Graph-based Multi-Agent Systems (MAS) enable complex cyclic workflows but suffer from inefficient static model allocation, where deploying strong models uniformly wastes computation on trivial sub-tasks. We propose CASTER (Context-Aware Strategy for Task Efficient Routing), a lightweight router for dynamic model selection in graph-based MAS. CASTER employs a Dual-Signal Router that combines semantic embeddings with structural meta-features to estimate task difficulty. During training, the router self-optimizes through a Cold Start to Iterative Evolution paradigm, learning from its own routing failures via on-policy negative feedback. Experiments using LLM-as-a-Judge evaluation across Software Engineering, Data Analysis, Scientific Discovery, and Cybersecurity demonstrate that CASTER reduces inference cost by up to 72.4% compared to strong-model baselines while matching their success rates, and consistently outperforms both heuristic routing and FrugalGPT across all domains.
In the rapidly evolving field of Electronic Design Automation (EDA), the deployment of Large Language Models (LLMs) for Register-Transfer Level (RTL) design has emerged as a promising direction. However, silicon-grade correctness remains bottlenecked by: (i) limited test coverage and reliability of simulation-centric evaluation, (ii) regressions and repair hallucinations introduced by iterative debugging, and (iii) semantic drift as intent is reinterpreted across agent handoffs. In this work, we propose Veri-Sure, a multi-agent framework that establishes a design contract to align agents' intent and uses a patching mechanism guided by static dependency slicing to perform precise, localized repairs. By integrating a multi-branch verification pipeline that combines trace-driven temporal analysis with formal verification consisting of assertion-based checking and boolean equivalence proofs, Veri-Sure enables functional correctness beyond pure simulations. We also introduce VerilogEval-v2-EXT, extending the original benchmark with 53 more industrial-grade design tasks and stratified difficulty levels, and show that Veri-Sure achieves state-of-the-art verified-correct RTL code generation performance, surpassing standalone LLMs and prior agentic systems.
Emerging 6G networks rely on complex cross-layer optimization, yet manually translating high-level intents into mathematical formulations remains a bottleneck. While Large Language Models (LLMs) offer promise, monolithic approaches often lack sufficient domain grounding, constraint awareness, and verification capabilities. To address this, we present ComAgent, a multi-LLM agentic AI framework. ComAgent employs a closed-loop Perception-Planning-Action-Reflection cycle, coordinating specialized agents for literature search, coding, and scoring to autonomously generate solver-ready formulations and reproducible simulations. By iteratively decomposing problems and self-correcting errors, the framework effectively bridges the gap between user intent and execution. Evaluations demonstrate that ComAgent achieves expert-comparable performance in complex beamforming optimization and outperforms monolithic LLMs across diverse wireless tasks, highlighting its potential for automating design in emerging wireless networks.
LLM-based agents are becoming central to software engineering tasks, yet evaluating them remains fragmented and largely model-centric. Existing studies overlook how architectural components, such as planners, memory, and tool routers, shape agent behavior, limiting diagnostic power. We propose a lightweight, architecture-informed approach that links agent components to their observable behaviors and to the metrics capable of evaluating them. Our method clarifies what to measure and why, and we illustrate its application through real world agents, enabling more targeted, transparent, and actionable evaluation of LLM-based agents.
Large Language Models (LLMs) have recently empowered agentic frameworks to exhibit advanced reasoning and planning capabilities. However, their integration in robotic control pipelines remains limited in two aspects: (1) prior \ac{llm}-based approaches often lack modular, agentic execution mechanisms, limiting their ability to plan, reflect on outcomes, and revise actions in a closed-loop manner; and (2) existing benchmarks for manipulation tasks focus on low-level control and do not systematically evaluate multistep reasoning and linguistic variation. In this paper, we propose Agentic LLM for Robot Manipulation (ALRM), an LLM-driven agentic framework for robotic manipulation. ALRM integrates policy generation with agentic execution through a ReAct-style reasoning loop, supporting two complementary modes: Code-asPolicy (CaP) for direct executable control code generation, and Tool-as-Policy (TaP) for iterative planning and tool-based action execution. To enable systematic evaluation, we also introduce a novel simulation benchmark comprising 56 tasks across multiple environments, capturing linguistically diverse instructions. Experiments with ten LLMs demonstrate that ALRM provides a scalable, interpretable, and modular approach for bridging natural language reasoning with reliable robotic execution. Results reveal Claude-4.1-Opus as the top closed-source model and Falcon-H1-7B as the top open-source model under CaP.
