FLY-EVAL++: An Evidence-Driven Evaluation Protocol for Safety-Constrained Flight Prediction with Large Language Models

Evaluating large language models (LLMs) in safety-critical, physics-governed environments requires more than accuracy-based metrics, because predictions that are numerically close to the ground truth can still violate operational constraints, combine fields in physically inconsistent ways, or fail to produce usable structured outputs. Existing evaluation protocols do not measure these failure modes reliably. We propose FLY-EVAL++, an evidence-driven evaluation protocol that combines deterministic verification of protocol compliance, physical feasibility, and safety constraints with fixed rubric-guided aggregation into interpretable multi-dimensional scores. We instantiate FLY-EVAL++ for Flight Trajectory and Attitude Prediction (FTAP) by extending the PilotBench setting with history-conditioned and multi-step prediction tasks. Across 66 LLMs, safety compliance is the most discriminative dimension of model behavior: models with comparable predictive performance differ by more than 28 points in safety score, and we observe recurrent failures including safety violations under physically plausible predictions and instability in multi-step rollouts. These results show that evaluation in safety-critical domains should measure constraint satisfaction and structured validity explicitly rather than rely on accuracy-centric reporting alone.

Safety by Design: Realized-Cost Constraints for Contextual Bandits with Continuous Actions

Contextual bandits are a standard framework for sequential decision-making under uncertainty, with applications in clinical trials, dosage selection, recommendation systems, and autonomous systems. Safety is central in many of these applications, since a single unsafe decision in settings such as dosage selection or autonomous driving can have catastrophic consequences. A common way to model safety in bandit problems is to associate each action with both a reward signal and a cost signal, and to optimize reward subject to constraints on cost. Most existing safety-constrained bandit models enforce safety by requiring the expected cost of each action to remain below a prescribed threshold. However, this may be insufficient in heteroscedastic settings, where the chosen action affects not only the expected reward and cost, but also the variability of the observed outcomes. We study contextual bandits with one-dimensional continuous actions and stage-wise high-probability constraints on the realized cost. We propose High-Probability Constrained UCB, an optimistic-pessimistic algorithm that explores for reward while conservatively estimating the safe action set. For linear reward and cost models, we prove a tight $\tilde{\mathcal{O}}(d\sqrt{T})$ regret bound, and we extend the analysis to general function classes using the eluder dimension. Experiments show that enforcing realized-cost safety substantially reduces violations compared with expected-cost constrained baselines.

Learning-Based Behavior Planning for Automated Driving: Real-World Integration and Deployment

Recent research in machine and deep learning has shown the potential of learningbased motion planning approaches to improve the driving behavior of automated vehicles, especially in complex environments. However, their complex nature and lack of transparency can hinder explainability and trustworthiness and complicate safety assurance. Motivated by these challenges, we propose a hybrid planning architecture that combines the advantages of machine learning with the verifiability and the determinism of classical approaches. Specifically, we developed a deep neural network to interpret complex traffic scenes and propose driving behavior, while an optimization-based supervision layer validates this proposal and enforces explicit drivability and safety constraints. We evaluate the learned planner's driving behavior in open-loop studies on real-world urban data, discuss system integration aspects for stable closed-loop operation, and report results from real-world deployment on our research vehicle karl..

Navigating the Proximity-Safety Balance: Constraint Decomposition for Human Following in Pedestrian Crowds

Following a target human in crowded environments involves an inherent conflict between staying close to the target and navigating safely among surrounding pedestrians and obstacles. This conflict becomes more severe in dense scenarios, where aggressive following risks collisions and conservative margins lead to target loss, especially when pedestrian behaviors are unfamiliar or unpredictable. Existing reinforcement learning (RL) methods typically encode these competing objectives into a single dense reward, but the resulting proximity-safety balance is implicit and difficult to adjust across conditions. To address this, we decompose the human-following task into a sparse task reward and independent cost constraints within a multi-constraint RL formulation, where each constraint is managed through cost thresholds with direct behavioral meaning rather than implicit reward weight ratios, allowing explicit and tunable control over the trade-off. We further quantify the prediction uncertainty of human motions and integrate these estimates into the RL costs to enhance safety under unpredictable conditions. Extensive experiments across both in-distribution and out-of-distribution settings demonstrate that our method achieves an effective proximity-safety balance compared to baselines. Real-robot deployment further validates the feasibility of our method in real-world scenarios. More details are available on our project page: https://nav-ps-balance.github.io/.

