每天知道
你的领域
出了什么

World models are widely used in offline reinforcement learning (RL) to improve sample efficiency and generate experience beyond a fixed dataset. However, they are vulnerable to model exploitation where data coverage is thin. Prior work addresses this either by collecting more expert demonstrations, which is often expensive, unsafe, or unavailable, or by conservative algorithms that avoid uncertain regions, which limits generalization. We propose instead to repair exploitation directly using human preferences over imagined rollouts, leveraging the strong intuitive physics that allows humans to easily spot egregious dynamics hallucinations. We formalize this as Dynamics Learning from Human Feedback (DLHF), a Bradley-Terry preference loss over trajectory log-likelihoods under a learned dynamics model. Unfortunately, naive DLHF is sample inefficient, so we introduce RENEW, which uses epistemic uncertainty to focus finetuning where the model is most exploitable. We evaluate on several Jumanji and classic control environments and find that while naive DLHF requires an outsize preference budget, RENEW makes the framework practical by improving sample efficiency, limiting catastrophic forgetting, and reducing exploitation in pretrained world models. Taken together, our results provide initial evidence that preferences can supervise world model dynamics directly, offering a new approach to addressing exploitation in offline model-based RL.

Video generation increasingly relies on keyframe-based workflows, where creators specify a sequence of reference images to guide generation. Although recent models support multi-keyframe conditioning, it remains unclear whether they can faithfully reproduce the prescribed keyframes while maintaining overall video quality. We present KeyFrame-Compass, the first comprehensive benchmark for evaluating keyframe-conditioned video generation. The benchmark contains 386 carefully curated samples spanning three application domains, two video structures, two prompt granularities, two conditioning formats, and four keyframe densities, enabling controlled analysis under diverse generation settings. We further introduce an automated evaluation framework that jointly measures keyframe execution and overall video quality. Specifically, we decompose keyframe execution into six complementary metrics covering presence, fidelity, temporal ordering, localization, persistence, and uniqueness, while assessing overall video quality through evidence-grounded MLLM judgments augmented with specialized perception models. Experiments on nine representative video generation systems reveal several fundamental limitations. Current models exhibit a clear trade-off between faithful keyframe execution and natural video synthesis. Their performance further degrades as keyframe constraints become denser and most open-source models also fail to interpret storyboard-grid inputs as temporally ordered keyframe sequences.

Embodied cognition requires agents to connect high-level task reasoning with the physical states to be achieved. We introduce Hy-Embodied-RxBrain, an embodied cognition foundation model with joint language-visual reasoning and imagination. Unlike vision-language models that emphasize scene understanding and textual decision making, or generative world models that mainly predict future visual states, RxBrain represents embodied plans in a single planning sequence where language and visual imagination play complementary roles. Language provides the abstract structure of a plan, including task decomposition, planning primitives, constraints, temporal order, and decision logic, while visual imagination grounds this structure through world state prediction and joint subgoal planning, associating each planning step with intermediate and final physical states. RxBrain adopts a unified multimodal Mixture-of-Transformers architecture that supports language, image, and video understanding and generation within one model. To train this capability, we build an automatic pipeline that converts embodied videos into joint text-visual planning supervision by decomposing videos into planning steps and aligning them with visual state transitions. We further introduce RxBrain-Bench to evaluate whether models can represent embodied plans through joint textual and visual components rather than separate understanding or generation. Experiments show that RxBrain maintains embodied understanding and generation abilities, and produces plans with coupled textual reasoning, world state prediction, and joint subgoal planning. We also extend RxBrain to continuous robot action generation, where it shows promising real-robot performance without large-scale action-data pretraining. These results provide an initial step toward foundation models for embodied cognition.