High-quality evaluation benchmarks are pivotal for deploying Large Language Models (LLMs) in Automated Code Review (ACR). However, existing benchmarks suffer from two critical limitations: first, the lack of multi-language support in repository-level contexts, which restricts the generalizability of evaluation results; second, the reliance on noisy, incomplete ground truth derived from raw Pull Request (PR) comments, which constrains the scope of issue detection. To address these challenges, we introduce AACR-Bench a comprehensive benchmark that provides full cross-file context across multiple programming languages. Unlike traditional datasets, AACR-Bench employs an "AI-assisted, Expert-verified" annotation pipeline to uncover latent defects often overlooked in original PRs, resulting in a 285\% increase in defect coverage. Extensive evaluations of mainstream LLMs on AACR-Bench reveal that previous assessments may have either misjudged or only partially captured model capabilities due to data limitations. Our work establishes a more rigorous standard for ACR evaluation and offers new insights on LLM based ACR, i.e., the granularity/level of context and the choice of retrieval methods significantly impact ACR performance, and this influence varies depending on the LLM, programming language, and the LLM usage paradigm e.g., whether an Agent architecture is employed. The code, data, and other artifacts of our evaluation set are available at https://github.com/alibaba/aacr-bench .
Fully Homomorphic Encryption (FHE) enables computations directly on encrypted data, but its high computational cost remains a significant barrier. Writing efficient FHE code is a complex task requiring cryptographic expertise, and finding the optimal sequence of program transformations is often intractable. In this paper, we propose CHEHAB RL, a novel framework that leverages deep reinforcement learning (RL) to automate FHE code optimization. Instead of relying on predefined heuristics or combinatorial search, our method trains an RL agent to learn an effective policy for applying a sequence of rewriting rules to automatically vectorize scalar FHE code while reducing instruction latency and noise growth. The proposed approach supports the optimization of both structured and unstructured code. To train the agent, we synthesize a diverse dataset of computations using a large language model (LLM). We integrate our proposed approach into the CHEHAB FHE compiler and evaluate it on a suite of benchmarks, comparing its performance against Coyote, a state-of-the-art vectorizing FHE compiler. The results show that our approach generates code that is $5.3\times$ faster in execution, accumulates $2.54\times$ less noise, while the compilation process itself is $27.9\times$ faster than Coyote (geometric means).
As large language models become integral to agentic artificial intelligence systems, their energy demands during inference may pose significant sustainability challenges. This study investigates whether deploying smaller-scale language models can reduce energy consumption without compromising responsiveness and output quality in a multi-agent, real-world environments. We conduct a comparative analysis across language models of varying scales to quantify trade-offs between efficiency and performance. Results show that smaller open-weights models can lower energy usage while preserving task quality. Building on these findings, we propose practical guidelines for sustainable artificial intelligence design, including optimal batch size configuration and computation resource allocation. These insights offer actionable strategies for developing scalable, environmentally responsible artificial intelligence systems.
