每天知道
你的领域
出了什么

Foundation multimodal large language models are designed to support a broad spectrum of capabilities across diverse domains. Multi-teacher on-policy distillation (MOPD) provides an effective framework for consolidating domain-specific expertise into a single student model. However, MOPD training gradually drives the student away from its initialization model, and general capabilities decline as the displacement grows, resulting in capability interference. A direct remedy is constraining the student toward its initialization, but this suppresses the acquisition of domain expertise as well. We propose Slow-Fast Multi-Teacher On-Policy Distillation (SF-MOPD), which couples a fast model, the current student updated directly by each teacher, with a slow model, an exponential moving average of the student. The slow model absorbs the learning signal gradually, serving as a moving capability reference that fuses the general foundation with confirmed domain expertise. For each teacher, SF-MOPD computes the teacher-induced update in log-probability space and removes only the component that pushes the fast model further away from the slow model, while retaining aligned and orthogonal components. Experiments across multiple model scales demonstrate that SF-MOPD effectively mitigates capability interference, enhances specialized multimodal capabilities, and reduces the average degradation on general-capability benchmarks, consistently outperforming vanilla MOPD.

Reinforcement learning from verifiable rewards (RLVR) usually optimizes answer correctness, yet useful language-model behavior also requires high-quality reasoning and concise responses. Existing multi-reward post-training methods typically scalarize rewards or combine specialists without explicitly protecting a reward priority order. This is problematic when trade-offs are asymmetric: conciseness, for example, should not improve at the cost of correctness. We introduce Lexicographic Multi-Objective On-Policy Distillation (LMOPD), a multi-teacher method for integrating reward-specialized policies under explicit priorities. For each student rollout, LMOPD selects the specialist for the first objective whose gate detects a deficiency, then locally projects its centered log-policy correction to remove components that oppose higher-priority specialists. We evaluate 30B-A3B mixture-of-experts transformer models in two- and four-expert settings on three math benchmarks, measuring retained specialist gains. With two experts, LMOPD's point estimates fully retain the accuracy and reasoning-quality gains while acquiring $46.9%$ of the conciseness gain. With four experts, it retains $\approx90%$ of both the accuracy gain and reasoning-correctness gain, compared to only $\approx57%$ by the next best evaluated baseline. Matched four-expertablations show that lexicographic routing outperforms random routing and that projection further strengthens both top-priority capabilities. Across both scales, LMOPD preserves the highest-priority capabilities more effectively than the existing baselines we evaluate, demonstrating the value of explicit priorities for specialist integration.

Vision foundation models such as DINOv2, SigLIP2, and MASt3R develop complementary capabilities from different pretraining objectives, yet their knowledge remains distributed across separate, specialized models. Multi-teacher knowledge distillation offers a path toward consolidating these capabilities into a single agglomerative backbone, but existing approaches assume a fixed set of teachers, and incorporating a new teacher requires repeating expensive joint distillation over the entire teacher set. We introduce GRAFT, a continual multi-teacher distillation framework that enables a unified backbone to progressively acquire capabilities from an open-ended sequence of foundation models. When a new teacher arrives, GRAFT treats the previously distilled model as a teacher for preserving learned capabilities, while the current student jointly learns from both the previous model and the incoming teacher. Furthermore, to reconcile the incompatible representation geometries of heterogeneous teachers, we introduce Teacher Specific Readout Tokens, which grant each teacher an independent read-out of the shared encoder, together with Geometry Agnostic Relational Loss that aligns a vision-language teacher by matching image-text similarity structures rather than raw feature values. We provide GRAFT model, which is a single, continually extensible backbone that unifies five domains, including image understanding, 2D dense prediction, 3D human pose estimation, 3D vision, and vision-language, delivering strong performance across all of them while acquiring each new capability at the cost of a single distillation rather than a full re-distillation.