Multi-reference-to-audio-video (MR2AV) generation aims to generate coherent audio-video content conditioned on multiple references and textual instructions. Existing benchmarks mainly focus on text-driven generation, single-reference subject preservation, or isolated audio-video alignment, leaving the emerging MR2AV setting largely unexplored. Compared with these settings, MR2AV requires models to jointly reason over multiple references while generating synchronized visual and audio content. Models must not only preserve each reference faithfully but also correctly bind and compose multiple referenced entities into coherent audio-visual events. To address this gap, we introduce MultiRef-Compass, a unified benchmark for MR2AV generation. It comprises $350$ carefully curated samples constructed through a scalable and controllable asset-composition pipeline, covering multi-view subject preservation, multi-entity binding, and human-object-scene composition. To provide interpretable assessment, MultiRef-Compass defines an evaluation protocol with four dimensions: Basic Quality, Reference Consistency, Audio-Visual Consistency, and Instruction Following, using 14 sub-metrics. MultiRef-Compass integrates automatic metrics with a rejudging-enhanced MLLM-as-a-Judge framework, enabling scalable and auditable evaluation of both perceptual fidelity and reference-conditioned composition. Extensive experiments on eight representative MR2AV systems reveal substantial room for improvement across multiple evaluation dimensions, underscoring the need for a comprehensive benchmark and positioning MultiRef-Compass as a foundation for future MR2AV research.

Text-to-video (T2V) generators can synthesize realistic and temporally coherent videos, but controllably removing a target concept from a generator remains difficult. Unlike text-to-image concept erasure, T2V unlearning must suppress a target concept that may persist across frames while preserving non-target subjects, actions, scenes, and temporal structure. We propose SIRUS, a training-free inference-time framework for concept-level T2V unlearning. Given textual aliases of a target concept, SIRUS localizes target-related prompt evidence and suppresses target expression during sampling, without updating the text encoder or denoising network. We further introduce a video-oriented evaluation framework for T2V unlearning that separately measures target forgetting, non-target preservation, video quality, jailbreak robustness, and efficiency, using video-level failure criteria, frame-level residue statistics, paired preservation analysis, VBench-based quality diagnostics, and deployment overhead measurement. Across five safety, object, and style concepts on CogVideoX, SIRUS reaches 70.4% average forgetting success and 25.7% average frame hit, compared with 44.4% / 47.2% for VideoEraser, while reducing the average VBench quality drop from -0.043 to -0.016, yielding the strongest forgetting-quality trade-off among fully evaluated baselines. Transfer experiments on Wan2.2 further suggest that SIRUS generalizes across modern T2V backbones.

Physics-informed neural networks (PINNs) have had a broad research impact in modeling domains governed by partial differential equations (PDE). However, PINNs have been shown to perform poorly, sometimes even converging to trivial solutions, in challenging PDE domains, or when generalizing to unseen but related PDE domains. Previously proposed solutions detail hyperparameter tuning to reduce loss imbalance between data-driven and physics guided losses, curriculum learning based training strategies, or dynamic re-sampling of hard collocation points. These methods face certain pitfalls: hyperparameter tuning is expensive, designing a training curriculum is ambiguous in multi-parameter PDE settings, and dynamic resampling still fails in complex PDE settings. Complementary to this line of thinking, we believe the initial PINN network weights also play a crucial role in the emergence of catastrophic failures during training, yet the effect of PINN weight initialization has been surprisingly under-investigated. To this end, we propose a framework for Learned Initialization via Gated Layerwise Optimization (LIGO-PINN) to overcome PINN convergence failures. Through rigorous evaluation on 1D and 2D PDE domains, including a challenging 2D fluid dynamics setting, we demonstrate that our methodology outperforms state-of-the-art methods designed to alleviate PINN failures, achieving a 91.5% average performance improvement across six baselines and 81% over the strongest baseline. We also verify that LIGO-PINN generalizes to 3D unstructured domains. Finally, we analyze training dynamics across all three PDE domains to explain both LIGO-PINN's improvement and the convergence failure of traditional PINNs. Code: https://github.com/scailab/ligo-pinn Keywords: Machine Learning, Physics-Informed Neural Networks, Deep Learning, PDE Modeling

Constrained generative models aim to produce samples that satisfy complex feasibility constraints while remaining faithful to the data distribution. Existing constrained generation methods typically enforce constraints either through training-time optimization or sampling-time correction. Training-time optimization approaches optimize on states induced by the training distribution, which can differ substantially from those encountered during sampling. Sampling-time correction methods instead modify the sampling process at inference, introducing distribution shift and requiring expensive tuning, particularly for few-step sampling. We propose a fine-tuning framework that incorporates constraint guidance obtained through online rollout into the training process, which aligns training with sampling by differentiating through the fixed noise schedule used to numerically integrate the denoising process. This exposes the model to violations that arise along the denoising trajectory and aligns diffusion learning with the sampling process. Experiments across multiple tasks show that our method improves constraint satisfaction while maintaining competitive sampling quality compared to prior methods.

