LLM-based role-playing has rapidly improved in fidelity, yet stronger adherence to persona constraints commonly increases vulnerability to jailbreak attacks, especially for risky or negative personas. Most prior work mitigates this issue with training-time solutions (e.g., data curation or alignment-oriented regularization). However, these approaches are costly to maintain as personas and attack strategies evolve, can degrade in-character behavior, and are typically infeasible for frontier closed-weight LLMs. We propose a training-free Dual-Cycle Adversarial Self-Evolution framework with two coupled cycles. A Persona-Targeted Attacker Cycle synthesizes progressively stronger jailbreak prompts, while a Role-Playing Defender Cycle distills observed failures into a hierarchical knowledge base of (i) global safety rules, (ii) persona-grounded constraints, and (iii) safe in-character exemplars. At inference time, the Defender retrieves and composes structured knowledge from this hierarchy to guide generation, producing responses that remain faithful to the target persona while satisfying safety constraints. Extensive experiments across multiple proprietary LLMs show consistent gains over strong baselines on both role fidelity and jailbreak resistance, and robust generalization to unseen personas and attack prompts.
论文检索
输入标题、作者或关键词，从 2,254 篇学术成果中精准定位
Deep multi-view clustering draws plentiful attention in various domains, owing to remarkable performance in learning patterns from complementary information of multi-view data. However, previous methods encounter two challenges. They utilize a single pre-defined clustering strategy to perceive diverse structures from data in multiple views subject to heterogeneous distributions, failing to fully capture intricate complementary structures. They leverage either the feature fusion or the result fusion in clustering, which cannot fully integrate complementary information. Therefore, a decoupled multi-agent actor-critic (PRIME) is proposed via defining multi-view clustering as a partially observable Markov game, which establishes a dynamic trial-and-error assignment process of samples in a decentralized perception with centralized learning framework to adaptively learn the optimal clustering strategy. In PRIME, an actor leverages the policy gradient paradigm to independently implement a Markov decision process of data partition in a view, which fully explores data structures to tailor a clustering sub-policy for a view. Meanwhile, a critic utilizes the value function paradigm to centrally guide the Markov game among actors in different views, which constructs both feature and result fusion to progressively enhance complementary knowledge integration for robust clustering results. Extensive experiments on 6 benchmark datasets verify the superiority of PRIME against 10 methods.
Multi-Agent Path Finding (MAPF) seeks collision-free paths for teams of agents and has a wide range of practical applications. LaCAM*, an anytime configuration-based solver, currently represents the state-of-the-art. Recent work has explored using guidance paths to steer LaCAM* toward configurations that avoid traffic congestion, thereby improving solution quality. However, existing approaches rely on Frank–Wolfe–style optimisation to repeatedly invoke single-agent search before executing LaCAM*, which creates a large computational overhead in large-scale problems. The guide path is also static, which is only helpful for finding the first solution in LaCAM*. To overcome this problem, we propose a new approach that exploits LaCAM*’s ability to construct a dynamic, lightweight traffic map during LaCAM*'s search. Experiments show that our method achieves higher solution quality than state-of-the-art guidance-path approaches in two variants of MAPF problems.
This paper studies a risk-sensitive formulation of the multi-robot search problem, termed multi-robot mean-standard deviation search (MuRMSS), in which a team of robots cooperatively search for a moving target by minimizing a linear combination of the mean and standard deviation of search time. However, the standard deviation term is inherently non-additive, making it difficult to estimate, incompatible with canonical multi-robot search algorithms, and preventing consistent decomposition into individual robot utilities, which is essential for scalable multi-robot cooperation. In view of these challenges, we propose MV-FAC, which comprises a mean-variance temporal-difference module that jointly learns the mean and variance of search time, a factorization module that decomposes them into individual utilities, and a decentralized policy optimization module that minimizes each robot’s individual mean-std objective. We further establish and prove the mean-std individual global minimization (MS-IGM) theorem, thereby ensuring consistency between individual- and team-level objectives. Extensive simulation studies on standard multi-robot search benchmarks demonstrate that MV-FAC achieves the best overall mean-std search-time performance. We also validate MV-FAC's practicality by deploying it on a physical multi-robot system for moving target search in a real-world building environment.