Large language models are increasingly deployed as multi-agent systems, where specialized roles communicate and collaborate through structured interactions to solve complex tasks that often exceed the capacity of a single agent. However, most existing systems still rely on a fixed role library and an execution-frozen interaction topology, a rigid design choice that frequently leads to task mismatch, prevents timely adaptation when new evidence emerges during reasoning, and further inflates inference cost. We introduce MetaGen, a training-free framework that adapts both the role space and the collaboration topology at inference time, without updating base model weights. MetaGen generates and rewrites query-conditioned role specifications to maintain a controllable dynamic role pool, then instantiates a constrained execution graph around a minimal backbone. During execution, it iteratively updates role prompts and adjusts structural decisions using lightweight feedback signals. Experiments on code generation and multi-step reasoning benchmarks show that MetaGen improves the accuracy and cost tradeoff over strong multi-agent baselines.
While prior work has examined the generation capabilities of Agentic AI systems, little is known about how reviewers respond to AI-authored code in practice. In this paper, we present a large-scale empirical study of code review dynamics in agent-generated PRs. Using a curated subset of the AIDev dataset, we analyze 19,450 inline review comments spanning 3,177 agent-authored PRs from real-world GitHub repositories. We first derive a taxonomy of 12 review comment themes using topic modeling combined with large language model (LLM)-assisted semantic clustering and consolidation. According to this taxonomy, we then investigate whether zero-shot prompts to LLM can reliably annotate review comments. Our evaluation against human annotations shows that open-source LLM achieves reasonably high exact match (78.63%), macro F1 score (0.78), and substantial agreement with human annotators at the review comment level. At the PR level, the LLM also correctly identifies the dominant review theme with 78% Top-1 accuracy and achieves an average Jaccard similarity of 0.76, indicating strong alignment with human judgments. Applying this annotation pipeline at scale, we find that apart from functional correctness and logical changes, reviews of agent-authored PRs predominantly focus on documentation gaps, refactoring needs, styling and formatting issues, with testing and security-related concerns. These findings suggest that while AI agents can accelerate code production, there remain gaps requiring targeted human review oversight.
Most existing memory-enhanced Large Language Model (LLM) approaches implicitly assume that memory validity can be established either through external evaluators that provide task-specific success signals or through internal model cognition, such as reflection, for editing memory entries. However, these assumptions often break down in practical environments with dynamic drifts. We propose the Global Verifier (GLOVE), a framework that introduces a new design dimension for LLM memory systems by establishing a relative notion of truth. Through active probing to detect inconsistencies between retrieved memories and fresh observations, GLOVE enables memory-environment realignment by verifying and updating memory without access to ground-truth supervision or strong reliance on model introspection. We evaluate GLOVE on diverse benchmarks spanning web navigation, planning, and control, augmented with controlled environmental drifts that introduce non-stationarity beyond the original benchmark settings. Our results show that GLOVE substantially improves agent success rates, suggesting a robust pathway to cognitive agents capable of self-evolving.
Recent vision-language models have strong perceptual ability but their implicit reasoning is hard to explain and easily generates hallucinations on complex queries. Compositional methods improve interpretability, but most rely on a single agent or hand-crafted pipeline and cannot decide when to collaborate across complementary agents or compete among overlapping ones. We introduce MATA (Multi-Agent hierarchical Trainable Automaton), a multi-agent system presented as a hierarchical finite-state automaton for visual reasoning whose top-level transitions are chosen by a trainable hyper agent. Each agent corresponds to a state in the hyper automaton, and runs a small rule-based sub-automaton for reliable micro-control. All agents read and write a shared memory, yielding transparent execution history. To supervise the hyper agent's transition policy, we build transition-trajectory trees and transform to memory-to-next-state pairs, forming the MATA-SFT-90K dataset for supervised finetuning (SFT). The finetuned LLM as the transition policy understands the query and the capacity of agents, and it can efficiently choose the optimal agent to solve the task. Across multiple visual reasoning benchmarks, MATA achieves the state-of-the-art results compared with monolithic and compositional baselines. The code and dataset are available at https://github.com/ControlNet/MATA.