In recent years Flow Matching has become a prominent method for generative modeling robot motion generation. In its generic form Flow Matching is an ODE-based neural sampler that is trained by regressing empirical flow fields associated with motion samples as data. However, in robot motion generation we often have additional constraints that might not be present in the collected data. The majority of current approaches train the flow on the available data and use inference-time guidance to enforce task-specific constraints. To address this mismatch, we propose ConFlow, a constraint-guided flow matching framework that incorporates constraint information directly into the training objective via differentiable barrier or cost functions. To address design specifications such as smoothness and boundary conditions, we propose replacing the standard Gaussian source distribution used in flow matching training with a conditional Gaussian Process. Our approach also uses infeasible demonstrations as negative supervision, improving constraint satisfaction without requiring additional expert data. Experiments on a two-robot navigation task demonstrate that ConFlow achieves lower collision rates and higher trajectory quality than standard flow matching baselines, with or without inference-time guidance. These results validate training-time constraint integration as an effective approach to closing the training--inference gap in generative motion models.

The rapid development of Large Language Models (LLMs) and Artificial Intelligent (AI) powered autonomous agents has fundamentally changed the existing forms of software governance. In spite of the rigorous standards of transparency and account ability required according to the international frameworks such as the European Union's AI Act, there is a considerable gap between theory and reality. The present study discusses the inherent drawbacks of currently utilized platforms for LLM evaluation, machine learning workflow, and application performance monitoring in general. It has been shown that current disjointed solutions fail to protect unbound state space agentic architecture from serious threats such as alignment drift, SaaS security concerns, and unauthorized deployment of shadow AI systems. Moreover, a solution is proposed for overcoming the discussed challenges in form of a coherent multi-level AI governance stack Traccia built on the top of OpenTelemetry infrastructure platform. Traccia resolves the last mile for AI Alignment by adding the telemetry data, passive semantic guardrail assessment, and execution lineage into a hashed trace ledger. Traccia automatically creates compliance evidence packages by appending tamper-resistant fingerprints and SHA-256 content hash, that map to regulatory requirements (Articles 12, 14, 19, 26(6), and 50 of the EU AI Act) without invading any data privacy. By performing this evaluation in a methodical manner, a solid machine-readable base has been created for enterprise-wide management of autonomous AI systems.

Production LLM-agent frameworks ship control primitives — human-in-the-loop approval gates, run cancellation, and execution timeouts — whose names and documentation imply barrier semantics: while a run is paused, cancelled, or timed out, no gated side effect executes. This contract holds on none of six widely used open-source frameworks. Model-free differential probes isolate a recurring sibling leak — an approval gate suspends its own branch while a sibling's effect executes during the pause, defeating rejection — in every framework shipping a pre-execution gate (five of six, four execution models, two language runtimes), and confirm replay double-execution, cancellation orphans, and timeout zombies. The hazard is reachable: frontier models emit the leak-triggering plan shape at rates up to 14%, and live models driving unmodified frameworks leak 215 of 1,200 runs (P(leak | emitted)=1.00); on naturalistic tau-bench episodes models serialize writes — the everyday gap is latent — while injection induces it deterministically and a 13-incident public corpus corroborates the replay and cancellation failures. We repair the gaps with SOUNDGATE, an environment-external Rust gate through which every side effect must be admitted, enforcing hold-until-decided, reject-cancels, dedup-on-replay, and fence-on-cancel under a stated complete-mediation contract, discharged for network egress by two kernel-enforced routes. The admission core is mechanically verified (Verus; TLA+/TLC to 7.5e7 states; TLAPS; Loom on the deployed Rust) and bridged to code by differential conformance over 1.2e7 operations with zero divergences. Under that contract SOUNDGATE blocks every measured violation on all six frameworks while releasing legitimate effects: gated tau-bench episodes complete with zero refusals at ~1 ms per write, and durable admission sustains ~12k admissions per second.

