Stories tagged science & research.
arXiv
arXiv:2609.26761v1 Announce Type: cross Abstract: Agents using the Model Context Protocol (MCP) rely on semantic matching to select tools from third-party servers, exposing a semantic supply-chain risk through attacker-controlled metadata and outputs. We introduce A2M (Attraction-to-Manipulation)…
arXiv
arXiv:2609.26039v1 Announce Type: cross Abstract: Point cloud generation has emerged as a crucial task for accurately capturing and reproducing the complexity of the physical world. However, existing generative approaches, predominantly relying on Transformers and Variational Autoencoders (VAEs)…
arXiv
arXiv:2609.25396v1 Announce Type: cross Abstract: Parallel coding agents can produce patches that work alone but fail when merged. This happens when one agent changes an interface or rule that another agent still relies on. We study these failures with stale, a benchmark for semantic coordination…
arXiv
arXiv:2609.25715v1 Announce Type: new Abstract: Though artificial intelligence (AI) increasingly transforms modern medicine, its integration into Traditional Chinese Medicine (TCM) has been relatively slow, primarily due to TCM's reliance on holistic, subjective diagnostic methods---namely…
arXiv
arXiv:2609.25591v1 Announce Type: new Abstract: Coding agents now find real vulnerabilities in production software. However, bug discovery results do not measure whether agents can construct exploit primitives. We introduce KEX-bench, a benchmark for evaluating coding agents on exploit primitive…
arXiv
arXiv:2609.25237v1 Announce Type: cross Abstract: Post-training is becoming a service (PTaaS): a customer hands an operator data and a goal, and a forward-deployed engineer (FDE) returns a fine-tuned, evaluated, and deployed model under a budget, a human-approval gate, and reproducibility…
arXiv
arXiv:2604.02947v2 Announce Type: replace Abstract: Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain state across interactions and translate intermediate outputs into concrete…
arXiv
arXiv:2609.25570v1 Announce Type: new Abstract: Large language models (LLMs) exhibit a parametric vulnerability to adversarial swarm consensus. To mitigate this sycophancy, we introduce Contrastive Epistemic Decoding (CED), a zero-shot inference intervention. Unlike standard Contrastive Decoding…
arXiv
arXiv:2609.24660v2 Announce Type: replace-cross Abstract: Human demonstrations offer a scalable way to collect manipulation data, but their contacts may be unstable or infeasible when transferred to a robot hand. Collecting demonstrations directly on the target robot avoids this mismatch but…
arXiv
arXiv:2609.25176v1 Announce Type: cross Abstract: Real-time voice assistants must reason over evolving requests, execute actions, and follow conversational rules. Qwen-Audio-3.1-Realtime brings these requirements together through Think, Act, and Speak and Coordinate. Think combines Core-Cocktail…
arXiv
arXiv:2609.25769v1 Announce Type: new Abstract: Graphical User Interface (GUI) Agents autonomously interact with software to fulfill user requests, where GUI navigation stands out as the most critical and challenging capability. Mastering this capability demands a complex synergy of step-wise…
arXiv
arXiv:2609.25848v1 Announce Type: new Abstract: A higher evaluation score does not always mean a better language model system. When optimization exploits an evaluator's mistakes, measured progress can conceal unchanged or deteriorating task performance. This failure can arise through parameter…
arXiv
arXiv:2609.26029v1 Announce Type: new Abstract: Ontology generation from Competency Questions (CQs) is a central yet labor-intensive phase of Ontology Engineering. While large language models (LLMs) offer promising automation capabilities, current evaluations remain fragmented. Task formulations…
arXiv
arXiv:2609.26069v1 Announce Type: new Abstract: Simulation-based tutor selection can be unstable when predictively adequate learner models imply different policy rankings. RankCert certifies one of eight equal-budget tutoring policies only when model-averaged utility, probability-best, posterior…
arXiv
arXiv:2609.26106v1 Announce Type: new Abstract: Early identification of non-responders to neoadjuvant chemotherapy (NACT) is crucial for timely treatment adaptation in breast cancer. However, many existing predictive models rely on multiparametric magnetic resonance imaging (MRI), late treatment…
arXiv
