Search for: All records

Large Language Models (LLMs) have achieved remarkable success across a wide array of tasks. Due to the impressive planning and reasoning abilities of LLMs, they have been used as autonomous agents to do many tasks automatically. Recently, based on the development of using one LLM as a single planning or decision-making agent, LLM-based multi-agent systems have achieved considerable progress in complex problem-solving and world simulation. To provide the community with an overview of this dynamic field, we present this survey to offer an in-depth discussion on the essential aspects of multi-agent systems based on LLMs, as well as the challenges. Our goal is for readers to gain substantial insights on the following questions: What domains and environments do LLM-based multi-agents simulate? How are these agents profiled and how do they communicate? What mechanisms contribute to the growth of agents' capacities? For those interested in delving into this field of study, we also summarize the commonly used datasets or benchmarks for them to have convenient access. To keep researchers updated on the latest studies, we maintain an open-source GitHub repository, dedicated to outlining the research on LLM-based multi-agent systems. 

Projection algorithms such as t-SNE or UMAP are useful for the visualization of high dimensional data, but depend on hyperpa- rameters which must be tuned carefully. Unfortunately, iteratively recomputing projections to find the optimal hyperparameter values is computationally intensive and unintuitive due to the stochastic nature of such methods. In this paper we propose Hy- perNP, a scalable method that allows for real-time interactive hyperparameter exploration of projection methods by training neural network approximations. A HyperNP model can be trained on a fraction of the total data instances and hyperparameter configurations that one would like to investigate and can compute projections for new data and hyperparameters at interactive speeds. HyperNP models are compact in size and fast to compute, thus allowing them to be embedded in lightweight visualiza- tion systems. We evaluate the performance of HyperNP across three datasets in terms of performance and speed. The results suggest that HyperNP models are accurate, scalable, interactive, and appropriate for use in real-world settings. 

Photoswitches are molecules that undergo a reversible, structural isomerization after exposure to different wavelengths of light. The dynamic control offered by molecular photoswitches is favorable for applications in materials chemistry, photopharmacology, and catalysis. Ideal photoswitches absorb visible light and have long-lived metastable isomers. We used high throughput virtual screening to predict the absorption maxima (λmax) of the E-isomer and half-lives (t1/2) of the Z-isomer. However, computing the photophysical and kinetic properties of each entry of a virtual molecular library containing 103–106 entries with density functional theory is prohibitively time-consuming. We applied active search, a machine learning technique to intelligently search a chemical search space of 255991 photoswitches based on 29 known azoarenes and their derivatives. We iteratively trained the active search algorithm based on whether a candidate absorbed visible light (λmax > 450 nm). Active search was found to triple the discovery rate compared to random search. Further, we projected 1962 photoswitches to 2D using the Uniform Manifold Approximation and Projection (umap) algorithm and found that λmax depends on the core, which is tunable with substituents. We then incorporated a second stage of screening with to predict the stabilities of the Z-isomers for the top 1% of candidates. We identified four ideal photoswitches that concurrently satisfy λmax > 450 nm and t1/2 > 2 hours; the range of λmax and t1/2 range from 465 to 531 nm and hours to years, respectively. 

We analyze the Secure Remote Password (SRP) protocol for structural weaknesses using the Cryptographic Protocol Shapes Analyzer (CPSA) in the first formal analysis of SRP (specifically, Version 3). SRP is a widely deployed Password Authenticated Key Exchange (PAKE) protocol used in 1Password, iCloud Keychain, and other products. As with many PAKE protocols, two participants use knowledge of a pre-shared password to authenticate each other and establish a session key. SRP aims to resist dictionary attacks, not store plaintext-equivalent passwords on the server, avoid patent infringement, and avoid export controls by not using encryption. Formal analysis of SRP is challenging in part because existing tools provide no simple way to reason about its use of the mathematical expression “v + g b mod q”. Modeling v + g b as encryption, we complete an exhaustive study of all possible execution sequences of SRP. Ignoring possible algebraic attacks, this analysis detects no major structural weakness, and in particular no leakage of any secrets. We do uncover one notable weakness of SRP, which follows from its design constraints. It is possible for a malicious server to fake an authentication session with a client, without the client’s participation. This action might facilitate an escalation of privilege attack, if the client has higher privileges than does the server. We conceived of this attack before we used CPSA and confirmed it by generating corresponding execution shapes using CPSA. 