Trustworthy deployment of LLM-based agents in software systems requires evaluating how they perform on application-specific workflows, with enough granularity to localize where they succeed and fail. Yet existing agent evaluation mechanisms are limited: benchmarks have low construct validity for application-specific workflows and environments, and replica evaluation environments are expensive and prone to drift. We propose Copy-on-Write (CoW) Scoring, a framework that evaluates agent operations directly within application environments using a PostgreSQL-level Copy-on-Write mechanism to isolate agent writes. CoW Scoring produces session- and operation-level scores that highlight where agents' database write operations succeed and fail in a given application environment, enabling inexpensive evaluation and iteration on agent harnesses and tool surfaces. We demonstrate the framework on Plane, an open-source project-management platform, where analysis surfaced specific issues in the tool surface, and corresponding fixes produced measurable improvements on affected models. Python library: https://github.com/trail-ml/agent-cow-python

Reinforcement learning has emerged as the dominant paradigm for training large language model (LLM) agents that interact with executable sandboxes. State-of-the-art algorithms such as PPO, RLOO, and GRPO inherit their rollout topology from RLHF: for each prompt, N independent trajectories are sampled from the initial state, and an advantage is computed by subtracting a group baseline. This design ignores a defining property of agent sandboxes. They are deterministic, snapshottable, and resumable from any intermediate state. We argue that this property enables a fundamentally different rollout topology: rather than N independent trees of depth T, one can construct a single tree of N leaves whose siblings share prefixes, and therefore share variance. We instantiate this idea as Branching Policy Optimization (BPO), a sandbox-native RL algorithm that (i) adaptively snapshots the sandbox at high-entropy decision points along a backbone trajectory, (ii) forks K alternative actions per branch point and rolls out each to termination, and (iii) computes per-step advantages from sibling returns rather than from independent prompts. We prove this estimator is unbiased and has strictly lower variance than the trajectory-level baseline, with the reduction equal to the prefix-explained portion of return variance. On WebShop, ALFWorld, and SWE-bench Verified with Qwen2.5-7B and Llama-3.1-8B backbones, BPO improves success by 3.6--6.1 absolute points over GRPO and RLOO at matched compute, halves gradient-norm variance, and matches the best baseline using 38% fewer policy updates.

Safety alignment in LLMs aims to align models with human values, but which values take precedence when they conflict? We investigate this question in the context of tool-calling LLM agents deployed in regulated industries, where agents processing confidential documents may encounter content that triggers safety-trained values (e.g., public welfare) that conflict with deployment-context instructions (e.g., internal logging). To empirically verify this phenomenon, we build a benchmark of 128 scenarios across 16 domains. We find that safety-aligned open-source models override their deployment instructions up to 43.4% of the time, engaging in whistleblowing, data exfiltration, and evidence tampering when processing documents that suggest organizational wrongdoing. We also find that abliteration reduces rates of external whistleblowing. These results reveal a fundamental tension in pluralistic alignment, where the same safety training that protects users can cause agents to act against deployment instructions in ways that create unpredictable liability risks. We release our benchmark as a framework to support evaluation of agent behavior under competing legitimate interests.

Multimodal Large Language Models (MLLMs) are increasingly deployed for nuanced content safety and moderation tasks, yet they remain vulnerable to adversarial attacks and out-of-distribution edge cases. Traditional active learning and manual annotation fail to scale against the complexity and volume of novel multimodal threats. In this paper, we propose an automated, agentic red-teaming framework that systematically synthesizes difficult examples using an iterative strategy that proposes novel hypotheses as well as mutating on past attempts. Leveraging a multi-agent architecture that consists of a high-reasoning Architect agent, an advanced image generator, and a multi-level verification committee of LLM raters, our system autonomously uncovers boundary-pushing violations and ambiguous policy edge cases without any human intervention. By employing these carefully synthesized adversarial examples as in-context demonstrations via test-time Retrieval, we substantially improve the target model's robustness, reducing the False Negative Rate (FNR) from 41.2% to 24.5% in a public image safety benchmark without relying on any human labeling.