AI-driven survey generation has advanced rapidly, yet related work generation (RWG) remains relatively underexplored. Unlike surveys that provide broad literature overviews, RWG synthesizes prior studies for a single focal paper, requiring contextual fit, cross-paper comparison, and accurate attribution. To address this gap, we propose MA-RWG, a fully automated multi-agent framework that generates polished related work sections from only a title and abstract. MA-RWG first retrieves high-quality candidate papers through semantic retrieval, optionally enhanced with a diversity-aware term. It then coordinates four specialized agents for summarization, organization, integration, and fact checking, enabling DAG-based taxonomy construction, feedback-guided refinement, and dual-model verification. For evaluation, we introduce a dedicated benchmark for paper-specific related work generation, covering generation quality, citation quality, and claim-level semantic similarity. Experimental results show that MA-RWG outperforms RAG-based baselines and survey-oriented agentic methods on the RWG task. Further ablation and cross-domain experiments demonstrate the soundness and robustness of the proposed framework.
Reward specification plays a central role in reinforcement learning (RL), guiding the agent’s behavior. To express non-Markovian rewards, formalisms such as reward machines have been introduced to capture dependencies on histories. However, traditional reward machines lack the ability to model precise timing constraints, limiting their use in time-sensitive applications. In this paper, we propose timed reward machines (TRMs), which are an extension of reward machines that incorporate timing constraints into the reward structure. TRMs enable more expressive specifications with tunable reward logic, for example, imposing costs for delays and granting rewards for timely actions. We study model-free RL frameworks (i.e., tabular Q-learning) for learning optimal policies with TRMs under digital and real-time semantics. Our algorithms integrate the TRM into learning via abstractions of timed automata and employ counterfactual-imagining heuristics that exploit the TRM's structure to improve search. Experimentally, we demonstrate that our algorithm learns policies that achieve high rewards while satisfying the timing constraints specified by the TRM on popular RL benchmarks.
Empowering Precise Embodied Agents with Executable Analytic Concepts as Semantic-Physical Blueprints
A core challenge for embodied agents is the ``semantic-to-physical gap"—the difficulty of mapping symbolic reasoning to precise execution. While Vision-Language Models (VLMs) enhance agent task planning, they often fail in problem classes requiring accurate alignment between functional geometry and physical constraints, such as articulated object manipulation or precision assembly. To address these challenges, we propose GRACE, an agent framework that adopts Executable Analytic Concepts (EAC) as a core knowledge annotation paradigm for object understanding. Under this paradigm, the agent does not merely perceive objects as unstructured visual data; instead, it interprets and annotates them as ``Semantic-Physical Blueprints", which provide a structured cognitive representation that encodes geometric primitives, mechanical affordances, and manipulation constraints. Central to our framework is a policy scaffolding mechanism, which allows the agent to dynamically ground VLM-based insights into these instantiated blueprints. This enables the agent to model and resolve complex decision-making tasks involving parameterized object descriptions and constrained motion planning. Experimental results demonstrate that agents utilizing this paradigm achieve high robustness in complex manipulation tasks. Furthermore, we demonstrate that GRACE supports automated concept discovery, offering a scalable and modular solution for high-precision embodied intelligence.
Unmanned aerial vehicle swarms in pursuit-evasion requires encirclement efficiency while maintaining safety constraints, facing a critical safety-efficiency trade-off. Existing safe multi-agent reinforcement learning (MARL) methods often yield either unsafe task policies or conservative policies. This is challenging since forward feasible safety under dense interactions requires online safety preview. To address this issue, we propose Safety-Constrained Online Preview Enforcement (SCOPE), a MARL-based algorithm that balances encirclement efficiency and safety by short-horizon preview and safety enforcement. SCOPE learns an online safety-preview dynamics model that rolls out future trajectories to inform encirclement decisions checking. By proposing preview-fused actor-critic, SCOPE uses short-horizon previews for efficient encirclement and less unsafe behavior. Hierarchical safety enforcement performs safety look-ahead and online action correction to maintain forward feasible safety. Experiments show that SCOPE better balances encirclement efficiency and safety than safe MARL baselines, maintaining average encirclement time while reducing the average agent cost by 65.6%. Code could be found at https://github.com/98177qdn/SCOPE.
