arXiv AI
Jun 9
OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics
arXiv:2606. 09826v1 Announce Type: cross Abstract: Vision-language model (VLM) agents are increasingly deployed in interactive game environments.
AI agents
Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv AI
Jun 9
Advancing Mathematics Research with AI-Driven Formal Proof Search
arXiv:2605. 22763v2 Announce Type: replace Abstract: Large language models (LLMs) increasingly excel at mathematical reasoning, but their unreliability limits their utility in mathematics research.
arXiv AI
Jun 9
MetaEvo: A Meta-Optimization Framework for Experience-Driven Agent Evolution
arXiv:2606. 07603v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit strong reasoning capabilities, yet most LLM-based agents are statically deployed and unable to improve through task interactions.
arXiv AI
Jun 9
WhiFlash: Accelerating Speculative Decoding with Token-Level Cross-Paradigm Routing
arXiv:2606. 07710v1 Announce Type: cross Abstract: The autoregressive nature of large language models (LLMs) remains a significant bottleneck for inference, particularly in complex agentic workloads.
arXiv AI
Jun 9
ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning
arXiv:2605. 16309v2 Announce Type: replace Abstract: LLM-based agents can recover from individual execution errors, yet they repeatedly fail on the same fault when the underlying process knowledge--operator schemas, preconditions, and constraints--remains unrepaired.
arXiv AI
Jun 9
From Statute to Control Flow: Span-Grounded Deontic Trees for Defeasible Scope Parsing
arXiv:2606. 08932v1 Announce Type: cross Abstract: Rule-following agents tasked with executing policies and regulations often fail via Silent Scope Omission (SSO): a model applies a general rule but silently drops nested exceptions or counter-exceptions, producing outputs that appear compliant yet break on important edge cases.
arXiv AI
Jun 9
Automated Framework to Evaluate and Harden LLM System Instructions against Encoding Attacks
arXiv:2604. 01039v2 Announce Type: replace-cross Abstract: System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications.
arXiv AI
Jun 9
From Validator Selection to Portfolio Collection Optimization in Proof-of-Stake Blockchains
arXiv:2606. 08282v1 Announce Type: new Abstract: We consider a problem arising in proof-of-stake blockchain environments, where agents called nominators select validators - entities responsible for maintaining the blockchain's physical infrastructure.
arXiv AI
Jun 9
Exploring Autonomous Agentic Data Engineering for Model Specialization
arXiv:2605. 30407v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated strong performance on general tasks, while often struggling to adapt to specialized domains without high-quality domain-specific data.
arXiv AI
Jun 9
CalBench: Evaluating Coordination-Privacy Trade-offs in Multi-Agent LLMs
arXiv:2605. 09823v3 Announce Type: replace-cross Abstract: Personal AI assistants are beginning to act as delegates with access to calendars, inboxes, and user preferences.
arXiv AI
Jun 9
SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research
arXiv:2606. 09730v1 Announce Type: new Abstract: Large language models are increasingly expected to handle complex, long-horizon real-world tasks whose context demands can grow without bound, yet model context windows remain inherently finite.
arXiv AI
Jun 9
Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directions
arXiv:2604. 08304v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) extends large language models (LLMs) with external knowledge, but this access path also introduces security risks that existing work often conflates with inherent LLM flaws.
arXiv Machine Learning
Jun 9
Formalizing Learning from Language Feedback with Provable Guarantees
arXiv:2506. 10341v2 Announce Type: replace Abstract: Interactively learning from observation and language feedback is an increasingly studied area driven by the emergence of large language model (LLM) agents.
arXiv AI
Jun 9
IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment
arXiv:2606. 08016v1 Announce Type: cross Abstract: Current image editing software often hinges on fixed filters or expert tuning, leaving a gap between amateur users' intent and outcomes.
arXiv AI
Jun 9
MBABench: Evaluating LLM Agents on End-to-End Spreadsheet Tasks in Finance
arXiv:2605. 22664v2 Announce Type: replace Abstract: LLM agents are increasingly expected to carry out end-to-end workflows, producing complete artifacts from high-level user instructions.
arXiv AI
Jun 9
Principled Agent Debate: Adversarial Arbitration for Sycophancy Reduction in Large Language Models
arXiv:2606. 07532v1 Announce Type: cross Abstract: RLHF-trained models are systematically biased toward agreement over accuracy, a structural property of the training process.
arXiv AI
Jun 9
Agent Economics: An Entropy-Controlled Pluralistic Alignment Framework for Preventing Artificial Hivemind in Autonomous Agents
arXiv:2606. 09039v1 Announce Type: new Abstract: This study proposes the Behavioral Protocol Framework (BPF), an entropy-controlled pluralistic alignment framework designed to address two critical challenges in autonomous agent economies: the hivemind effect arising from excessive strategic convergence among agents and the lack of transparency in autonomous decision-making processes.
arXiv AI
Jun 9
Skill Retrieval Augmentation for Agentic AI
arXiv:2604. 24594v3 Announce Type: replace-cross Abstract: As large language models (LLMs) evolve into agentic problem solvers, they increasingly rely on external, reusable skills to handle tasks beyond their native parametric capabilities.
arXiv Machine Learning
Jun 9
RepoLaunch: Automating Build and Management of Code Repositories across Languages and Platforms
arXiv:2603. 05026v2 Announce Type: replace-cross Abstract: Language model (LM) agents have driven substantial progress in automated software engineering (SWE), yet building and testing software repositories at scale remains a largely manual and labor-intensive bottleneck.
arXiv Machine Learning
Jun 9
QDS-SNN: Energy-efficient Quantum Deeply-Supervised Spiking Neural Network Algorithm for Traffic Sign Recognition
arXiv:2606. 07657v1 Announce Type: cross Abstract: Traffic sign recognition is crucial for intelligent transportation and autonomous driving, as it can improve driving efficiency and ensure road safety.