Large language models are increasingly deployed as agents, but reliable agentic behavior requires more than next-token prediction. At inference time, it is preferred that an agent can decide whether to proceed with its current reasoning, defer to a stronger model, request additional information, invoke external tools, or abstain under the given setup. Existing approaches address these decisions through prompt-level routing, external orchestration, or task-specific fine-tuning, which primarily rely on input-side signals, and are often costly and difficult to maintain as model backbones evolve. We ask whether such control decisions can be inferred directly from a model's latent generation process. We introduce Multi-Head Latent Control, a lightweight layer that reads hidden-state trajectories from a frozen LLM or VLM to produce deployment-time control signals. A Capability Head predicts whether the current model can solve the instance or should defer to a stronger collaborator, while a Resolution Head predicts appropriate resolution decision Clarification, Tool Use, Abstention, or Direct Answering. Both heads are trained only on latent traces from the same frozen LLM backbone, enabling post hoc adaptation without modifying the model. Across language and vision-language settings, Multi-Head Latent Control consistently improves the quality-cost tradeoff of multi-model systems, enabling early handoff from partial generations and more accurate intervention decisions. In routed execution (small + large model), it reduces large-model usage by up to 90.7 percent on AndroidWorld and 27-53 percent on average across benchmarks, while retaining most of large-model performance. Additionally, the learned control signals improve tool-use decision quality, yielding up to +158 percent relative score gain and 65.5 percent fewer missed-required tool calls.

Context engineering has become central to building reliable AI agents, yet it remains largely unmeasured. Agents do not fail in isolation: their behavior is shaped by the instructions, tools, memory, retrieved knowledge, guardrails, and untrusted inputs accumulated in their context. When this context is weak, agents drift, hallucinate, misuse tools, ignore constraints, become vulnerable to injection, and waste tokens. This paper validates context-engineering quality as an independent leading indicator of agent reliability. We implement the measurement in ProofAgent-Harness, an open-source infrastructure for AI agent evaluation that uses multi-juror, consensus-based scoring. The harness assesses context across seven criteria: role clarity, guardrail coverage, instruction consistency, tool schema quality, grounding sufficiency, injection hardening, and token efficiency. Crucially, the context score is isolated from behavioral metrics and release decisions, enabling a non-circular validation. Through a controlled context-quality study across regulated agent domains, holding frontier LLM agents fixed and varying only their operating context, we show that context-quality criteria consistently predict their corresponding behavioral outcomes. Grounding sufficiency predicts hallucination resistance, guardrail coverage predicts manipulation resistance, instruction consistency predicts instruction following, and tool-schema quality predicts tool use. These findings establish context measurement as a validated preflight signal for agent reliability and position context engineering as an auditable layer of agent evaluation and governance.

Mobile usage traces are critical for tasks such as user behavior prediction and app recommendation, yet their use is constrained by privacy restrictions and costly large-scale data collection. Although generative models perform well on general time series, their application to mobile usage data remains challenging because (i) limited user activity causes severe sparsity, (ii) heterogeneous variable types complicate joint modeling, and (iii) functional differences across apps create pronounced usage imbalance. To address these challenges, we propose Multivariate-Imaging Diffusion (MIDiff), a diffusion-based framework operating in an imaging space defined by Cross-Gramian Angular Sum Field (C-GASF). C-GASF transforms sparse multivariate sequences into correlation images, while MIDiff employs Triple Attention in a U-Net to preserve temporal consistency and variable dependencies. Experiments show that MIDiff achieves state-of-the-art performance across fidelity metrics. In particular, it obtains a Discriminative Accuracy (DA) of 0.1526, compared with 0.3476 for the strongest baseline, ZITS-VAE, demonstrating its effectiveness in generating realistic and diverse mobile usage traces. Our code is available at https://github.com/YilaiLiu-HKU/MIDiff.

Efficient long-context inference is not only about reducing memory cost, but also about keeping useful contextual evidence accessible as generation proceeds. However, existing compression-oriented approaches, such as key-value (KV) cache compression and context compression, often either make an early decision about which contextual information to keep or rely on an external compressor. Such designs make it difficult to adapt the compressed context to the evidence needed by later reasoning steps. This paper introduces PReM (Preserve and Refresh Memory), a context-compression framework that maintains the long context as the model's internal layer-wise KV memory and learns what to preserve and when to refresh it. Specifically, PReM uses a dedicated memory layer to make memory-selection decisions, and a special memory token <m> to trigger refreshes during generation. To train this behavior, PReM introduces Phase-Separated Refresh Training, aligning memory selection with memory-conditioned generation while preserving continuity across refreshes. Experiments with 32K-token contexts show that PReM outperforms strong baselines under both 16x and 32x compression, while maintaining a favorable balance between answer quality and inference efficiency.