TD(λ) in value-based MARL algorithms or the Temporal Difference critic learning in Actor-Critic-based (AC-based) algorithms synergistically integrate elements from Monte-Carlo simulation and Q function bootstrapping via dynamic programming, which effectively addresses the inherent bias-variance trade-off in value estimation. Based on that, some recent works link the adaptive λ value to the policy distribution in the single-agent reinforcement learning area. However, because of the large joint action space from multiple agents and the limited transition data in Multi-agent Reinforcement Learning, the policy distribution is infeasible to calculate statistically. To solve the policy distribution calculation problem in MARL settings, we employ a parametric likelihood-free density ratio estimator with two replay buffers instead of calculating statistically. The two replay buffers of different sizes respectively store the historical trajectories that represent the data distribution of the past and current policies. Based on the estimator, we assign Adaptive TD(λ), ATD(λ), values to state-action pairs based on their likelihood under the stationary distribution of the current policy. We apply the proposed method on two competitive baseline methods, QMIX for value-based algorithms, and MAPPO for AC-based algorithms, over SMAC benchmarks and Gfootball academy scenarios, and demonstrate consistently competitive or superior performance compared to other baseline approaches with static λ values.
We study influence maximization in general stochastic models, the observed cascades model, and the independent cascade (IC) model. For general stochastic models with only black-box sample access, we introduce a low-adaptivity optimization framework that improves sample complexity and running time over the prior work and is instrumental to all our results. We further introduce an adaptive algorithm guided by empirical variance, avoiding pessimistic worst-case bounds. Combining our optimization framework with sketching, we obtain the first algorithm with provable guarantees and nearly-linear running time for influence maximization on observed cascades, optimal up to logarithmic factors. For IC, we prove a novel tail bound replacing a factor n with 𝜏 (the number of diffusion steps) in sample complexity, improving over prior work when 𝜏 is small, as is common due to small-world phenomena. Experiments confirm substantial speedups while maintaining solution quality.
Modern AI-driven systems rely on large populations of autonomous agents that make decentralized routing decisions under uncertainty, where rare but severe tail latency can critically degrade quality of experience, safety, and reliability. To model agents’ aversion to such tail latency, we study nonatomic selfish routing games in which agents minimize the Conditional Value-at-Risk (CVaR) of path latency. CVaR explicitly captures both the likelihood and severity of tail latency, but its inherent nonadditivity across network edges poses a fundamental challenge. We address it by identifying a worst-case dependence structure—tail risk concentration—under which tail latency across network edges is synchronized. We show that CVaR penalizes this dependence structure and becomes additive under worst-case tail dependence, which enables tight inefficiency analysis. To quantify the resulting inefficiency induced by risk-aversion, we adopt the price of risk aversion (PRA), defined as the worst-case ratio between the total system cost at a risk-averse equilibrium and that at a risk-neutral equilibrium. We show that, for arbitrary latency functions and general network topologies, the PRA under CVaR admits a tight upper bound that grows linearly with both the network size and the maximum edge-level upper-tail cost. We further prove that this bound is tight by constructing a family of Braess-type networks that achieve a matching lower bound. These results provide the first tight worst-case inefficiency bound for CVaR-based selfish routing and offer insights into how tail-risk-averse decision making by autonomous agents amplifies congestion externalities in large-scale multi-agent systems.
Parameter sharing is a central design choice in cooperative multi-agent reinforcement learning, yet it fundamentally conflicts with the need for role specialization in heterogeneous cooperative environments. Existing role-based methods typically learn monolithic role representations, which often suffer from gradient interference and fail to capture the compositional structure of complex behaviors. Inspired by Trait Theory, we propose DEcompose and COnstruct Roles (DECOR), a framework that models agent roles as dynamic compositions of orthogonal behavioral traits. DECOR introduces an orthogonal Mixture-of-Experts architecture to decompose behaviors into independent traits, mitigating destructive gradient interference under parameter sharing, and a group-consensus guided mechanism to extract team-level tactical intents that guide role composition.Experiments on multiple benchmarks demonstrate that DECOR consistently improves sample efficiency and overall performance over existing related methods.
Agents implemented using Large Language Models (LLMs) offer novel solutions for tasks such as document summarization. However, single-agent systems, limited by their own knowledge base, often exhibit information omissions or inconsistencies with the facts, while multi-agent systems lacking effective organization can fall into the trap of social cognitive defects such as flattery and premature consensus. Inspired by the U.S. jury system, we propose JURIS, a judicial-decision-inspired multi-agent collaborative framework. Specifically, the document summarization process simulates a lawsuit scenario: multiple generator agents condense the target text into multiple sentences from different perspectives, much like lawyers on both sides providing different evidence; multiple decision-making agents consider the overall picture based on defense and voting mechanisms to select candidate sentences, much like a jury adopting different evidence; finally, a chief editor agent compiles a summary of all selected sentences, much like a secretary summarizing a plan and a judge giving a final verdict. Extensive experiments on in-domain news and cross-domain benchmarks demonstrate that JURIS consistently and significantly outperforms strong single-agent and multi-agent baselines across automatic evaluation metrics, multi-dimensional quality assessments, and human judgments, validating the effectiveness of decision-driven structured multi-agent collaboration for document summarization.