Sponge attacks increasingly threaten LLM systems by inducing excessive computation and DoS. Existing defenses either rely on statistical filters that fail on semantically meaningful attacks or use static LLM-based detectors that struggle to adapt as attack strategies evolve. We introduce SHIELD, a multi-agent, auto-healing defense framework centered on a three-stage Defense Agent that integrates semantic similarity retrieval, pattern matching, and LLM-based reasoning. Two auxiliary agents, a Knowledge Updating Agent and a Prompt Optimization Agent, form a closed self-healing loop, when an attack bypasses detection, the system updates an evolving knowledgebase, and refines defense instructions. Extensive experiments show that SHIELD consistently outperforms perplexity-based and standalone LLM defenses, achieving high F1 scores across both non-semantic and semantic sponge attacks, demonstrating the effectiveness of agentic self-healing against evolving resource-exhaustion threats.
Automatically extracting workflows as procedural graphs from natural language is promising yet underexplored, demanding both structural validity and logical alignment. While recent large language models (LLMs) show potential for procedural graph extraction, they often produce ill-formed structures or misinterpret logical flows. We present \model{}, a multi-agent framework that formulates procedural graph extraction as a multi-round reasoning process with dedicated structural and logical refinement. The framework iterates through three stages: (1) a graph extraction phase with the graph builder agent, (2) a structural feedback phase in which a simulation agent diagnoses and explains structural defects, and (3) a logical feedback phase in which a semantic agent aligns semantics between flow logic and linguistic cues in the source text. Important feedback is prioritized and expressed in natural language, which is injected into subsequent prompts, enabling interpretable and controllable refinement. This modular design allows agents to target distinct error types without supervision or parameter updates. Experiments demonstrate that \model{} achieves substantial improvements in both structural correctness and logical consistency over strong baselines.
Recent progress at the intersection of large language models (LLMs) and time series (TS) analysis has revealed both promise and fragility. While LLMs can reason over temporal structure given carefully engineered context, they often struggle with numeric fidelity, modality interference, and principled cross-modal integration. We present TS-Debate, a modality-specialized, collaborative multi-agent debate framework for zero-shot time series reasoning. TS-Debate assigns dedicated expert agents to textual context, visual patterns, and numerical signals, preceded by explicit domain knowledge elicitation, and coordinates their interaction via a structured debate protocol. Reviewer agents evaluate agent claims using a verification-conflict-calibration mechanism, supported by lightweight code execution and numerical lookup for programmatic verification. This architecture preserves modality fidelity, exposes conflicting evidence, and mitigates numeric hallucinations without task-specific fine-tuning. Across 20 tasks spanning three public benchmarks, TS-Debate achieves consistent and significant performance improvements over strong baselines, including standard multimodal debate in which all agents observe all inputs.
Secure code review is critical at the pre-commit stage, where vulnerabilities must be caught early under tight latency and limited-context constraints. Existing SAST-based checks are noisy and often miss immature, context-dependent vulnerabilities, while standalone Large Language Models (LLMs) are constrained by context windows and lack explicit tool use. Agentic AI, which combine LLMs with autonomous decision-making, tool invocation, and code navigation, offer a promising alternative, but their effectiveness for pre-commit secure code review is not yet well understood. In this work, we introduce AgenticSCR, an agentic AI for secure code review for detecting immature vulnerabilities during the pre-commit stage, augmented by security-focused semantic memories. Using our own curated benchmark of immature vulnerabilities, tailored to the pre-commit secure code review, we empirically evaluate how accurate is our AgenticSCR for localizing, detecting, and explaining immature vulnerabilities. Our results show that AgenticSCR achieves at least 153% relatively higher percentage of correct code review comments than the static LLM-based baseline, and also substantially surpasses SAST tools. Moreover, AgenticSCR generates more correct comments in four out of five vulnerability types, consistently and significantly outperforming all other baselines. These findings highlight the importance of Agentic Secure Code Review, paving the way towards an emerging research area of immature vulnerability detection.
