a model on the same problems written under two incompatible conventions, both correct, and ask what the ordering of that data writes into the par
arXiv:2610.00232v1 Announce Type: new Abstract: Fixed-size recurrent memory limits storage growth during inference, but successful recall depends on the task and training. We study a small DeltaNet va
arXiv:2512.00939v3 Announce Type: replace-cross Abstract: Recent progress in contact-rich robotic manipulation has been striking, yet most deployed systems remain confined to simple, scripted routines
arXiv:2606.15420v2 Announce Type: replace-cross Abstract: Safety evaluations test a policy on prompts that omit the incentive information deployment supplies: a commission, a performance score, a dash
arXiv:2610.01253v1 Announce Type: new Abstract: Quantum Reinforcement Learning (QRL) integrates reinforcement learning with parameterized quantum circuits and is a promising approach to combinatorial
arXiv:2610.00840v1 Announce Type: cross Abstract: Transformer-based large language models (LLMs) such as RoBERTa represent text using contextual word embeddings (CWEs), which alter the embeddings asso
arXiv:2610.00239v1 Announce Type: new Abstract: Model failover restores availability, but changes which financial institutions share decision errors. We formulate outage-contingent routing through a l
arXiv:2610.01989v1 Announce Type: new Abstract: Concept erasure removes copyright-protected, privacy-sensitive, or otherwise undesirable concepts from pretrained text-to-image diffusion models to supp
arXiv:2610.01301v1 Announce Type: cross Abstract: Most current grasp synthesis systems are trained offline and remain fixed during deployment. While this works well when deployment conditions resemble
arXiv:2610.01583v1 Announce Type: cross Abstract: Despite many studies about causes and remedies of plasticity loss in Reinforcement Learning (RL) under continual task changes, no RL method has yet co
arXiv:2610.01397v1 Announce Type: new Abstract: Dynamic humanoid motions such as flips risk hardware damage due to suboptimal policies, disturbances or sim-to-real gaps. A motion tracking policy offer
arXiv:2610.01794v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models rely strongly on language for describing task information, despite having multimodal inputs. We hypothesize that oth
arXiv:2610.01833v1 Announce Type: new Abstract: Enterprise AI agent skills evolve as tool APIs, models, and specifications change, yet final-output evaluation can miss process-level behavioral drift.
arXiv:2610.00328v1 Announce Type: new Abstract: Structured tool calls often fail after only a small number of fields violate a schema or an execution contract. Regenerating the complete object enlarge
arXiv:2610.01403v1 Announce Type: new Abstract: Spiking Transformers merge the energy-efficiency of spiking neural networks (SNNs) with the representational power of self-attention, creating a promisi
arXiv:2610.02019v1 Announce Type: cross Abstract: The rapid growth of video-based social media has increased users' exposure to harmful content, creating a need for reliable automated video safety det
arXiv:2610.01599v1 Announce Type: cross Abstract: Stochastic recursive momentum (STORM) achieves fast convergence for nonconvex optimization via the variance reduction effect, but existing analyses re
Cool eval. Simply ask an LLM “Land or Water?” and give it a latitude and longitude coordinate as text. Ask 16,200 times, plot as image. The models know. From compressing the internet. results for all
arXiv:2610.01124v1 Announce Type: new Abstract: Electroencephalography (EEG) foundation models are often pretrained with a fixed channel vocabulary or a limited set of montages, making transfer diffic
arXiv:2610.02195v1 Announce Type: new Abstract: The generalized Schrodinger bridge on a graph moves mass between two distributions while charging a cost for the states visited. It has been approached
arXiv:2610.01963v1 Announce Type: new Abstract: Emergency department (ED) triage is a high-stakes prioritization task in which demographic, socioeconomic, and system-context information may improperly
arXiv:2610.01193v1 Announce Type: cross Abstract: Counterfactual generation seeks to sample outcomes under a hypothetical intervention or decision using observational data collected under the factual
arXiv:2610.02005v1 Announce Type: new Abstract: A multi-LLM council lets several large language models (LLMs) deliberate on a question and return an answer together with a confidence estimate. As thes
arXiv:2610.00277v1 Announce Type: new Abstract: Federated multimodal graph foundation models (GFMs) aim to adapt pretrained multimodal models to decentralized graph data, where each client owns a priv
arXiv:2610.00890v1 Announce Type: cross Abstract: Coding agents often fail in the last mile: they build most of a feature but drop a requirement, test only the cases their implementation already handl
arXiv:2610.01319v1 Announce Type: new Abstract: When constraints conflict, an optimizer must determine which requirements to preserve and which to relax. On the one hand, a priority ordering specifies
arXiv:2610.01921v1 Announce Type: cross Abstract: Cross-lingual contrastive learning has been a core component of multilingual encoder training, but the ability to explicitly align representations is
arXiv:2610.01649v1 Announce Type: new Abstract: Weight-space networks operate directly on parameters of other neural networks, enabling tasks such as predicting model properties, editing trained model
arXiv:2610.00759v1 Announce Type: cross Abstract: Cyber attack agents are typically trained and evaluated within a single simulator, making it unclear whether learned policies transfer beyond the envi