Bound-Independent Pruning (BIP) is a powerful technique for accelerating tree-based complete search algorithms for Distributed Constraint Optimization Problems (DCOPs) by pruning dominated regions of the search space using only local information. However, BIP fundamentally relies on constructing a context-dependent dominating space through joint optimization over local constraints, incurring exponential computational and storage complexity that limits its practical scalability. To address this limitation, we propose DR-BIP, a decoupled and sound reformulation of BIP that enables efficient identification of dominated subspaces without explicitly computing the dominating space. By reformulating dominated-subspace detection into pairwise dominance tests and decoupling them across independent constraints, DR-BIP eliminates joint optimization and reduces both computational and storage complexity from exponential to polynomial. The resulting dominance components can be precomputed and reused across context changes, further improving efficiency. We formally prove the correctness of DR-BIP and integrate it into several state-of-the-art tree-based complete DCOP algorithms. Extensive empirical evaluation on standard benchmarks confirms that DR-BIP consistently outperforms BIP, significantly reducing both computation time and communication overhead.
Existing Autonomous Mobility-on-Demand (AMoD) systems and demand-responsive algorithms are designed to adaptively respond to traffic demands, enhancing traffic service quality and profitability. However, such approaches may exacerbate traffic congestion by concentrating vehicles in high-demand areas. In addition, repeated braking, acceleration, and low-speed driving in traffic jams lead to substantial increases in emissions. Moreover, existing Deep Reinforcement Learning (DRL)-based approaches fail to address the instability of cooperative learning in environments with highly variable rewards, such as carbon emissions. To address these issues, we propose the Spatio-Temporal Attention Rebalancing (STAR) framework, leveraging an encoder-decoder architecture. In the proposed framework, we maximize the number of requests served and minimize CO₂ emissions, while ensuring high service quality by limiting maximum travel delays and waiting times for passengers. To evaluate the proposed framework, we conduct simulations in realistic urban traffic scenarios. Experimental results demonstrate that our framework consistently outperforms existing baselines. In a large-scale scenario with a fleet of one hundred vehicles, our approach improves the service rate by up to 10.1% and reduces CO₂ emissions per passenger by up to 69.6% compared to the baseline methods. The proposed framework and baselines are publicly available at https://github.com/2jungeuni/eco-friendly-fleet-rebalancing.
We introduce Hedonic Project Games, a model in which agents choose projects with divisible rewards while holding subjective preferences over coalition composition. This framework captures a fundamental trade-off absent from existing models: agents care simultaneously about who they collaborate with and what they work on. We study three stability notions: classical Nash Stability and two refinements, Joining Stability and Leaving Stability, which account for the welfare of both the deviating agent and the affected coalition members. We evaluate the efficiency of stable outcomes using the Price of Anarchy and Price of Stability, comparing the social welfare of stable outcomes to that of an optimal allocation. While stable outcomes may not exist in general, we identify broad and natural preference classes in which stability and efficiency improve significantly. In particular, under monotonic-decreasing preferences in coalition size, Nash and joining stability coincide and are guaranteed to exist, whereas leaving stability may fail. Under per-capita non-decreasing preferences, socially optimal outcomes are always Nash stable and coincide with leaving stability, although equilibrium inefficiency remains unbounded. Experiments on synthetic and real-world data support the theoretical efficiency results.
Hedonic games are a central model of coalition formation, yet most of their general subclasses are marked by negative results: stable outcomes often fail to exist, and deciding their existence is typically computationally hard. The most notable exception is the class of hedonic games with the common ranking property (HGCRP), a nontrivial subclass that guarantees both the existence and tractability of stable partitions. The common ranking property implies the top-coalition property, which in turn implies the weak top-coalition property, forming a natural hierarchy of increasingly general domains. In this paper, we extend the frontier of strong existence and tractability results beyond the HGCRP to hedonic games with the top-coalition property (HGTCP) and hedonic games with the weak top-coalition property (HGWTCP). We show that every HGWTCP instance admits a strong individually stable (SIS) partition that can be computed in polynomial time, and prove that our polynomial-time algorithm generates a partition that is both SIS and Pareto optimal (PO) if preferences are strict. These results show that strong stability and tractability results persist well beyond the common ranking framework. We further show that a contractually Nash stable (CNS) partition may fail to exist even in HGTCP, revealing a sharp contrast with HGCRP, where the existence of partitions that are both CNS and PO is guaranteed. Taken together, these results provide a comprehensive characterization of stability and efficiency in top-coalition-based hedonic games, mapping how stability guarantees evolve from HGCRP to HGWTCP.
