Self-Evolving Multi-Agent Collaboration Networks for Software Development

LLM-driven multi-agent collaboration (MAC) systems have demonstrated impressive capabilities in automatic software development at the function level. However, their heavy reliance on human design limits their adaptability to the diverse demands of real-world software development. To address this limitation, we introduce EvoMAC, a novel self-evolving paradigm for MAC networks. Inspired by traditional neural network training, EvoMAC obtains text-based environmental feedback by verifying the MAC network's output against a target proxy and leverages a novel textual backpropagation to update the network. To extend coding capabilities beyond function-level tasks to more challenging software-level development, we further propose rSDE-Bench, a requirement-oriented software development benchmark, which features complex and diverse software requirements along with automatic evaluation of requirement correctness. Our experiments show that: i) The automatic requirement-aware evaluation in rSDE-Bench closely aligns with human evaluations, validating its reliability as a software-level coding benchmark. ii) EvoMAC outperforms previous SOTA methods on both the software-level rSDE-Bench and the function-level HumanEval benchmarks, reflecting its superior coding capabilities. The benchmark can be downloaded at https://yuzhu-cai.github.io/rSDE-Bench/.

Synthesizing Post-Training Data for LLMs through Multi-Agent Simulation

Post-training is essential for enabling large language models (LLMs) to follow human instructions. Inspired by the recent success of using LLMs to simulate human society, we leverage multi-agent simulation to automatically generate diverse text-based scenarios, capturing a wide range of real-world human needs. We propose MATRIX, a multi-agent simulator that creates realistic and scalable scenarios. Leveraging these outputs, we introduce a novel scenario-driven instruction generator MATRIX-Gen for controllable and highly realistic data synthesis. Extensive experiments demonstrate that our framework effectively generates both general and domain-specific data. Notably, on AlpacaEval 2 and Arena-Hard benchmarks, Llama-3-8B-Base, post-trained on datasets synthesized by MATRIX-Gen with just 20K instruction-response pairs, outperforms Meta's Llama-3-8B-Instruct model, which was trained on over 10M pairs; see our project at https://github.com/ShuoTang123/MATRIX-Gen.

AI-Aided Kalman Filters

The Kalman filter (KF) and its variants are among the most celebrated algorithms in signal processing. These methods are used for state estimation of dynamic systems by relying on mathematical representations in the form of simple state-space (SS) models, which may be crude and inaccurate descriptions of the underlying dynamics. Emerging data-centric artificial intelligence (AI) techniques tackle these tasks using deep neural networks (DNNs), which are model-agnostic. Recent developments illustrate the possibility of fusing DNNs with classic Kalman-type filtering, obtaining systems that learn to track in partially known dynamics. This article provides a tutorial-style overview of design approaches for incorporating AI in aiding KF-type algorithms. We review both generic and dedicated DNN architectures suitable for state estimation, and provide a systematic presentation of techniques for fusing AI tools with KFs and for leveraging partial SS modeling and data, categorizing design approaches into task-oriented and SS model-oriented. The usefulness of each approach in preserving the individual strengths of model-based KFs and data-driven DNNs is investigated in a qualitative and quantitative study, whose code is publicly available, illustrating the gains of hybrid model-based/data-driven designs. We also discuss existing challenges and future research directions that arise from fusing AI and Kalman-type algorithms.

Continuously Optimizing Radar Placement with Model Predictive Path Integrals

Continuously optimizing sensor placement is essential for precise target localization in various military and civilian applications. While information theory has shown promise in optimizing sensor placement, many studies oversimplify sensor measurement models or neglect dynamic constraints of mobile sensors. To address these challenges, we employ a range measurement model that incorporates radar parameters and radar-target distance, coupled with Model Predictive Path Integral (MPPI) control to manage complex environmental obstacles and dynamic constraints. We compare the proposed approach against stationary radars or simplified range measurement models based on the root mean squared error (RMSE) of the Cubature Kalman Filter (CKF) estimator for the targets' state. Additionally, we visualize the evolving geometry of radars and targets over time, highlighting areas of highest measurement information gain, demonstrating the strengths of the approach. The proposed strategy outperforms stationary radars and simplified range measurement models in target localization, achieving a 38-74% reduction in mean RMSE and a 33-79% reduction in the upper tail of the 90% Highest Density Interval (HDI) over 500 Monte Carl (MC) trials across all time steps. Code will be made publicly available upon acceptance.

Robust Collaborative Perception without External Localization and Clock Devices

A consistent spatial-temporal coordination across multiple agents is fundamental for collaborative perception, which seeks to improve perception abilities through information exchange among agents. To achieve this spatial-temporal alignment, traditional methods depend on external devices to provide localization and clock signals. However, hardware-generated signals could be vulnerable to noise and potentially malicious attack, jeopardizing the precision of spatial-temporal alignment. Rather than relying on external hardwares, this work proposes a novel approach: aligning by recognizing the inherent geometric patterns within the perceptual data of various agents. Following this spirit, we propose a robust collaborative perception system that operates independently of external localization and clock devices. The key module of our system,~\emph{FreeAlign}, constructs a salient object graph for each agent based on its detected boxes and uses a graph neural network to identify common subgraphs between agents, leading to accurate relative pose and time. We validate \emph{FreeAlign} on both real-world and simulated datasets. The results show that, the ~\emph{FreeAlign} empowered robust collaborative perception system perform comparably to systems relying on precise localization and clock devices.

