arXiv:2601.11044v4 Announce Type: replace Abstract: Large Language Models (LLMs) based autonomous agents demonstrate multifaceted capabilities to contribute substantially to economic production. However, existing benchmarks remain focused on single agentic capability, failing to capture long-horizon real-world scenarios. Moreover, the reliance on human-in-the-loop feedback for realistic tasks creates a scalability bottleneck, hindering automated rollout collection and evaluation. […]
The Semi-Executable Stack: Agentic Software Engineering and the Expanding Scope of SE
arXiv:2604.15468v2 Announce Type: replace-cross Abstract: AI-based systems, currently driven largely by LLMs and tool-using agentic harnesses, are increasingly discussed as a possible threat to software engineering. Foundation models get stronger, agents can plan and act across multiple steps, and tasks such as scaffolding, routine test generation, straightforward bug fixing, and small integration work look more […]
FSFM: A Biologically-Inspired Framework for Selective Forgetting of Agent Memory
arXiv:2604.20300v2 Announce Type: replace Abstract: For LLM agents, memory management critically impacts efficiency, quality, and security. While much research focuses on retention, selective forgetting–inspired by human cognitive processes (hippocampal indexing/consolidation theory and Ebbinghaus forgetting curve)–remains underexplored. We argue that in resource-constrained environments, a well-designed forgetting mechanism is as crucial as remembering, delivering benefits across three […]
VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation
arXiv:2604.21375v1 Announce Type: cross Abstract: Autonomous GUI agents face two fundamental challenges: early stopping, where agents prematurely declare success without verifiable evidence, and repetitive loops, where agents cycle through the same failing actions without recovery. We present VLAA-GUI, a modular GUI agentic framework built around three integrated components that guide the system on when to […]
A Comprehensive Guide to Differential Privacy: From Theory to User Expectations
arXiv:2509.03294v3 Announce Type: replace-cross Abstract: The increasing availability of personal data has enabled significant advances in fields such as machine learning, healthcare, and cybersecurity. However, this data abundance also raises serious privacy concerns, especially in light of powerful re-identification attacks and growing legal and ethical demands for responsible data use. Differential privacy (DP) has emerged […]
ELMoE-3D: Leveraging Intrinsic Elasticity of MoE for Hybrid-Bonding-Enabled Self-Speculative Decoding in On-Premises Serving
arXiv:2604.14626v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) models have become the dominant architecture for large-scale language models, yet on-premises serving remains fundamentally memory-bound as batching turns sparse per-token compute into dense memory activation. Memory-centric architectures (PIM, NMP) improve bandwidth but leave compute underutilized under MoE’s low arithmetic intensity at high batch sizes. Speculative decoding (SD) […]
Learning Reasoning Reward Models from Expert Demonstration via Inverse Reinforcement Learning
arXiv:2510.01857v3 Announce Type: replace Abstract: Current approaches to improving reasoning in large language models (LLMs) primarily rely on either supervised fine-tuning (SFT) over expert traces or reinforcement learning (RL) with outcome-level rewards. However, SFT is fundamentally imitative, while outcome-based RL assumes access to a well-specified verifier. To address this gap, we propose an adversarial inverse […]
mcdok at SemEval-2026 Task 13: Finetuning LLMs for Detection of Machine-Generated Code
arXiv:2604.21365v1 Announce Type: cross Abstract: Multi-domain detection of the machine-generated code snippets in various programming languages is a challenging task. SemEval-2026 Task~13 copes with this challenge in various angles, as a binary detection problem as well as attribution of the source. Specifically, its subtasks also cover generator LLM family detection, as well as a hybrid […]
AISafetyBenchExplorer: A Metric-Aware Catalogue of AI Safety Benchmarks Reveals Fragmented Measurement and Weak Benchmark Governance
arXiv:2604.12875v2 Announce Type: replace Abstract: The rapid expansion of large language model (LLM) safety evaluation has produced a substantial benchmark ecosystem, but not a correspondingly coherent measurement ecosystem. We present AISafetyBenchExplorer, a structured catalogue of 195 AI safety benchmarks released between 2018 and 2026, organized through a multi-sheet schema that records benchmark-level metadata, metric-level definitions, […]
LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety
arXiv:2604.12710v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often demonstrate strong safety performance in high-resource languages, yet exhibit severe vulnerabilities when queried in low-resource languages. We attribute this gap to a mismatch between language-agnostic semantic understanding ability and language-dominant safety alignment biased toward high-resource languages. Consistent with this hypothesis, we empirically identify the semantic […]
Secure LLM Fine-Tuning via Safety-Aware Probing
arXiv:2505.16737v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have achieved remarkable success across many applications, but their ability to generate harmful content raises serious safety concerns. Although safety alignment techniques are often applied during pre-training or post-training, recent studies show that subsequent fine-tuning on adversarial or even benign data can still compromise model safety. […]
Trust-SSL: Additive-Residual Selective Invariance for Robust Aerial Self-Supervised Learning
arXiv:2604.21349v1 Announce Type: cross Abstract: Self-supervised learning (SSL) is a standard approach for representation learning in aerial imagery. Existing methods enforce invariance between augmented views, which works well when augmentations preserve semantic content. However, aerial images are frequently degraded by haze, motion blur, rain, and occlusion that remove critical evidence. Enforcing alignment between a clean […]