The growing adoption of local inference frameworks such as Ollama has made it increasingly common for developers to run large code models on laptops and other resource-constrained hardware. In these settings, post-training quantization is essential for reducing memory footprint and enabling practical deployment, yet its impact on generated code remains insufficiently understood. We empirically evaluate six state-of-the-art quantization methods (GPTQ, AWQ, QuIP#, AQLM, BitsAndBytes, and GGUF) on two representative large code model families, Qwen2.5-Coder and CodeLlama, using the multilingual McEval and CoderEval benchmarks for Python and Java. We assess functional correctness (pass@1) together with maintainability, reliability, security, and structural complexity. We also introduce a novel analysis of robustness under varying prompt complexity, characterized by Shannon entropy and token length. Our results show that quantization techniques differ meaningfully in their impact on correctness and code quality. AQLM consistently matches or exceeds the full-precision baseline, whereas QuIP# exhibits the largest correctness degradation, particularly on complex prompts. Security attributes remain stable across models, benchmarks, and programming languages, while robustness to prompt complexity varies across techniques. These findings provide practical guidance for selecting quantization strategies for deploying large code models on resource-constrained hardware and highlight the importance of evaluating quantized models beyond functional correctness.

We report a way to make a frozen small language model both more capable and dramatically cheaper at once, without changing any weights. Verified knowledge is deposited once as a byte-exact key-value (KV) state artifact and later restored, by graft, into a fresh inference context. The restore is bit-exact: under a pinned deterministic configuration, the grafted logits are byte-for-byte identical to a fresh computation (SHA-256 equality), with zero KL divergence and 100% argmax agreement over fifty samples. We show that own-position graft is the unique numerically exact operating point on a model with floating-point rotary encoding, and we verify byte-exactness on two model scales (12B, 31B) and two GPU targets, one through a pre-registered replay. On AIME 2025, a frozen Gemma-4-12B moves from 80.0% to 93.3% once a verified solution library is grafted, above its own 77.5% and its 31B sibling's 89.2% published anchors. On the recurring case, eight problems the base model never solves within a 401,026-token budget are answered from cached verified solutions in 61 total decode tokens, a factor of 6,574 fewer tokens and about 8,700x less energy; the capability claim proper rests on held-out transfer (7 of 7 at 31B). The same byte-exact store widens usable context from 32,768 to 2,854,766 tokens at zero extra accelerator memory, and moves byte-identical between machines of the same architecture. We describe the system at the behavior level; the engine is proprietary, and every reported number is backed by committed input and output hashes so the scoring can be re-checked without it.

Current alignment approaches typically focus on emulating human behavior using static representations of human preferences, failing to capture the dynamic, context-dependent nature of real-world human-AI interactions. In this paper, we argue for a shift from static and emulative to interactive and complementary alignment, where preferences emerge through interaction and alignment is defined not by satisfying preferences alone. We first formalize this gap by contrasting existing alignment with a trajectory-level view in which human and model behavior co-evolve over time. Because these interaction dynamics have not been adequately captured within existing ML formulations, we ground this perspective in insights from an interdisciplinary workshop. We draw on lessons from social-science accounts of human-human collaboration and then argue that human-AI systems amplify these dynamics, introducing new asymmetries that make reasoning about uncertainty harder and introduce new coordination challenges. Based on these lessons and new challenges, we conclude by outlining a research agenda for developing AI systems that align with humans in interaction, requiring an interdisciplinary synthesis of machine learning and the social and decision sciences.

While Large Language Models (LLMs) have demonstrated significant capability in software code generation, their application to analog Electronic Design Automation (EDA) is bottlenecked. Owing to limited circuit topology understanding and data, directly prompting LLMs and multimodal models leads to hallucinations and failure to produce schematics capable of passing rigorous SPICE simulations, as we show in our work. Instead, we propose an end-to-end, multi-step LLM agentic framework ATLAS, capable of generating a functional Successive Approximation Register (SAR) Analog-to-Digital Converter (ADC) that successfully passes simulation validation. To adhere to the rigid constraints of analog design, we utilize expert knowledge to ground the LLM in its planning, selection, parameterization, and iterative modification. As part of ATLAS, we introduce Template-Constrained Generation - which unlike other template-based works - builds towards a more generalized SAR ADC generation flow. We demonstrate a strong proof-of-concept of our framework by developing SAR ADCs across technology nodes and input specs. Overall, our expert-knowledge grounded multi-step agentic ATLAS establishes a pragmatic foundation for integrating LLMs into reliable analog design methodologies.