Decentralized and Lifelong-Adaptive Multi-Agent Collaborative Learning

Decentralized and lifelong-adaptive multi-agent collaborative learning aims to enhance collaboration among multiple agents without a central server, with each agent solving varied tasks over time. To achieve efficient collaboration, agents should: i) autonomously identify beneficial collaborative relationships in a decentralized manner; and ii) adapt to dynamically changing task observations. In this paper, we propose DeLAMA, a decentralized multi-agent lifelong collaborative learning algorithm with dynamic collaboration graphs. To promote autonomous collaboration relationship learning, we propose a decentralized graph structure learning algorithm, eliminating the need for external priors. To facilitate adaptation to dynamic tasks, we design a memory unit to capture the agents' accumulated learning history and knowledge, while preserving finite storage consumption. To further augment the system's expressive capabilities and computational efficiency, we apply algorithm unrolling, leveraging the advantages of both mathematical optimization and neural networks. This allows the agents to `learn to collaborate' through the supervision of training tasks. Our theoretical analysis verifies that inter-agent collaboration is communication efficient under a small number of communication rounds. The experimental results verify its ability to facilitate the discovery of collaboration strategies and adaptation to dynamic learning scenarios, achieving a 98.80% reduction in MSE and a 188.87% improvement in classification accuracy. We expect our work can serve as a foundational technique to facilitate future works towards an intelligent, decentralized, and dynamic multi-agent system. Code is available at https://github.com/ShuoTang123/DeLAMA.

Self-Alignment of Large Language Models via Monopolylogue-based Social Scene Simulation

Aligning large language models (LLMs) with human values is imperative to mitigate potential adverse effects resulting from their misuse. Drawing from the sociological insight that acknowledging all parties' concerns is a key factor in shaping human values, this paper proposes a novel direction to align LLMs by themselves: social scene simulation. To achieve this, we present MATRIX, a novel social scene simulator that emulates realistic scenes around a user's input query, enabling the LLM to take social consequences into account before responding. MATRIX serves as a virtual rehearsal space, akin to a Monopolylogue, where the LLM performs diverse roles related to the query and practice by itself. To inject this alignment, we fine-tune the LLM with MATRIX-simulated data, ensuring adherence to human values without compromising inference speed. We theoretically show that the LLM with MATRIX outperforms Constitutional AI under mild assumptions. Finally, extensive experiments validate that our method outperforms over 10 baselines across 4 benchmarks. As evidenced by 875 user ratings, our tuned 13B-size LLM exceeds GPT-4 in aligning with human values. Code is available at https://github.com/pangxianghe/MATRIX.

Robust Interference Mitigation techniques for Direct Position Estimation

Global Navigation Satellite System (GNSS) is pervasive in navigation and positioning applications, where precise position and time referencing estimations are required. Conventional methods for GNSS positioning involve a two-step process, where intermediate measurements such as Doppler shift and time delay of received GNSS signals are computed and then used to solve for the receiver's position. Alternatively, Direct Position Estimation (DPE) was proposed to infer the position directly from the sampled signal without intermediate variables, yielding to superior levels of sensitivity and operation under challenging environments. However, the positioning resilience of DPE method is still under the threat of various interferences. Robust Interference Mitigation (RIM) processing has been studied and proved to be efficient against various interference in conventional two-step positioning (2SP) methods, and therefore worthy to be explored regarding its potential to enhance DPE. This article extends DPE methodology by incorporating RIM strategies that address the increasing need to protect GNSS receivers against intentional or unintentional interferences, such as jamming signals, which can deny GNSS-based positioning. RIM, which leverages robust statistics, was shown to provide competitive results in two-step approaches and is here employed in a high-sensitivity DPE framework with successful results. The article also provides a quantification of the loss of efficiency of using RIM when no interference is present and validates the proposed methodology on relevant interference cases, while the approach can be used to mitigate other common interference signals.

On Parametric Misspecified Bayesian Cramér-Rao bound: An application to linear Gaussian systems

A lower bound is an important tool for predicting the performance that an estimator can achieve under a particular statistical model. Bayesian bounds are a kind of such bounds which not only utilizes the observation statistics but also includes the prior model information. In reality, however, the true model generating the data is either unknown or simplified when deriving estimators, which motivates the works to derive estimation bounds under modeling mismatch situations. This paper provides a derivation of a Bayesian Cram\'{e}r-Rao bound under model misspecification, defining important concepts such as pseudotrue parameter that were not clearly identified in previous works. The general result is particularized in linear and Gaussian problems, where closed-forms are available and results are used to validate the results.

Unrolled Graph Learning for Multi-Agent Collaboration

Multi-agent learning has gained increasing attention to tackle distributed machine learning scenarios under constrictions of data exchanging. However, existing multi-agent learning models usually consider data fusion under fixed and compulsory collaborative relations among agents, which is not as flexible and autonomous as human collaboration. To fill this gap, we propose a distributed multi-agent learning model inspired by human collaboration, in which the agents can autonomously detect suitable collaborators and refer to collaborators' model for better performance. To implement such adaptive collaboration, we use a collaboration graph to indicate the pairwise collaborative relation. The collaboration graph can be obtained by graph learning techniques based on model similarity between different agents. Since model similarity can not be formulated by a fixed graphical optimization, we design a graph learning network by unrolling, which can learn underlying similar features among potential collaborators. By testing on both regression and classification tasks, we validate that our proposed collaboration model can figure out accurate collaborative relationship and greatly improve agents' learning performance.