QiMeng-VPID: Verification-Grounded Port-Level Iterative Decomposition for Complex Verilog Generation
While Large Language Models (LLMs) have shown promise in translating natural-language specifications to Register-Transfer Level (RTL) designs, they often fail on complex, port-rich IPs. Existing frameworks typically separate generation from debugging, relying on static decomposition and iterative repair, which is hard to verify and yields unstable, inefficient maintenance. In this work, we propose VPID, a multi-agent framework for generating complex Verilog that achieves monotonic functional improvement. Given RTL’s inherent concurrency and the alignment between verification and port-level behavior, our key insight is to treat ports as verifiable boundaries for dynamic decomposition, enabling fine-grained analysis to pinpoint root causes and guide targeted debugging. Specifically, we implement a behavior locking mechanism that preserves the behavior of verified ports to ensure monotonicity, preventing regressions in correct functionalities. To accelerate convergence, we introduce an experience-guided refinement strategy that distills historical waveform mismatches into constraints, guiding the targeted debugging for the unverified ports. Together with precise Abstract Syntax Tree (AST)-based code extraction, these mechanisms enable an efficient incremental generation workflow. Experiments on RealBench demonstrate that VPID outperforms both one-pass general-purpose LLMs and existing agent-based frameworks in both syntax and functional correctness, presenting a robust approach for automating Verilog generation for complex RTL designs.
Real-world multi-agent systems, from traffic coordination to resource allocation, are often modeled as general-sum games where individual incentives conflict with collective welfare. In these settings, the central challenge is not merely finding an equilibrium, but selecting socially desirable outcomes among many suboptimal Nash equilibria. Standard deep multi-agent reinforcement learning (MARL) methods struggle with this problem, as value-decomposition approaches are constrained by monotonicity assumptions and policy-gradient methods often converge to stable but socially inefficient equilibria. To address this limitation, we propose Phi-Actor-Critic (Phi-AC), a framework that leverages swap regret minimization to steer learning toward high-welfare correlated equilibria (CE). To make counterfactual regret estimation tractable in deep MARL, Phi-AC employs a centralized attention critic that predicts vector-valued regrets in a single forward pass, avoiding computationally expensive counterfactual simulations. We further introduce a Lagrangian-based equilibrium selection mechanism that optimizes social welfare while enforcing stability through regret constraints. Experiments on matrix games, Multi-Agent Particle Environments (MPE), and the Melting Pot Harvest scenario demonstrate that Phi-AC learns efficient and stable coordination strategies across diverse mixed-motive settings while maintaining high collective return and competitive fairness.
Retrosynthesis prediction is a cornerstone of drug discovery, enabling the synthesis of novel therapeutic candidates. However, current deep learning models falter when navigating the unexplored chemical space essential for innovation. In these realistic scenarios, models face a challenging mixed out-of-distribution (OOD) shift: they must handle both novel molecular scaffolds (covariate shift) and unseen reaction templates (label shift), leading to severe performance degradation. To address this, we propose AgentRetro, a framework integrating spectral domain generalization with Large Language Model (LLM) agents. It features a Spectral Domain Enhancer (SDE) that partitions chemical space via spectral clustering to capture diverse domain structures, and a Multi-Knowledge Agent (MKA) that enriches data with LLM-generated OOD reactions and textual rationales. These components are unified by a dual training strategy: meta-learning for template adaptability and adversarial learning for structural invariance. Crucially, our analysis reveals that explicitly decoupling structural invariance from mechanistic adaptability is essential for overcoming the interference between conflicting distribution shifts. Experiments show AgentRetro consistently improves state-of-the-art baselines, notably boosting EditRetro’s OOD Top-10 accuracy from 41.7% to 50.1%. The source code is available at https://github.com/jiahangshen/IJCAI26-AgentRetro.