arXiv:2605.23094v1 Announce Type: cross Abstract: Generative augmentation is often proposed as a remedy for small medical-image datasets, but synthetic images are only useful when they improve downstream task performance. “Augmentation” here means synthetic supplementation: GAN-generated samples added to the real training pool, not geometric or photometric transforms of existing images. Twelve class-plane StyleGAN2-ADA generators were […]
PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning
arXiv:2605.23074v1 Announce Type: new Abstract: The emergence of Large Reasoning Language Models (LRMs) has paved the way for tackling complex reasoning tasks through test-time scaling by generating long-form Chain-of-Thought (CoT) trajectories during inference. Meanwhile, these trajectories often contain explicit reflection markers such as “wait”, “but”, and “alternatively”, signaling hesitation, revision, and the consideration of alternative […]
Exploiting Longitudinal Context in Clinician-Verified Interactive Lesion Tracking
arXiv:2605.23118v1 Announce Type: cross Abstract: Tracking tumor lesions across serial CT scans is essential for oncological response assessment. Existing automated methods face a fundamental trade-off: end-to-end trackers achieve high automation but offer no opportunity to correct silent tracking failures, while decoupled registration-segmentation pipelines permit user verification yet discard the lesion’s prior appearance, limiting accuracy in […]
Disentangling Interaction and Bias Effects in Opinion Dynamics of Large Language Models
arXiv:2509.06858v2 Announce Type: replace-cross Abstract: Large Language Models are increasingly used to simulate human opinion dynamics, yet the effect of genuine interaction is often obscured by systematic biases. We develop a Bayesian framework to disentangle and quantify three such biases: (i) A topic bias toward the LLM’s default stance; (ii) an agreement bias favoring agreement […]
Infra-Bayesian Reinforcement Learning Agents Outperform Classical RL For Worst-Case Robustness
arXiv:2605.23146v1 Announce Type: cross Abstract: Classical reinforcement learning assumes the agent interacts with a fixed environment whose behavior does not depend on the agent’s policy. This assumption breaks down in non-realizable settings where other actors might anticipate the agent’s behavior, including environments crucial to AI safety, where the agent interacts with predictors, humans, other AI […]
Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems
arXiv:2605.23109v1 Announce Type: new Abstract: AI agents increasingly excel at generating, testing, and refining code. However, they fall short on tasks requiring formal guarantees of full coverage that testing alone cannot provide. Distributed systems are a prime example: properties such as consistency between reads and writes must hold under every possible interleaving of events. Mechanized […]
PoisonForge: Task-Level Targeted Poisoning Benchmark for Instruction-Tuned LLMs
arXiv:2605.23168v1 Announce Type: cross Abstract: When practitioners fine-tune LLMs on unvetted datasets, an adversary can exploit the data supply chain through task-level poisoning: inserting a small number of crafted instruction-response pairs that cause the model to embed attacker-specified entities, such as a country, in outputs for a targeted task family while behaving normally elsewhere. We […]
R$^3$L: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification
arXiv:2601.03715v2 Announce Type: replace-cross Abstract: Reinforcement learning drives recent advances in LLM reasoning and agentic capabilities, yet current approaches struggle with both exploration and exploitation. Exploration suffers from low success rates on difficult tasks and high costs of repeated rollouts from scratch. Exploitation suffers from coarse credit assignment and training instability: Trajectory-level rewards penalize valid […]
Adaptive Mass-Segmented KV Compression for Long-Context Reasoning
arXiv:2605.23200v1 Announce Type: cross Abstract: The linear growth of the Key-Value (KV) cache is a critical bottleneck in long-form LLM inference. Existing KV compression methods mitigate this by evicting tokens based on importance scores. However, we show that their reliance on global Top-k selection triggers Region Wipe-out: the severe eviction of contiguous reasoning blocks that […]
Are Frontier LLMs Ready for Cybersecurity? Evidence for Vertical Foundation Models from Dual-Mode Vulnerability Benchmarks
arXiv:2605.23243v1 Announce Type: cross Abstract: We evaluate whether frontier LLMs are ready for cybersecurity through a dual-mode benchmark: white-box function-level vulnerability detection (VulnLLM-R, across C/Java/Python) and black-box web application security testing (five production-style applications with 118 ground-truth vulnerabilities across 20+ CWE families, which we will open-source). We test six frontier models (GPT-5.4, Codex~5.3, Claude Opus~4.6, […]
HTMuon: Improving Muon via Heavy-Tailed Spectral Correction
arXiv:2603.10067v2 Announce Type: replace-cross Abstract: Muon has recently shown promising results in LLM training. In this work, we study how to further improve Muon. We argue that Muon’s orthogonalized update rule suppresses the emergence of heavy-tailed weight spectra and over-emphasizes the training along noise-dominated directions. Motivated by the Heavy-Tailed Self-Regularization (HT-SR) theory, we propose HTMuon. […]
6G Communication Networks Enabling Embodied Agents: Architecture and Prototype
arXiv:2605.23263v1 Announce Type: cross Abstract: Embodied agents, which couple intelligent decision-making with physical actuation in the real world, impose far more stringent and heterogeneous communication requirements than purely software-based agents. While 6G promises sub-millisecond latency, ultra-high reliability, native intelligence, and integrated sensing, systematic studies on how to exploit these capabilities for embodied agent communication remain […]