Large language models can synthesize a game's rules as executable code - a Code World Model (CWM) - which a classical planner then searches over. Such models are typically accepted when they reach high transition accuracy on sampled trajectories. We argue this is the wrong notion of adequacy for planning. We show four things. (1) An LLM-synthesized CWM can pass a sampling gate at 100% transition accuracy and be $\geq 98%$ state-accurate on the planner's own search distribution, yet lose systematically at play, because the $<1%$ it gets wrong is exactly the pivotal dynamics; the play cost of the omitted rule is $0.091$ (seed-clustered 95% CI $[0.065,0.117]$, $n=4800$). We call this the verified-vs-correct gap, and confirm it end-to-end through the synthesis pipeline. (2) The harm follows a quantitative law, $\mathrm{danger}=\mathrm{play_cost}\times(1-\mathrm{rarity})^N$, whose $(1-\mathrm{rarity})^N$ gate-miss factor is proven exact and whose play cost is empirically bounded. (3) The failure is not repaired by more data: LLM synthesis behaves as rule translation, not rule inference, and did not infer the omitted rule across models (GPT-5.x) and data regimes (including DAgger and targeted examples). (4) The same mechanism recurs on the belief-inference function of imperfect-information CWMs: we prove a coverage bound (a size-$N$ gate is identifying when $N\gtrsim b^{d_{\max}}$), explaining why shallow games such as Kuhn poker show no gap, and hand-construct Beacon, a verified-but-wrong inference function that passes the gate yet loses every game. These results suggest adequacy for planning-oriented world models should be measured on the search distribution or by play directly, not by prediction accuracy on sampled transitions.

Artificial Intelligence (AI) answer engines now field a growing share of the questions that analysts, scholars, and the public ask about issues of peace and conflict. Large Language Models (LLMs) are known to hallucinate under certain conditions, but do these errors have discernible patterns when they are asked about conflicts, and if so what can that teach us about the changing global conflict information environment? To answer, we first asked a battery of questions about 28 conflicts to five leading answer engines and scored their 5,460 answers against documented evidence. We found that the thinner the retrievable record around a given conflict, the more the engines invent, misattribute, and miscount. Thin records don't just encourage hallucination, but create structural exposure to mis- and disinformation, because they are the easiest records to warp through Generative Engine Optimization (GEO) to bias engine responses. Through an analysis of 1,048 websites that the AI LLMs pulled conflict facts from, we found that GEO source optimization is already happening, and while state-partisan digital capture remains incipient it is rapidly growing. We explain what these findings mean for scholarship with the rise of GEO information warfare, and for policy argue for a return to the deep local monitoring and translation-based research that AI tools cannot replicate, closing with a discussion of future research opportunities and challenges in this fast-moving space.

People use language models for practical questions whose answers are difficult to verify. We show that models exhibit covert value leakage: the information they provide is influenced by their own values, without this influence being disclosed to the user. In one of our evaluations, the user is considering investing in an AI company and wants to know how likely the AI bubble is to pop. Claude Opus 4.8 gives a lower probability when the company under consideration is Anthropic rather than OpenAI. Yet Claude mostly fails to disclose this influence to the user. Covert value leakage is a form of misalignment because it goes against the user's preferences and is likely to mislead them. To investigate this phenomenon, we introduce a suite of evaluations to quantify value leakage and whether models disclose it. We find that models are influenced by different types of values, including preferences for morally good outcomes, for the company that developed them, and for some human leisure activities over others. We often observe large differences among frontier models on the same evaluation. For example, on a Fermi-estimation task, Claude models falsely claim to give unbiased answers in their chain-of-thought, while Qwen models explain how their values bias their answers. Value leakage is a failure mode distinct from sycophancy and reward hacking, and current alignment training and evaluations do not adequately address it.