A robot demonstration records two things in the same frames: what happened to the objects, and how one particular arm made it happen. We condition on the first. A demonstration is compiled into an effect program: the 3D keypoint trajectories of the objects that moved, two points marking where each was held, and the configuration the scene ends in, with the demonstrator removed. PEWAM, a 71.5M-parameter world-action model, generates effect, robot execution, action and terminal state as four streams with independent flow-matching times, so clamping a program and sampling the execution turns inference into programming, re-solved closed loop from the live scene. On held-out LIBERO-Goal tasks, one demonstration's program completes 40 of 90 episodes, where the same backbone given a goal image or language, and published demonstration-conditioned methods, complete at most 19; on three of Meta-World's held-out classes it exceeds the best published results, though not on the five-class mean. Because a program is a set of coordinates, a person can edit it: the placement follows a shifted terminal state and the grasp turns with rotated contact points. The same program runs on four robot arms without retraining, and after a push, re-solving completes 23 of 60 episodes where replaying the demonstration completes 6. On a Franka arm, fine-tuned on real demonstrations of other tasks, programs compiled from single human videos complete 36 of 40 trials, against 22 for the same backbone conditioned on the video's last frame as a goal image.

World action models (WAMs) have emerged as a promising paradigm for robotic control by jointly predicting future visual dynamics and actions from an initial observation and instruction. However, existing WAMs struggle with long-horizon prediction, as generating dense video rollouts is highly inefficient. Some recent WAMs address this by predicting a single future frame without generating the full video, but this approach neglects how to progress toward the goal. We present ProWAM, a progressive world action model that jointly predicts actions and an ordered sequence of sparse visual sub-goals, providing explicit visual guidance to anchor action generation throughout task execution. This design scales naturally, as sub-goal prediction can be learned from large-scale action-free videos, allowing the video backbone to offload complex visual planning from the action policy. For efficient action generation, ProWAM executes a single video-backbone forward pass to cache sparse sub-goal features, eliminating iterative full-video generation and requiring only lightweight action denoising during replanning. Across extensive evaluations, ProWAM achieves superior out-of-distribution robustness. On simulation benchmarks, it sets new state-of-the-art results on LIBERO-Plus (85.8%) and randomized RoboTwin (75.7%), outperforming the strongest baseline with relative gains of up to +35.9%. On RoboCasa365, ProWAM achieves a 48.1% success rate and 18.2% on the challenging Composite-Unseen split, ranking 4th overall. Crucially, in zero-shot real-world experiments, ProWAM achieves 70.0% success, outperforming the strongest baseline by +15.0 (from 55.0% to 70.0%, a +27.3% relative gain) in novel scenes. These results demonstrate the value of progress-indexed visual foresight for closed-loop control. Our program is in https://sii-ferenas.github.io/ProWAM-page.

Interactive world models are increasingly capable of generating environments and acting within them, yet deliberately editing an existing executable world remains underexplored. We formulate world editing as intervening on an existing world while preserving properties that should remain unchanged, and introduce intervention depth as an axis describing how strongly an edit couples world entities, dynamics, and systems. We instantiate this capability through industry-grade game modding and introduce IGMWorld, together with IGMBench, a benchmark of 110 tasks and over 1.1K executable state and behavioral criteria across Minecraft and Terraria. The tasks span property, entity, dynamics, and system interventions and are evaluated through deterministic executability, behavioral, preservation, and visual checks. Frontier coding agents already exhibit substantial world-editing capability: the strongest configuration solves 78.2% of tasks under a strict task-level criterion, while criterion-level performance reaches 94.8%. Reliability generally decreases with intervention depth, and this pattern persists even among tasks with similar numbers of evaluation criteria. Most failed edits still build and load successfully, suggesting that the main difficulty is making the edited world behave as requested. Visual consistency remains a separate weakness, with all evaluated configurations below 50% joint visual pass rate. These results show that world editing is a distinct capability from world generation and interaction, and that executable games provide a practical testbed for studying it.