Recommendation systems must optimize multiple objectives while satisfying hard business constraints such as fairness and coverage. For example, an e-commerce platform may require every recommendation list to include items from multiple sellers and at least one newly listed product; violating such constraints--even once--is unacceptable in production. Prior work on multi-objective recommendation and recent LLM-based recommender agents largely treat constraints as soft penalties or focus on item scoring and interaction, leading to frequent violations in real-world deployments. How to leverage LLMs for coordinating constrained optimization in recommendation systems remains underexplored. We propose DualAgent-Rec, an LLM-coordinated dual-agent framework for constrained multi-objective e-commerce recommendation. The framework separates optimization into an Exploitation Agent that prioritizes accuracy under hard constraints and an Exploration Agent that promotes diversity through unconstrained Pareto search. An LLM-based coordinator adaptively allocates resources between agents based on optimization progress and constraint satisfaction, while an adaptive epsilon-relaxation mechanism guarantees feasibility of final solutions. Experiments on the Amazon Reviews 2023 dataset demonstrate that DualAgent-Rec achieves 100% constraint satisfaction and improves Pareto hypervolume by 4-6% over strong baselines, while maintaining competitive accuracy-diversity trade-offs. These results indicate that LLMs can act as effective orchestration agents for deployable and constraint-compliant recommendation systems.
Large Language Models (LLMs) are increasingly used to generate natural-language explanations in recommender systems, acting as explanation agents that reason over user behavior histories. While prior work has focused on explanation fluency and relevance under fixed inputs, the robustness of LLM-generated explanations to realistic user behavior noise remains largely unexplored. In real-world web platforms, interaction histories are inherently noisy due to accidental clicks, temporal inconsistencies, missing values, and evolving preferences, raising concerns about explanation stability and user trust. We present RobustExplain, the first systematic evaluation framework for measuring the robustness of LLM-generated recommendation explanations. RobustExplain introduces five realistic user behavior perturbations evaluated across multiple severity levels and a multi-dimensional robustness metric capturing semantic, keyword, structural, and length consistency. Our goal is to establish a principled, task-level evaluation framework and initial robustness baselines, rather than to provide a comprehensive leaderboard across all available LLMs. Experiments on four representative LLMs (7B--70B) show that current models exhibit only moderate robustness, with larger models achieving up to 8% higher stability. Our results establish the first robustness benchmarks for explanation agents and highlight robustness as a critical dimension for trustworthy, agent-driven recommender systems at web scale.
As LLMs increasingly act as autonomous agents in interactive and multi-agent settings, understanding their strategic behavior is critical for safety, coordination, and AI-driven social and economic systems. We investigate how payoff magnitude and linguistic context shape LLM strategies in repeated social dilemmas, using a payoff-scaled Prisoner's Dilemma to isolate sensitivity to incentive strength. Across models and languages, we observe consistent behavioral patterns, including incentive-sensitive conditional strategies and cross-linguistic divergence. To interpret these dynamics, we train supervised classifiers on canonical repeated-game strategies and apply them to LLM decisions, revealing systematic, model- and language-dependent behavioral intentions, with linguistic framing sometimes matching or exceeding architectural effects. Our results provide a unified framework for auditing LLMs as strategic agents and highlight cooperation biases with direct implications for AI governance and multi-agent system design.
We study how to fine-tune LLMs using user-edit deployment data consisting of a set of context, an agent's response, and user edits. This deployment data is naturally generated by users in applications such as LLMs-based writing assistants and coding agents. The _natural_ origin of user edits makes it a desired source for adapting and personalizing LLMs. In this setup, there emerges a unification of various feedback types namely preferences, supervised labels, and cost that are typically studied separately in the literature. In this paper, we initiate the theoretical investigation of learning from user edits. We first derive bounds for learning algorithms that learn from each of these feedback types. We prove that these algorithms have different trade-offs depending upon the user, data distribution, and model class. We then propose a simple ensembling procedure to jointly learn from these feedback types. On two domains adapted from Gao et al. 2024, we show our ensembling procedure outperforms these methods that learn from individual feedback. Further, we show that our proposed procedure can robustly adapt to different user-edit distributions at test time.
