arXiv:2603.11330v1 Announce Type: new Abstract: Data-driven discovery of governing equations from time-series data provides a powerful framework for understanding complex biological systems. Library-based approaches that use sparse regression over candidate functions have shown considerable promise, but they face a critical challenge when candidate functions become strongly correlated: numerical ill-conditioning. Poor or restricted sampling, together with […]
WebWeaver: Breaking Topology Confidentiality in LLM Multi-Agent Systems with Stealthy Context-Based Inference
arXiv:2603.11132v1 Announce Type: cross Abstract: Communication topology is a critical factor in the utility and safety of LLM-based multi-agent systems (LLM-MAS), making it a high-value intellectual property (IP) whose confidentiality remains insufficiently studied. % Existing topology inference attempts rely on impractical assumptions, including control over the administrative agent and direct identity queries via jailbreaks, which […]
From Entity-Centric to Goal-Oriented Graphs: Enhancing LLM Knowledge Retrieval in Minecraft
arXiv:2505.18607v2 Announce Type: replace Abstract: Large Language Models (LLMs) demonstrate impressive general capabilities but often struggle with step-by-step procedural reasoning, a critical challenge in complex interactive environments. While retrieval-augmented methods like GraphRAG attempt to bridge this gap, their fragmented entity-relation graphs hinder the construction of coherent, multi-step plans. In this paper, we propose a novel […]
A Simple Efficiency Incremental Learning Framework via Vision-Language Model with Nonlinear Multi-Adapters
arXiv:2603.11211v1 Announce Type: cross Abstract: Incremental Learning (IL) aims to learn new tasks while preserving previously acquired knowledge. Integrating the zero-shot learning capabilities of pre-trained vision-language models into IL methods has marked a significant advancement. However, these methods face three primary challenges: (1) the need for improved training efficiency; (2) reliance on a memory bank […]
LLM-Augmented Digital Twin for Policy Evaluation in Short-Video Platforms
arXiv:2603.11333v1 Announce Type: new Abstract: Short-video platforms are closed-loop, human-in-the-loop ecosystems where platform policy, creator incentives, and user behavior co-evolve. This feedback structure makes counterfactual policy evaluation difficult in production, especially for long-horizon and distributional outcomes. The challenge is amplified as platforms deploy AI tools that change what content enters the system, how agents adapt, […]
Artificial Intelligence for Sentiment Analysis of Persian Poetry
arXiv:2603.11254v1 Announce Type: cross Abstract: Recent advancements of the Artificial Intelligence (AI) have led to the development of large language models (LLMs) that are capable of understanding, analysing, and creating textual data. These language models open a significant opportunity in analyzing the literature and more specifically poetry. In the present work, we employ multiple Bidirectional […]
Consistency of Large Reasoning Models Under Multi-Turn Attacks
arXiv:2602.13093v3 Announce Type: replace Abstract: Large reasoning models with reasoning capabilities achieve state-of-the-art performance on complex tasks, but their robustness under multi-turn adversarial pressure remains underexplored. We evaluate nine frontier reasoning models under adversarial attacks. Our findings reveal that reasoning confers meaningful but incomplete robustness: most reasoning models studied significantly outperform instruction-tuned baselines, yet all […]
Hindsight-Anchored Policy Optimization: Turning Failure into Feedback in Sparse Reward Settings
arXiv:2603.11321v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for post-training reasoning models. However, group-based methods such as Group Relative Policy Optimization (GRPO) face a critical dilemma in sparse-reward settings: pure Reinforcement Learning (RL) suffers from advantage collapse and high-variance gradient estimation, while mixed-policy optimization introduces persistent […]
RewardHackingAgents: Benchmarking Evaluation Integrity for LLM ML-Engineering Agents
arXiv:2603.11337v1 Announce Type: new Abstract: LLM agents increasingly perform end-to-end ML engineering tasks where success is judged by a single scalar test metric. This creates a structural vulnerability: an agent can increase the reported score by compromising the evaluation pipeline rather than improving the model. We introduce RewardHackingAgents, a workspace-based benchmark that makes two compromise […]
Novelty Adaptation Through Hybrid Large Language Model (LLM)-Symbolic Planning and LLM-guided Reinforcement Learning
arXiv:2603.11351v1 Announce Type: cross Abstract: In dynamic open-world environments, autonomous agents often encounter novelties that hinder their ability to find plans to achieve their goals. Specifically, traditional symbolic planners fail to generate plans when the robot’s planning domain lacks the operators that enable it to interact appropriately with novel objects in the environment. We propose […]
Enhancing Heterogeneous Multi-Agent Cooperation in Decentralized MARL via GNN-driven Intrinsic Rewards
arXiv:2408.06503v4 Announce Type: replace-cross Abstract: Multi-agent Reinforcement Learning (MARL) is emerging as a key framework for various sequential decision-making and control tasks. Unlike their single-agent counterparts, multi-agent systems necessitate successful cooperation among the agents. The deployment of these systems in real-world scenarios often requires decentralized training, a diverse set of agents, and learning from infrequent […]
Vision-Based Hand Shadowing for Robotic Manipulation via Inverse Kinematics
arXiv:2603.11383v1 Announce Type: cross Abstract: Teleoperation of low-cost robotic manipulators remains challenging due to the complexity of mapping human hand articulations to robot joint commands. We present an offline hand-shadowing and retargeting pipeline from a single egocentric RGB-D camera mounted on 3D-printed glasses. The pipeline detects 21 hand landmarks per hand using MediaPipe Hands, deprojects […]