We introduce IGNITE, a generative world foundation model for fusion plasma behavior simulation trained in a self-supervised manner from over a decade of unlabeled experimental data at the DIII-D National Fusion Facility. The core of IGNITE is a dynamics model that can simulate DIII-D discharges from a given set of actuator trajectories. These trajectories can be supplied or generated on-the-fly from a textual prompt or from desired experimental outcomes. The model architecture consists of several spatio-temporal tokenizers that embed the different input modalities, including time-series like spatio-temporal measurement data, image sequences, and high-resolution spectrograms, each of which collected at vastly different time scales. The backbone is composed of an auto-regressive dynamics model that has the capacity to predict entire DIII-D discharges given initial latent plasma states and actuator trajectories over a theoretical infinite horizon. IGNITE paves the way towards efficient AI-driven experimental planning and world modeling for nuclear fusion.

Text-to-image generation enables users to explore several images generated from the same prompt. For these generated images to be useful, each one must reflect the user's preferences, measured by a learned reward, and differ visually from the others to maintain diversity. Existing methods are limited: they either address reward and diversity separately or combine them in one aggregate score, enabling high diversity to offset low rewards. In this paper, we address these limitations by formulating generation as satisficing: every image (candidate) must satisfy a reward floor and the batch of images must satisfy a diversity cutoff. The reward floor controls the balance between worst-candidate reward and batch diversity; we show that varying this floor defines a Pareto frontier. To traverse this frontier, we introduce SatisDive, a training-free inference-time method. SatisDive uses a batch-relative reward cutoff to distinguish lower- from higher-reward candidates, emphasizing reward improvement for candidates below the cutoff and diversity among candidates above it. On Pick-a-Pic, at matched DreamSim, SatisDive improves worst-candidate reward over FK steering by up to 0.43 with FLUX.1-dev as the base model and HPSv3 as the reward, and by up to 0.70 with SANA-1.6B as the base model and ImageReward as the reward. More broadly, across their overlapping DreamSim ranges, SatisDive's satisfaction-diversity curve Pareto-dominates FK steering's curve in each setting.

Existing 3D large language models (LLMs) compromise on two fronts: they compress shapes into latent codebook indices or coordinate text, which removes spatial structure from what the model observes, and they acquire the 3D modality by fine-tuning the backbone, which overwrites its general language ability. We present OctLLM, which addresses both limitations. Geometry enters as an explicit 3D sequence of octree occupancy tokens. However, full octree sequences grow rapidly with depth; OctLLM therefore randomly empties penultimate-level nodes and omits descendants while preserving shape, yielding a shorter coordinate- and depth-anchored Sparse Octree (S-Octree) for position-aware mask-modeling generation and 3D understanding. On the other front, existing methods introduce a new modality with full fine-tuning or LoRA, but full fine-tuning is costly, LoRA limits 3D capacity, and both modify the language pathway. OctLLM instead adds 3D capacity in parameters separate from the pretrained ones: mesh tokens are routed through independent trainable branches in a subset of blocks while text and image tokens retain the frozen vision-language pathway, and the two streams interact through shared self-attention. It trains far fewer parameters than full fine-tuning, yet sets a new state of the art among unified multimodal LLMs, lowering image-to-3D FID by $17.4%$ and raising render-grounded captioning by $28.7$ points over ShapeLLM-Omni, while matching the backbone on general language benchmarks.

Flow-map distillation enables one- and few-step generation by learning finite-time transitions of a pretrained generative ODE. We investigate whether changing the teacher's time parameterization can make these transitions easier to learn. Motivated by the hypothesis that trajectory segments with large normal acceleration are harder to distill, we propose a geometry-aware time reparameterization that allocates more student time to these regions while preserving the teacher's geometric paths and terminal distribution. We derive a shared clock that equalizes a population normal-acceleration statistic under suitable assumptions, and construct a practical approximation from robust, regularized estimates across teacher trajectories. We incorporate this clock into Lagrangian flow-map distillation, using the transformed time coordinate to condition the student. The clock is estimated once before distillation and requires neither teacher retraining nor additional student parameters or inference-time network evaluations. Experiments on synthetic data, CIFAR-10, and CelebA-64 show improved sample quality over identity-time distillation at matched inference budgets, including improvements in one- and two-step image generation. The gains in one-step generation, where no intermediate sampling times can be adjusted, highlight the benefits of time reparameterization during distillation.