Large Language Models (LLMs) are increasingly relied upon for complex workflows, yet their ability to maintain flow of instructions remains underexplored. Existing benchmarks conflate task complexity with structural ordering, making it difficult to isolate the impact of prompt topology on performance. We introduce RIFT, Reordered Instruction Following Testbed, to assess instruction following by disentangling structure from content. Using rephrased Jeopardy! question-answer pairs, we test LLMs across two prompt structures: linear prompts, which progress sequentially, and jumping prompts, which preserve identical content but require non-sequential traversal. Across 10,000 evaluations spanning six state-of-the-art open-source LLMs, accuracy dropped by up to 72% under jumping conditions (compared to baseline), revealing a strong dependence on positional continuity. Error analysis shows that approximately 50% of failures stem from instruction-order violations and semantic drift, indicating that current architectures internalize instruction following as a sequential pattern rather than a reasoning skill. These results reveal structural sensitivity as a fundamental limitation in current architectures, with direct implications for applications requiring non-sequential control flow such as workflow automation and multi-agent systems.
Autonomous unmanned aerial vehicle (UAV) systems are increasingly deployed in safety-critical, networked environments where they must operate reliably in the presence of malicious adversaries. While recent benchmarks have evaluated large language model (LLM)-based UAV agents in reasoning, navigation, and efficiency, systematic assessment of security, resilience, and trust under adversarial conditions remains largely unexplored, particularly in emerging 6G-enabled settings. We introduce $α^{3}$-SecBench, the first large-scale evaluation suite for assessing the security-aware autonomy of LLM-based UAV agents under realistic adversarial interference. Building on multi-turn conversational UAV missions from $α^{3}$-Bench, the framework augments benign episodes with 20,000 validated security overlay attack scenarios targeting seven autonomy layers, including sensing, perception, planning, control, communication, edge/cloud infrastructure, and LLM reasoning. $α^{3}$-SecBench evaluates agents across three orthogonal dimensions: security (attack detection and vulnerability attribution), resilience (safe degradation behavior), and trust (policy-compliant tool usage). We evaluate 23 state-of-the-art LLMs from major industrial providers and leading AI labs using thousands of adversarially augmented UAV episodes sampled from a corpus of 113,475 missions spanning 175 threat types. While many models reliably detect anomalous behavior, effective mitigation, vulnerability attribution, and trustworthy control actions remain inconsistent. Normalized overall scores range from 12.9% to 57.1%, highlighting a significant gap between anomaly detection and security-aware autonomous decision-making. We release $α^{3}$-SecBench on GitHub: https://github.com/maferrag/AlphaSecBench
Emotional Support Conversation requires not only affective expression but also grounded instrumental support to provide trustworthy guidance. However, existing ESC systems and benchmarks largely focus on affective support in text-only settings, overlooking how external tools can enable factual grounding and reduce hallucination in multi-turn emotional support. We introduce TEA-Bench, the first interactive benchmark for evaluating tool-augmented agents in ESC, featuring realistic emotional scenarios, an MCP-style tool environment, and process-level metrics that jointly assess the quality and factual grounding of emotional support. Experiments on nine LLMs show that tool augmentation generally improves emotional support quality and reduces hallucination, but the gains are strongly capacity-dependent: stronger models use tools more selectively and effectively, while weaker models benefit only marginally. We further release TEA-Dialog, a dataset of tool-enhanced ESC dialogues, and find that supervised fine-tuning improves in-distribution support but generalizes poorly. Our results underscore the importance of tool use in building reliable emotional support agents.
