Benefiting from the powerful language expression and planning capabilities of Large Language Models (LLMs), LLM-based autonomous agents have achieved promising performance in various downstream tasks. Recently, based on the development of single-agent systems, researchers propose to construct LLM-based multi-agent systems to tackle more complicated tasks. In this paper, we propose a novel framework, named COPPER, to enhance the collaborative capabilities of LLM-based agents with the self-reflection mechanism. To improve the quality of reflections, we propose to fine-tune a shared reflector, which automatically tunes the prompts of actor models using our counterfactual PPO mechanism. On the one hand, we propose counterfactual rewards to assess the contribution of a single agent's reflection within the system, alleviating the credit assignment problem. On the other hand, we propose to train a shared reflector, which enables the reflector to generate personalized reflections according to agent roles, while reducing the computational resource requirements and improving training stability. We conduct experiments on three datasets to evaluate the performance of our model in multi-hop question answering, mathematics, and chess scenarios. Experimental results show that COPPER possesses stronger reflection capabilities and exhibits excellent generalization performance across different actor models.

Recent large language models (LLMs) are trained on diverse corpora and tasks, leading them to develop complementary strengths. Multi-agent debate (MAD) has emerged as a popular way to leverage these strengths for robust reasoning, though it has mostly been applied to language-only tasks, leaving its efficacy on multimodal problems underexplored. In this paper, we study MAD for solving vision-and-language reasoning problems. Our setup enables generalizing the debate protocol with heterogeneous experts that possess single- and multi-modal capabilities. To this end, we present Weighted Iterative Society-of-Experts (WISE), a generalized and modular MAD framework that partitions the agents into Solvers, that generate solutions, and Reflectors, that verify correctness, assign weights, and provide natural language feedback. To aggregate the agents' solutions across debate rounds, while accounting for variance in their responses and the feedback weights, we present a modified Dawid-Skene algorithm for post-processing that integrates our two-stage debate model. We evaluate WISE on SMART-840, VisualPuzzles, EvoChart-QA, and a new SMART-840++ dataset with programmatically generated problem instances of controlled difficulty. Our results show that WISE consistently improves accuracy by 2-7% over the state-of-the-art MAD setups and aggregation methods across diverse multimodal tasks and LLM configurations.

Table-based question answering requires complex reasoning capabilities that current LLMs struggle to achieve with single-pass inference. Existing approaches, such as Chain-of-Thought reasoning and question decomposition, lack error detection mechanisms and discard problem-solving experiences, contrasting sharply with how humans tackle such problems. In this paper, we propose MAPLE (Multi-agent Adaptive Planning with Long-term mEmory), a novel framework that mimics human problem-solving through specialized cognitive agents working in a feedback-driven loop. MAPLE integrates 4 key components: (1) a Solver using the ReAct paradigm for reasoning, (2) a Checker for answer verification, (3) a Reflector for error diagnosis and strategy correction, and (4) an Archiver managing long-term memory for experience reuse and evolution. Experiments on WiKiTQ and TabFact demonstrate significant improvements over existing methods, achieving state-of-the-art performance across multiple LLM backbones.

Automatically configuring storage systems is hard: parameter spaces are large and conditions vary across workloads, deployments, and versions. Heuristic and ML tuners are often system specific, require manual glue, and degrade under changes. Recent LLM-based approaches help but usually treat tuning as a single-shot, system-specific task, which limits cross-system reuse, constrains exploration, and weakens validation. We present StorageXTuner, an LLM agent-driven auto-tuning framework for heterogeneous storage engines. StorageXTuner separates concerns across four agents - Executor (sandboxed benchmarking), Extractor (performance digest), Searcher (insight-guided configuration exploration), and Reflector (insight generation and management). The design couples an insight-driven tree search with layered memory that promotes empirically validated insights and employs lightweight checkers to guard against unsafe actions. We implement a prototype and evaluate it on RocksDB, LevelDB, CacheLib, and MySQL InnoDB with YCSB, MixGraph, and TPC-H/C. Relative to out-of-the-box settings and to ELMo-Tune, StorageXTuner reaches up to 575% and 111% higher throughput, reduces p99 latency by as much as 88% and 56%, and converges with fewer trials.