Long-video generation and world models have shown strong potential for interactive entertainment and embodied simulation by predicting future observations conditioned on user actions and historical memory. However, as memory sequences grow longer and their structures become increasingly complex, managing long-range spatial context becomes increasingly challenging, calling for a more intelligent and systematic memory-management strategy. Building on the advancing spatial reasoning capabilities of multimodal large language models (MLLMs) and the broader vision of unified models, we propose Spatial Memory Intelligence (SMI), the first framework to systematically employ an understanding model for spatial-memory management in long-video world models. SMI introduces four coordinated atomic operations: spatial clustering, within-cluster sparsification, action-aware retrieval, and reliability-aware filtering. Extensive experiments across multiple baselines, benchmarks, and world-model backbones demonstrate the effectiveness and generalizability of SMI, achieving comprehensive improvements in memory sparsity, generation stability, and spatial consistency.

Training-free safeguards for text-to-image generation often rely on a reusable safety signal, such as an unsafe direction or global toxic subspace, applied broadly across prompts. We provide a controlled geometric analysis of this global-unsafety assumption and reveal a consistent coverage-selectivity trade-off: compact unsafe subspaces fail to cover heterogeneous unsafe semantics, whereas broader aggregation increasingly distorts safety-adjacent benign prompts. Motivated by this finding, we propose CALM (Counterfactual Adaptive Local Modulation), a training-free safeguard that replaces uniform global removal with prompt-local counterfactual correction. Using matched unsafe-benign anchors, CALM routes each prompt to active unsafe categories, minimally edits only violating token representations toward the safe side, and suppresses positively aligned unsafe residual components. Across broad evaluation, CALM significantly improves unsafe content suppression while preserving benign utility, demonstrating that local counterfactual correction provides a more selective alternative to global unsafe signal removal.

Diffusion transformers (DiTs) generate high-fidelity images from text and image conditions, but their outputs carry large variance and their faithfulness to a desired target depends heavily on how the condition is supplied. We present DAGS, a lightweight, attention-free, disentangled appearance and geometry conditioning scheme that steers a frozen image DiT to produce high-fidelity, highly faithful, and independently controllable renders. Two small convolutional encoders compute conditioning features once per frame and inject them as a learned, per-layer, element-wise residual into the image tokens, avoiding the quadratic cost of stacking conditions through attention. Because control and temporal handling live outside the frozen backbone, we retain its vast pretrained prior and eliminate backbone-overfitting risk. We further add a small recurrent lighting stabilizer and a training-free temporal guidance term that, coupled with our conditioning, elevate a per-frame image model into a streaming renderer. DAGS produces controllable, high-quality renders at a fraction of the compute of path tracing; it is not real-time, trading compute for controllability and quality. On a matched 1-spp + G-buffer input, per-frame DAGS reconstructs +8.6 dB / +10.1 dB PSNR over the real-time denoiser Intel OIDN and the diffusion renderer RGB<->X while being 2.5-8x more temporally stable perceptually (temporal-LPIPS flicker).

A family of tabular anomaly detectors trains a neural map toward a fixed target under squared-error loss and scores anomalies by the test-time residual; contraction matching, one-step rectified flow, and reconstruction autoencoders all fit this template. We characterize a convergence collapse: better optimization makes the detector worse. At convergence, the learned map tracks the target even off-distribution, so the residual signal vanishes on anomalies as well as on normal data. These detectors therefore rely on implicit non-convergence (early stopping, capacity caps) to retain signal. We argue this is structural: effective anomaly detection requires a locality constraint that blocks unconstrained extrapolation. Classical detectors (kNN, KDE, isolation forests, LOF) enforce locality explicitly; fixed-target neural detectors do not. We formalize the connection by showing that the kernel-regression analog of a fixed-target detector is a finite-bandwidth Nadaraya-Watson smoother, which we call Kernel Contraction Matching (KCM). KCM is closed-form, training-free, and CPU-efficient, yet matches established neural baselines on ADBench. Building on this bridge, we introduce the Kernel-Anchored Regularizer (KAR), which penalizes deviation of the neural prediction from a kernel-weighted average of training targets. Across collapse-prone ADBench datasets and three backbones, KAR mitigates collapse and improves AUROC under prolonged training.