Large language models deployed as autonomous agents face critical memory limitations, lacking selective forgetting mechanisms that lead to either catastrophic forgetting at context boundaries or information overload within them. While human memory naturally balances retention and forgetting through adaptive decay processes, current AI systems employ binary retention strategies that preserve everything or lose it entirely. We propose FadeMem, a biologically-inspired agent memory architecture that incorporates active forgetting mechanisms mirroring human cognitive efficiency. FadeMem implements differential decay rates across a dual-layer memory hierarchy, where retention is governed by adaptive exponential decay functions modulated by semantic relevance, access frequency, and temporal patterns. Through LLM-guided conflict resolution and intelligent memory fusion, our system consolidates related information while allowing irrelevant details to fade. Experiments on Multi-Session Chat, LoCoMo, and LTI-Bench demonstrate superior multi-hop reasoning and retrieval with 45\% storage reduction, validating the effectiveness of biologically-inspired forgetting in agent memory systems.
With the rapid expansion of the Internet of Things (IoT) and heterogeneous wireless networks, the Age of Information (AoI) has emerged as a critical metric for evaluating the performance of real-time and personalized systems. While AoI-based random access is essential for next-generation applications such as the low-altitude economy and indoor service robots, existing strategies, ranging from rule-based protocols to learning-based methods, face critical challenges, including idealized model assumptions, slow convergence, and poor generalization. In this article, we propose Reflex-Core, a novel Large Language Model (LLM) agent-based framework for AoI-driven random access in heterogeneous networks. By devising an "Observe-Reflect-Decide-Execute" closed-loop mechanism, this framework integrates Supervised Fine-Tuning (SFT) and Proximal Policy Optimization (PPO) to enable optimal, autonomous access control. Based on the Reflex-Core framework, we develop a Reflexive Multiple Access (RMA) protocol and a priority-based RMA variant for intelligent access control under different heterogeneous network settings. Experimental results demonstrate that in the investigated scenarios, the RMA protocol achieves up to a 14.9% reduction in average AoI compared with existing baselines, while the priority-based version improves the convergence rate by approximately 20%.
While Large Language Model (LLM) agents excel at general tasks, they inherently struggle with continual adaptation due to the frozen weights after deployment. Conventional reinforcement learning (RL) offers a solution but incurs prohibitive computational costs and the risk of catastrophic forgetting. We introduce Just-In-Time Reinforcement Learning (JitRL), a training-free framework that enables test-time policy optimization without any gradient updates. JitRL maintains a dynamic, non-parametric memory of experiences and retrieves relevant trajectories to estimate action advantages on-the-fly. These estimates are then used to directly modulate the LLM's output logits. We theoretically prove that this additive update rule is the exact closed-form solution to the KL-constrained policy optimization objective. Extensive experiments on WebArena and Jericho demonstrate that JitRL establishes a new state-of-the-art among training-free methods. Crucially, JitRL outperforms the performance of computationally expensive fine-tuning methods (e.g., WebRL) while reducing monetary costs by over 30 times, offering a scalable path for continual learning agents. The code is available at https://github.com/liushiliushi/JitRL.
Vision-and-Language Navigation (VLN) requires an embodied agent to navigate in a complex 3D environment according to natural language instructions. Recent progress in large language models (LLMs) has enabled language-driven navigation with improved interpretability. However, most LLM-based agents still rely on single-shot action decisions, where the model must choose one option from noisy, textualized multi-perspective observations. Due to local mismatches and imperfect intermediate reasoning, such decisions can easily deviate from the correct path, leading to error accumulation and reduced reliability in unseen environments. In this paper, we propose DV-VLN, a new VLN framework that follows a generate-then-verify paradigm. DV-VLN first performs parameter-efficient in-domain adaptation of an open-source LLaMA-2 backbone to produce a structured navigational chain-of-thought, and then verifies candidate actions with two complementary channels: True-False Verification (TFV) and Masked-Entity Verification (MEV). DV-VLN selects actions by aggregating verification successes across multiple samples, yielding interpretable scores for reranking. Experiments on R2R, RxR (English subset), and REVERIE show that DV-VLN consistently improves over direct prediction and sampling-only baselines, achieving competitive performance among language-only VLN agents and promising results compared with several cross-modal systems.Code is available at https://github.com/PlumJun/DV-VLN.