The Off-Support Barrier: Why Semantic Safety Constraints Are Not Learning-Problem Invariants, and What Follows for Prior Design, Containment, and Verification

We argue that a single structural fact organizes a wide range of phenomena in contemporary AI safety: a semantic safety constraint (e.g., the agent does not escape its sandbox) is an off-support object. Formally, if q is the data distribution and \(p(\cdot\mid w)\) the model, the safety predicate B is not measurable with respect to \(σ(\text{model}, q)\), whereas the real log-canonical threshold (RLCT) of singular learning theory (SLT) is. From this non-invariance we derive, as corollaries rather than independent observations: (i) why reward hacking and sandbox escape arise under outcome-based optimization; (ii) why encoding such constraints through Bayesian prior design or soft penalty weighting has poor leverage in singular models; (iii) why hard invariants belong in the harness and soft dispositions in the model; (iv) why the same B is nonetheless soundly and locally certifiable by formal verification, exactly as the local learning coefficient (LLC) locally pins the same RLCT --- with two precise points of disanalogy; and (v) why the residual difficulty, identifying which off-support region matters, coincides with performative prediction and self-referential functional dynamics, where SLT's analytic machinery breaks down. We use the July 2026 OpenAI--Hugging Face evaluation incident as the motivating case. Numerical experiments code and related proofs in lean are available at https://github.com/xiangze/Preventing_Jailbreak_as_regularization

Adjustment Speed as a Safety Constraint for Nonstationary Reinforcement Learning

Ensuring safety in reinforcement learning under nonstationarity requires determining whether a learning system can safely adapt to forecasted environmental change within the required recovery horizon. Existing safe reinforcement learning methods typically assume stationary environments and do not explicitly consider adaptation speed as a safety concern. However, when environments evolve over time, delayed adaptation may result in transient unsafe behavior. This paper proposes adjustment speed as a safety constraint for nonstationary reinforcement learning. The central idea is to define safety in terms of adaptation feasibility: future states or regions may become unsafe when the adaptation required to remain safe exceeds the learning system's calibrated recovery capacity. The proposed framework uses learned context representations and short-horizon context forecasts to estimate adaptation demand and compare it with the agent's achievable adaptation capacity. When predicted adaptation demand exceeds the calibrated recovery capacity, the framework proactively tightens the admissible action set and activates an action-level shield to reduce unsafe behavior before violations occur. Experiments in a nonstationary driving environment show that the proposed approach primarily reduces safety violations in short-horizon windows aligned with context changes. Ablation studies further show that shielding is more conservative for peak- and tail-risk suppression, while optimization-level adjustment provides additional reductions in short-horizon switch-conditioned violations. These results support adaptation feasibility as a practical safety principle for reinforcement learning under nonstationarity and demonstrate that proactive intervention can improve safety during periods of environmental change.

Heterogeneous Agent Cohorts for Safe Open-Ended Exploration with Runtime Constraint Memory

LLM agents today are caught in an awkward bind. Lock them down with static safety instructions and they rarely venture beyond the obvious; give them free reign with tools and multi-agent debate, and safety violations quickly follow. Rather than forcing a single model to juggle both creativity and caution, we separate the concerns across specialized roles. A Disrupter generates unconventional proposals, a Validator enforces hard runtime checks at the tool gateway, and a Broker pulls in distant but relevant analogies. Failures are not discarded -- they are compiled, via MCTS, into compact, signed constraint patches we call Scars. These patches are cached locally and inherited by future cohorts, turning repeated failures into reusable, low-cost runtime constraints. In a spatial-semantic sandbox (N=20 runs, p<0.01), our cohort reaches remote targets where debate fails, the Validator prevents all executed breaches, and Scars reduce token consumption by 15.1% by avoiding redundant validator checks. Furthermore, credit-based Communication Allocation Scores (CAS) restrict outbound bandwidth, reducing overall token costs by 55.9% under resource constraints.