Abstract--Agentic methods have emerged as a powerful and autonomous paradigm that enhances reasoning, collaboration, and adaptive control, enabling systems to coordinate and independently solve complex tasks. We extend this paradigm to safety alignment by introducing Agentic Moderation, a model-agnostic framework that leverages specialized agents to defend multimodal systems against jailbreak attacks. Unlike prior approaches that apply as a static layer over inputs or outputs and provide only binary classifications(safe or unsafe), our method integrates dynamic, cooperative agents,including Shield, Responder, Evaluator, and Reflector,to achieve context-aware and interpretable moderation. Extensive experiments across five datasets and four representative large vision-language models (L VLMs) demonstrate that our approach reduces the Attack Success Rate (ASR) by 7-19%, maintains a stable Non-Following Rate (NF), and improves the Refusal Rate (RR) by 4-20%, achieving robust, interpretable, and well-balanced safety performance. By harnessing the flexibility and reasoning capacity of agentic architectures, Agentic Moderation provides modular, scalable, and fine-grained safety enforcement, highlighting the broader potential of agentic systems as a foundation for automated safety governance. Large vision-language models (L VLMs) integrate visual and textual modalities, enabling richer multimodal reasoning and expanding their application scope. Malicious users can exploit cross-modal interactions and the continuous nature of visual embedding spaces, which makes adversarial defenses especially challenging. Cross-modality adversarial attacks exploit visual vulnerabilities and modality shifts in semantic meaning. Examples include pixel-level perturbations that embed harmful intent within images [1]-[3], malicious content rendered via typography or flowcharts [4], harmful behaviors that emerge only from the combination of benign-looking text and visual inputs, implicit cross-modal interactions that obscure adversarial intent [5], and hybrid or ensemble strategies that combine these mechanisms [6].

Pedestrians Localization in Non-Line-of-Sight (NLoS) regions within urban environments poses a significant challenge for autonomous driving systems. While mmWave radar has demonstrated potential for detecting objects in such scenarios, the 2D radar point cloud (PCD) data is susceptible to distortions caused by multipath reflections, making accurate spatial inference difficult. Additionally, although camera images provide high-resolution visual information, they lack depth perception and cannot directly observe objects in NLoS regions. In this paper, we propose a novel framework that interprets radar PCD through road layout inferred from camera for localization of NLoS pedestrians. The proposed method leverages visual information from the camera to interpret 2D radar PCD, enabling spatial scene reconstruction. The effectiveness of the proposed approach is validated through experiments conducted using a radar-camera system mounted on a real vehicle. The localization performance is evaluated using a dataset collected in outdoor NLoS driving environments, demonstrating the practical applicability of the method.

Vision-Language-Action (VLA) models have achieved notable success but often struggle with limited generalizations. To address this, integrating generalized Vision-Language Models (VLMs) as assistants to VLAs has emerged as a popular solution. However, current approaches often combine these models in rigid, sequential structures: using VLMs primarily for high-level scene understanding and task planning, and VLAs merely as executors of lower-level actions, leading to ineffective collaboration and poor grounding challenges. In this paper, we propose an embodied agent framework, PhysiAgent, tailored to operate effectively in physical environments. By incorporating monitor, memory, self-reflection mechanisms, and lightweight off-the-shelf toolboxes, PhysiAgent offers an autonomous scaffolding framework to prompt VLMs to organize different components based on real-time proficiency feedback from VLAs to maximally exploit VLAs' capabilities. Experimental results demonstrate significant improvements in task-solving performance on complex real-world robotic tasks, showcasing effective self-regulation of VLMs, coherent tool collaboration, and adaptive evolution of the framework during execution. PhysiAgent makes practical and pioneering efforts to integrate VLMs and VLAs, effectively grounding embodied agent frameworks in real-world settings.

Agricultural visual question answering is essential for providing farmers and researchers with accurate and timely knowledge. However, many existing approaches are predominantly developed for evidence-constrained settings such as text-only queries or single-image cases. This design prevents them from coping with real-world agricultural scenarios that often require multi-image inputs with complementary views across spatial scales, and growth stages. Moreover, limited access to up-to-date external agricultural context makes these systems struggle to adapt when evidence is incomplete. In addition, rigid pipelines often lack systematic quality control. To address this gap, we propose a self-reflective and self-improving multi-agent framework that integrates four roles, the Retriever, the Reflector, the Answerer, and the Improver. They collaborate to enable context enrichment, reflective reasoning, answer drafting, and iterative improvement. A Retriever formulates queries and gathers external information, while a Reflector assesses adequacy and triggers sequential reformulation and renewed retrieval. Two Answerers draft candidate responses in parallel to reduce bias. The Improver refines them through iterative checks while ensuring that information from multiple images is effectively aligned and utilized. Experiments on the AgMMU benchmark show that our framework achieves competitive performance on multi-image agricultural QA.