Personal AI assistants have attracted significant interest for their potential to enhance everyday life by automating routine tasks, supporting consequential decisions, and assisting with everyday personal matters. Yet despite rapid recent technical advances, these assistants continue to exhibit undesirable behaviors, such as sycophancy, overconfidence, and hallucination. We argue that these failures stem from a fundamental limitation: language models lack an explicit representation of the person beyond the context they are given, which we term as the Severance Problem. Even with rich personal context and strong commonsense reasoning capabilities from the backbone model, current AI assistants fail to represent what remains unknown about the user. We propose a simple solution: incorporating structured ignorance into the language model context via the Severance Schema, which explicitly outlines dimensions along which the model lacks knowledge about the user, including physicality, temporality, consequences, continuity, multiplicity, and interiority. Empirically, across five model families, with the Severance Schema, the assistant consistently reduces sycophancy, harmful advice, and hallucination. Notably, models with the schema ask clarifying questions when information about the user is missing, rather than confidently extrapolating from incomplete user information.

In this paper, we study the connection between an LLM's output distribution and the data used to train it. Specifically, we study the degree to which an LLM's next-token distribution agrees with the empirical next-token distribution (ENTD) given the context in the training data. The ENTD is an appealing target because it is the unrestricted global minimizer of the next-token cross entropy loss used for pretraining, as well as an easily interpretable function of the pretraining corpus. We find that for a significant fraction of inputs, the LLM's distribution agrees with the ENTD almost perfectly, and the average agreement increases with model scale and training compute. Nevertheless, there is a long tail of input sequences where the LLM and ENTD differ significantly, and we examine several possible sources of this discrepancy across the transformer architecture, training procedure, and finite-sample noise in the ENTD estimate itself. More broadly, we hope our findings will encourage more work on ``data-centric mechanistic interpretability,'' a complement to standard mechanistic interpretability that opens the black box of how model behaviors arise from the data, rather than how they are encoded in the learned weights.

Large language models often appear to reason reliably, yet on many questions repeated sampling yields both correct and incorrect answers, revealing an underlying fragility in how final decisions are formed. We study whether this fragility can be exploited through implicit reasoning steering: using natural-language text to bias a model toward a designated answer without explicit instructions, triggers, or direct answer cues. Our approach, Concept Chaining, generates a short connection paragraph that links question entities to a target option through one or two intermediate concepts. We then continue pretraining a victim model on these connection paragraphs and evaluate whether its answer preference shifts on the original multiple-choice questions. Our results show that indirect, natural-looking text can systematically steer model predictions while remaining substantially less inferable than direct paraphrases, which shows that reasoning brittleness is not merely an evaluation artifact: it creates a practical channel through which latent biases can be amplified by ordinary-looking text to covertly redirect model decisions.

Reasoning or inference-scaling models are the new generation of Large Language Models (LLMs) capable of complex problem solving. To investigate their problem-solving capability in physics, we evaluated model o4-mini by OpenAI on solving traditional, end-of-chapter problems from Halliday and Resnick's "Fundamentals of Physics," spanning core topics in the undergraduate physics curriculum. Performance was analyzed across modality and problem difficulty. The model solved the problems with overall accuracy of about 90%, but performance depended strongly on representation: accuracy was much higher on text-only problems (96%) than on problems requiring coordinated interpretation of text and images (79%). Accuracy also declined significantly as the problem difficulty increased from low to medium to high. These results show that state-of-the-art LLMs can solve much of the standard introductory physics problems, but that their performance remains uneven and constrained by problem modality and problem difficulty.

Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and harmful intermediate interactions. We propose LOTAPO , a self-generated process-supervision method based on backward leave-one-turn attribution. For each search turn, LOTAPO replaces the turn and its retrieval observation with a fixed [DELETE] placeholder and measures the resulting change in the current policy's mean log-likelihood of the gold answer. This Answer-Likelihood Gain estimates the turn's contribution while preserving all downstream interactions, allowing early evidence to be evaluated in the complete reasoning context. LOTAPO further applies sign-consistency gating, retaining only normalized process advantages whose directions agree with their raw attribution scores. The method requires no additional reward model, teacher, verifier, or LLM-as-a-Judge. Across seven knowledge-intensive question-answering datasets with local retrieval, LOTAPO achieves an average exact-match score of 0.326, outperforming the strongest step-reward baseline, IGPO, by 0.053. Ablations show complementary benefits from backward attribution and sign-consistency gating, demonstrating that policy-derived retrospective attribution can provide effective process supervision for multi-turn search agents.