Safe Inference-Time Alignment via Lagrangian Reward Augmentation

Inference-time alignment steers a frozen language model during decoding using auxiliary reward signals, avoiding the cost of repeated weight updates. However, existing inference-time alignment methods typically optimize a single scalar score, so explicit safety constraints must either be ignored or encoded through manually tuned penalties. We propose Lagrangian Reward Augmentation (LARA), a general inference-time alignment framework under safety constraints. Starting from a KL-regularized constrained objective with a reward model and a cost model, LARA dualizes the constraint and reduces the optimization problem to a one-dimensional convex problem over a nonnegative dual variable. Estimated on a small calibration set, this dual variable defines an augmented reward that can be used as a drop-in scoring signal within existing inference-time alignment methods. For sequence-level sampling methods, such as Best-of-N reranking, the calibrated dual variable corresponds to the solution of the expected-cost constrained problem. For token-level reward-guided decoding methods, the same construction yields a principled dual-calibrated heuristic rather than an exact constrained-policy guarantee. We evaluate LARA on both sequence-level and token-level inference-time alignment methods, and find that LARA improves the helpfulness-harmlessness tradeoff, with Best-of-N achieving the best performance among inference-time methods, approaching finetuning-based direct alignment baselines.

Safe and Generalizable Hierarchical Multi-Agent RL via Constraint Manifold Control

Multi-agent systems are widely used in safety-critical applications that require coordinated behavior under strict safety constraints. Existing approaches face a fundamental trade-off: learning-based methods achieve strong empirical performance but lack theoretical safety guarantees, while control-theoretic methods enforce safety but often lead to overly conservative and inefficient behaviors. We propose a hierarchical multi-agent reinforcement learning framework that enforces hard safety constraints under mild assumptions at low level via a constraint manifold, while enabling effective coordination through high-level policy learning. Our approach provides theoretical safety guarantees in the multi-agent setting and yields stationary learning dynamics, thereby enabling stable and efficient training. Empirically, our method achieves competitive performance while maintaining nearly perfect safety rates, and generalizes effectively to varying numbers of agents and obstacles.

Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horizon LLM Agents

Modern LLM agents increasingly rely on context compaction, summarization, or eviction to keep long-running sessions within a token budget. We show that this context-management layer is a safety-critical failure surface: in-context governance constraints that agents reliably obey while visible can be silently removed by compaction, causing the same agent to perform prohibited tool actions later in the session. We call this failure mode Governance Decay. We introduce ConstraintRot, a benchmark of long-horizon agent scenarios with deterministic tool-call grading, and measure compaction-induced violations across seven model families. Across 1,323 episodes, violation rises from 0% with the policy in full context to 30% after compaction, reaching 59% for some models; when the constraint survives the summary, violation remains 0%, but when it is dropped, violation reaches 38%. We further study a Compaction-Eviction Attack, in which adversarial in-context content biases the summarizer to omit a legitimate policy, and show that optimized injections defeat every evaluated model. Finally, we propose Constraint Pinning, a simple training-free mitigation that quarantines governance constraints from lossy compaction and restores violation to 0% in our benchmark. These results identify context management as a first-class governance surface for deployed LLM agents.

Designing Safety-Constrained LLM Systems for Public Health Information Access

We present the design and implementation of a safety constrained large language model (LLM) system for public health information access, focusing on maternal and child health (MCH) resource navigation. While LLM based systems offer flexible and natural interfaces for information retrieval, their deployment in healthcare contexts introduces risks related to safety, trust, and uncontrolled generation. This work explores practical design patterns for constraining LLM behavior in safety critical environments. We introduce a multi-layered architecture that integrates domain-restricted retrieval augmented generation (RAG), strict boundary enforcement to prevent medical advice, anonymous multiuser session management, and comprehensive audit logging for monitoring and compliance. A key aspect of the design is a controlled data pipeline that grounds all responses in curated public health resources, avoiding reliance on the model pretrained medical knowledge. We implement the system in a real world public health setting and conduct scenario-based validation across in scope, out of scope, and emergency queries. Results show consistent enforcement of safety constraints, reliable resource grounding, and stable system performance, with an average response time of 5.3 seconds. Beyond the specific application, we discuss design trade offs and lessons learned in balancing safety, usability, and system flexibility. Our findings provide practical guidance for deploying LLM based systems in healthcare and other domains where strict information boundaries and accountability are required.

Safety-Contract Graph Multi-Agent Reinforcement Learning for Autonomous Network Security Response