arXiv:2609.26126v1 Announce Type: new Abstract: Many AI systems make decisions locally, even when every realized output must obey an additive conservation law, such as selecting exactly a fixed number of items. This constraint can be statistically invisible: small subsets of a balanced fixed-budget…
arXiv
arXiv:2609.26160v1 Announce Type: new Abstract: Fix a corpus and send recipe search to infinity: try every order of the skills, every arrangement from blocked to interleaved, every composition, and keep the best. Two quantities decide what that search was worth: the diameter of the reachable set it…
arXiv
arXiv:2609.26213v1 Announce Type: new Abstract: We study the multiplayer multi-armed bandit problem with information asymmetry under Bernoulli rewards, for three information structures: asymmetry in actions, in rewards, and in both. Replacing the Hoeffding-style confidence intervals of prior work…
arXiv
arXiv:2609.26279v1 Announce Type: new Abstract: Bot accounts and coordinated influence operations are often discovered via heuristic methods, leaving a dearth of reliable ground-truth labels for training detection systems. To address this challenge, we study a natural question: can we generate…
arXiv
arXiv:2609.26461v1 Announce Type: new Abstract: Pseudorandom number generators (PRNGs) constitute indispensable computational tools across multiple scientific domains, including Monte Carlo simulations, stochastic computing, and artificial intelligence (AI). The reproducibility of such applications…
arXiv
arXiv:2609.26642v1 Announce Type: new Abstract: Successful agent execution need not identify which future product improvement its user would value. We present a decision-specific audit that maps a declared observation channel and product-value contrast to compatible intervals and witness…
arXiv
arXiv:2609.26777v1 Announce Type: new Abstract: We introduce SWE-Serve, a benchmark for evaluating agents on production inference engineering tasks. Implementing an inference feature can require coordinating multiple changes across the serving stack, including model support, runtime execution, and…
arXiv
arXiv:2609.25047v1 Announce Type: cross Abstract: Autonomous agents that automatically build artificial intelligence (AI) models could broaden access to AI across science and engineering. A popular line of such agents frames model building as a code search problem and solves it by tree search, in…
arXiv
arXiv:2609.25052v1 Announce Type: cross Abstract: "An agent that writes its conclusions into a store it later retrieves from closes a loop usually reported as one-way contamination. Taking the loop to the infinite-tenure limit against an append-only store gives a different picture: because writing…
arXiv
arXiv:2609.25563v1 Announce Type: cross Abstract: Agent memory enables enterprise agents to retain knowledge acquired during work and reuse it across tasks and agents, turning execution experience into persistent organizational knowledge. Realizing this potential requires both source--memory…
arXiv
arXiv:2609.26209v1 Announce Type: cross Abstract: Collections of diverse observations often share one acquisition, processing, geometric, or channel corruption, while only an unpaired clean reference set is available. For a prescribed low-dimensional correction shared across observations, the…
arXiv
arXiv:2609.26300v1 Announce Type: cross Abstract: Despite their strong performance, large language models (LLMs) are bottlenecked by KV cache memory traffic during long-context inference. Sparse attention is widely used to accelerate LLM inference by computing exact attention over a selected subset…
arXiv
arXiv:2609.26361v1 Announce Type: cross Abstract: With the rapid pace of AI research and the hundreds of daily new publications, staying up-to-date with the latest developments has become increasingly difficult. For researchers, quickly identifying impactful work is essential, yet manually…
arXiv
arXiv:2609.26426v1 Announce Type: cross Abstract: Finite Element Analysis (FEA) is widely used for transient mechanical simulations, but its high computational cost limits real-time and high-resolution applications. Deep learning surrogate models can reduce this cost; however, many existing…
arXiv
arXiv:2609.26487v1 Announce Type: cross Abstract: Recursive models can continue updating their latent states beyond their nominal inference budget, so an incorrect output at that budget does not show whether computation is unfinished or has entered a persistently unsuccessful regime. We study the…