Abstract Projection algorithms such as t‐SNE or UMAP are useful for the visualization of high dimensional data, but depend on hyperparameters which must be tuned carefully. Unfortunately, iteratively recomputing projections to find the optimal hyperparameter values is computationally intensive and unintuitive due to the stochastic nature of such methods. In this paper we propose HyperNP, a scalable method that allows for real‐time interactive hyperparameter exploration of projection methods by training neural network approximations. A HyperNP model can be trained on a fraction of the total data instances and hyperparameter configurations that one would like to investigate and can compute projections for new data and hyperparameters at interactive speeds. HyperNP models are compact in size and fast to compute, thus allowing them to be embedded in lightweight visualization systems. We evaluate the performance of HyperNP across three datasets in terms of performance and speed. The results suggest that HyperNP models are accurate, scalable, interactive, and appropriate for use in real‐world settings. 

Abstract We present the results of a search for gravitational-wave transients associated with core-collapse supernova SN 2023ixf, which was observed in the galaxy Messier 101 via optical emission on 2023 May 19, during the LIGO–Virgo–KAGRA 15th Engineering Run. We define a five-day on-source window during which an accompanying gravitational-wave signal may have occurred. No gravitational waves have been identified in data when at least two gravitational-wave observatories were operating, which covered ∼14% of this five-day window. We report the search detection efficiency for various possible gravitational-wave emission models. Considering the distance to M101 (6.7 Mpc), we derive constraints on the gravitational-wave emission mechanism of core-collapse supernovae across a broad frequency spectrum, ranging from 50 Hz to 2 kHz, where we assume the gravitational-wave emission occurred when coincident data are available in the on-source window. Considering an ellipsoid model for a rotating proto-neutron star, our search is sensitive to gravitational-wave energy 1 × 10⁻⁴M_⊙c²and luminosity 2.6 × 10⁻⁴M_⊙c²s⁻¹for a source emitting at 82 Hz. These constraints are around an order of magnitude more stringent than those obtained so far with gravitational-wave data. The constraint on the ellipticity of the proto-neutron star that is formed is as low as 1.08, at frequencies above 1200 Hz, surpassing past results. 

Abstract Continuous gravitational waves (CWs) emission from neutron stars carries information about their internal structure and equation of state, and it can provide tests of general relativity. We present a search for CWs from a set of 45 known pulsars in the first part of the fourth LIGO–Virgo–KAGRA observing run, known as O4a. We conducted a targeted search for each pulsar using three independent analysis methods considering single-harmonic and dual-harmonic emission models. We find no evidence of a CW signal in O4a data for both models and set upper limits on the signal amplitude and on the ellipticity, which quantifies the asymmetry in the neutron star mass distribution. For the single-harmonic emission model, 29 targets have the upper limit on the amplitude below the theoretical spin-down limit. The lowest upper limit on the amplitude is 6.4 × 10⁻²⁷for the young energetic pulsar J0537−6910, while the lowest constraint on the ellipticity is 8.8 × 10⁻⁹for the bright nearby millisecond pulsar J0437−4715. Additionally, for a subset of 16 targets, we performed a narrowband search that is more robust regarding the emission model, with no evidence of a signal. We also found no evidence of nonstandard polarizations as predicted by the Brans–Dicke theory. 

Abstract We present results from a search for X-ray/gamma-ray counterparts of gravitational-wave (GW) candidates from the third observing run (O3) of the LIGO–Virgo–KAGRA network using the Swift Burst Alert Telescope (Swift-BAT). The search includes 636 GW candidates received with low latency, 86 of which have been confirmed by the offline analysis and included in the third cumulative Gravitational-Wave Transient Catalogs (GWTC-3). Targeted searches were carried out on the entire GW sample using the maximum-likelihood Non-imaging Transient Reconstruction and Temporal Search pipeline on the BAT data made available via the GUANO infrastructure. We do not detect any significant electromagnetic emission that is temporally and spatially coincident with any of the GW candidates. We report flux upper limits in the 15–350 keV band as a function of sky position for all the catalog candidates. For GW candidates where the Swift-BAT false alarm rate is less than 10⁻³Hz, we compute the GW–BAT joint false alarm rate. Finally, the derived Swift-BAT upper limits are used to infer constraints on the putative electromagnetic emission associated with binary black hole mergers.