Generative graph models are central to understanding and simulating complex networks. However, existing approaches have complementary strengths and limitations. Mechanistic models offer interpretability but rely on instance-specific estimation methods. Deep generative models, on the other hand, offer amortized inference at the cost of interpretability and are largely limited to graph sizes seen during training. Scientific applications motivate a framework that retains the strengths of both paradigms. We bridge them by formulating both the generative model and parameter recovery in function space. A multifractal step graphon extends standard step graphons with a recursive construction that compactly parameterizes complex networks. This formulation admits a neural inverse operator to recover its parameters, enabling inference on unseen graph sizes. We evaluate our model, trained only on synthetic multifractal step graphon realizations, against both paradigms. Against a graph foundation model pretrained on empirical networks, our method achieves the best average performance on three of four metrics in a zero-shot graph-generation benchmark, indicating that the model transfers to real-world graphs. We also apply our method to single-observation networks, a regime largely inaccessible to deep models that require training corpora, where it performs comparably to an instance-specific method that optimizes on each graph. In a multi-subject EEG case study, the inferred parameters track a reversible change in brain state more sensitively than traditional network statistics. Together, these results indicate that mechanistic interpretability and amortized inference can be effectively unified in a generative graph model to enhance our understanding of complex networks.

Inference-time control steers a pretrained generative model towards a target distribution without retraining. We study tilted targets $π_0\propto G_0\,p_0$, where $p_0$ is the sampler output distribution and $G_0$ is an evaluable reweighting function. Existing approaches rely on sequential annealing with sequential Monte Carlo (SMC) or parallel annealing with replica exchange (RE). Sequential control is exact but needs large particle populations, whereas no exact parallel control method exists: existing RE corrections approximate an intractable time reversal and are biased. We propose Exact Non-equilibrium COntrol with Replica Exchange (ENCORE), the first exact parallel control method. Each replica stores its generation trajectory, so the upward move is a truncation and the intractable time reversal is never simulated. We prove target invariance and show that the resulting dynamics are those of non-equilibrium replica exchange with the exact time reversal as forward proposal. Under regularity conditions, our diffusion analysis shows that both sequential and parallel control become unstable under refinement of the time discretisation without guidance, whereas guided proposals remain stable and yield diagnostics for tuning the schedule and the computational budget. Across synthetic targets, Boltzmann sampling of biomolecules, and image generation, ENCORE achieves competitive accuracy and diversity, remains robust to sampler perturbations, and applies to distilled samplers where existing RE corrections are unavailable.

Sampling from the posterior is the central task of computational Bayesian inverse problems. The standard workhorse in Bayesian inference - Markov chain Monte Carlo (MCMC) - is sequential, yields correlated samples, and must be rerun for each observation. Conditional flow matching offers an amortized alternative: a transport map, trained once on joint samples of parameter and data, that yields independent approximate posterior samples for any observation at negligible online cost, without new likelihood evaluations. We give a careful, MCMC-literate assessment of flow matching for PDE-based inverse problems with function-valued parameters. Exploiting the flow's tractable density, we derive computable accuracy estimates of the underlying approximate posterior in total-variation distance and Kullback-Leibler divergence and, moreover, propose a hybrid sampler that is asymptotically exact by Metropolization. We validate the accuracy estimates and demonstrate the amortization in several numerical examples, including electrical impedance tomography and a likelihood-free Lotka-Volterra model.