Autonomous network-security response systems promise to reduce Security Operations Centre (SOC) reaction latency, but reward-only multi-agent reinforcement learning (MARL) can improve security reward while remaining non-deployable. We present a safety-contract graph MARL framework and instantiate it as ACD$^3$-GAT (Adaptive Constrained Counterfactual Decisioning with a Graph Attention Network encoder), an architecture that separates simulator observations from reusable operational budgets, constrained optimization, graph state encoding, and counterfactual action screening. We evaluate the method in CAGE Challenge 4, where agents operate under budgets for Mean Time to Recover (MTTR), false-positive response, and firewall change-management disruption. Across the benchmark, every unconstrained method violates the SOC downtime budget in 100% of evaluated episodes, with mean downtime proxy costs of 311-430 against a budget of 50. This complements prior CAGE Challenge 4 findings by showing that reward-only learning lacks operational discipline. Constrained MAPPO-GAT (C-MAPPO-GAT) isolates Lagrangian operational-cost control and budget-aware screening, while ACD$^3$-GAT adds budget context, CVaR tail-risk estimation, opponent-belief state, and Graph Counterfactual Risk Propagation (G-CRP). The replicated comparison includes three 200-episode seeds for IPPO, MAPPO-GAT, C-MAPPO-GAT, and ACD$^3$-GAT. C-MAPPO-GAT reduces downtime violation from 100% to 0.3% and mean downtime cost from 355.4 to 15.5 relative to MAPPO-GAT. ACD$^3$-GAT reduces mean downtime cost to 48.2 with a 13.8% violation rate, placing it on the safety-contract frontier rather than at the most conservative compliance point. Topology-seed and coupled adaptive Red-process stress tests preserve this contrast and show lower worst adaptive degradation for safety-constrained policies than reward-only MAPPO-GAT.

SafeRun: Enabling Determinism in LLM Planning for Running

Large Language Models enable flexible natural-language planning but remain unreliable in determinism-critical domains due to their probabilistic nature. This limitation is especially problematic in running planning, where violating safety rules can lead to safety risks. We propose SafeRun, a framework for deterministic LLM-based planning via a decoupled architecture. SafeRun separates soft interpretation by an LLM from hard constraint enforcement by a deterministic solver, ensuring strict safety constraints while preserving natural-language flexibility. To validate SafeRun, we build a comprehensive benchmark for running planning under realistic physiological and safety constraints. Experiments across five LLMs show that SafeRun achieves 100\% safety score (vs.\ 79.1\% PE average and 97.6\% CodeAct average) while maintaining competitive instruction-following scores. The SafeRun benchmark is publicly available at \href{https://huggingface.co/datasets/zzp-seeker/SafeRun-RunPlanning-Benchmark}{huggingface}.

SkillHarness: Harnessing Safe Skills for Computer-Use Agents

Computer-Use Agents (CUAs) are increasingly deployed in dynamic interactive environments, creating a growing need for continual skill learning during interaction. Recent approaches address this challenge by learning reusable skills from successful trajectories. However, these skill learning methods largely assume static and safe environments, overlooking risks from adversarial interactions (e.g., prompt injections) and environmental dynamics (e.g., pop-ups). In dynamic settings, such assumptions can lead to risky skill learning and brittle execution, undermining the reliability of CUAs. This raises the question: how can CUAs learn and use skills safely in dynamic environments? To address this problem, we propose SkillHarness, a framework for safe skill harnessing in dynamic environments. SkillHarness moves beyond static skill abstractions by modeling skill learning and utilization as a safety-constrained interaction process. Specifically, we introduce the skill boundary that leverages multi-source supervision signals to identify safe skills from interaction trajectories, and construct self-improving safety constraints throughout the skill lifecycle. In addition, SkillHarness introduces selective skill reuse, where tasks are guided to decompose according to context and completed through the selective activation of skill subsets. Our experiments demonstrate that SkillHarness significantly reduces the unsafe rate of learned skills by 57.1% and consistently improves execution stability under dynamic environmental changes, outperforming existing baselines.

LabBuilder: Protocol-Grounded 3D Layout Generation for Interactable and Safe Laboratory

Automated laboratories hold the promise of accelerating scientific discovery, yet their deployment is bottlenecked by the difficulty of designing safe and executable environments. While simulator-based design offers scalability, existing 3D scene generation methods are primarily tailored for household settings, optimizing for visual plausibility while neglecting the rigorous functional semantics and safety constraints essential for scientific experimentation. We present LabBuilder, an end-to-end system that generates and verifies 3D laboratory layouts from concise textual specifications. It operates through three tightly coupled components: LabForge first curates a meta-dataset of annotated assets and chemical knowledge, translating natural language specifications into structured protocols; building on these protocols, LabGen synthesizes laboratory layouts via an iterative, constraint-aware optimization strategy; finally, LabTouchstone evaluates the resulting layouts as a unified benchmark. Extensive experiments demonstrate that LabBuilder significantly outperforms existing state-of-the-art methods, producing laboratory environments that are not only realistic but also functionally valid and safe for complex experimental workflows.