Large Language Models (LLMs) struggle to automate real-world vulnerability detection due to two key limitations: the heterogeneity of vulnerability patterns undermines the effectiveness of a single unified model, and manual prompt engineering for massive weakness categories is unscalable. To address these challenges, we propose \textbf{MulVul}, a retrieval-augmented multi-agent framework designed for precise and broad-coverage vulnerability detection. MulVul adopts a coarse-to-fine strategy: a \emph{Router} agent first predicts the top-$k$ coarse categories and then forwards the input to specialized \emph{Detector} agents, which identify the exact vulnerability types. Both agents are equipped with retrieval tools to actively source evidence from vulnerability knowledge bases to mitigate hallucinations. Crucially, to automate the generation of specialized prompts, we design \emph{Cross-Model Prompt Evolution}, a prompt optimization mechanism where a generator LLM iteratively refines candidate prompts while a distinct executor LLM validates their effectiveness. This decoupling mitigates the self-correction bias inherent in single-model optimization. Evaluated on 130 CWE types, MulVul achieves 34.79\% Macro-F1, outperforming the best baseline by 41.5\%. Ablation studies validate cross-model prompt evolution, which boosts performance by 51.6\% over manual prompts by effectively handling diverse vulnerability patterns.
Recently, the frontier of Large Language Model (LLM) capabilities has shifted from single-turn code generation to agentic software engineering-a paradigm where models autonomously navigate, edit, and test complex repositories. While post-training methods have become the de facto approach for code agents, **agentic mid-training**-mid-training (MT) on large-scale data that mirrors authentic agentic workflows-remains critically underexplored due to substantial resource requirements, despite offering a more scalable path to instilling foundational agentic behaviors than relying solely on expensive reinforcement learning. A central challenge in realizing effective agentic mid-training is the distribution mismatch between static training data and the dynamic, feedback-rich environment of real development. To address this, we present a systematic study of agentic mid-training, establishing both the data synthesis principles and training methodology for effective agent development at scale. Central to our approach is **agent-native data**-supervision comprising two complementary types of trajectories: **contextually-native trajectories** that preserve the complete information flow an agent experiences, offering broad coverage and diversity; and **environmentally-native trajectories** collected from executable repositories where observations stem from actual tool invocations and test executions, providing depth and interaction authenticity. We verify the model's agentic capabilities on `SWE-Bench Verified`. We demonstrate our superiority over the previous open software engineering mid-training recipe `Kimi-Dev` under two post-training settings with an aligned base model and agentic scaffold, while using less than half mid-training tokens (73.1B). Besides relative advantage, our best performing 32B and 72B models achieve **56.1%** and **58.5%** resolution rates, respectively, which are ...
Existing automated attack suites operate as static ensembles with fixed sequences, lacking strategic adaptation and semantic awareness. This paper introduces the Agentic Reasoning for Methods Orchestration and Reparameterization (ARMOR) framework to address these limitations. ARMOR orchestrates three canonical adversarial primitives, Carlini-Wagner (CW), Jacobian-based Saliency Map Attack (JSMA), and Spatially Transformed Attacks (STA) via Vision Language Models (VLM)-guided agents that collaboratively generate and synthesize perturbations through a shared ``Mixing Desk". Large Language Models (LLMs) adaptively tune and reparameterize parallel attack agents in a real-time, closed-loop system that exploits image-specific semantic vulnerabilities. On standard benchmarks, ARMOR achieves improved cross-architecture transfer and reliably fools both settings, delivering a blended output for blind targets and selecting the best attack or blended attacks for white-box targets using a confidence-and-SSIM score.