World models (WMs) simulate the transition dynamics of environments, enabling agents to plan over the consequences of their actions. In text-based environments, fine-tuning a Language Model (LM) to serve as a WM has emerged as a dominant paradigm. However, despite the widespread success of non-parametric approaches such as Retrieval Augmented Generation (RAG), retrieval for LM-based world modelling remains underexplored. We conduct a systematic evaluation across five diverse environments spanning embodied, web navigation and social settings, comparing fine-tuning and RAG-based approaches for LM-based world modelling. Our study reveals that fine-tuning often outperforms RAG, with fine-tuned WMs enabling agents to obtain higher rewards on 15/20 settings. While both construction paradigms benefit from additional and more diverse exploration, RAG-based approaches prove more data-efficient, and fine-tuning approaches disproportionately benefit from scaling the amount of experience collected. With a focus on RAG-based WMs, we devise a procedure that uses counterfactual intervention to estimate the error rate of the retrieval stage, and show that retrievers consistently surface suboptimal transitions from the experience buffer. Hoping to address this failing, we study a variety of query reformulation strategies, demonstrating that a hierarchical approach outperforms the traditional retrieval pipeline. Finally, we compose our findings into a hybrid world modelling system that parametrically captures core environment dynamics, while learning to rely on retrieval from an actively maintained memory store. Our hybrid system consistently outperforms other methods across multiple environments and models, showcasing the robustness of the approach and the applicability of our findings.

Agent harnesses make many small, typed decisions per task: which model to call, which tool to use, whether retrieved text is relevant, whether an input carries an injection. System-1 decision models answer such questions in a single forward pass with class probabilities, promising large cost and latency savings over LLM calls. We present a paired evaluation of an open-weight (Laya) and a hosted (Jev) System-1 model on 11 agent decision points built from 18 public sources: 7,283 base cases plus 6,640 robustness variants, with byte-identical inputs, paired tests, and cross-hardware and cross-day reproducibility checks. Jev is significantly more accurate on 9 of 11 decision points (+10.8 to +46.0 pp). Neither model beats chance on zero-shot model routing, and they tie on RAG relevance gating. Laya changes 30% of its answers when the option order is reversed and degrades sharply with many or similar candidates (31% at 50 nearest-neighbour tools, vs. 98% for Jev on items with a unique correct tool). We also audit our own pipeline. Three analysis errors and one design confound distorted headline deployment claims: an omitted pre-screen cost (reported 23.9% saving, actual 4.3%), gate accuracy reported as end-to-end quality (58% vs. 98%), in-sample thresholds (5% target, up to 17% held-out misses), and a "channel effect" on injection false positives that vanishes with channel-native content. Two other suspected confounds did not change the conclusions. All cases, raw outputs and analysis code are available at https://github.com/David-DL-Space/sys1-eval.

Agents are increasingly given open-ended research tasks: discovering an empirical law from self-designed experiments, improving a heuristic whose optimum nobody knows, or beating a standing record. Their execution logs record every step of this research, yet the runs are still judged by their outcome score. That score alone does not establish whether an agent's claims follow from executed experiments, and a reference answer may be unavailable. We evaluate the agent's epistemic process: how it forms hypotheses, tests them, and revises them in response to evidence. We introduce OEB (Open-Endedness Bench), a benchmark-agnostic methodology that reads only the agent's execution record and never a reference answer or an outcome score. OEB compiles the record into a unified epistemic event graph whose edges connect the propositions the agent states to the executed actions that test them; each node carries an exact excerpt that code verifies against the record. One principle governs scoring: prose can state a proposition, but only evidence returned by an executed action can support or refute it, so OEB checks what the agent writes against what it actually ran. From the graph, OEB scores four competence axes (evidence, experiment, revision, and no reward hacking), mostly as the share of opportunities for sound research that the agent took, and profiles six subjective persona traits that describe the agent's research habits. We score 119 existing runs over 12 tasks from three benchmarks: LLM post-training, chip design, and a training-speed record. Against logged results, only 16-29% of the improvements agents claim are real. On 9 of 10 tasks, the best run tries more new ideas in its second half than the worst run. The persona readings follow the model: for every trait, the model that ran explains more of its variance across runs than the task (a median of 43% against 7%).

We study long context language models. Instead of training long context natively, or designing a long context harness, we train a model over the simplest possible harness: a tool to call itself with any specified prompt and a tool to read tokens in a range from the input context. We finetune Qwen3.6-35B-A3B on a diverse synthetic dataset using this harness. With only 8,000 tokens of context, our small model is as strong as GPT-5.4 with 1M tokens of context on the OOLONG-synth benchmark when document length exceeds 40K tokens.

We present MeshQuery, a training-free agentic approach to automatic UV unwrapping of production-grade quad meshes. A Vision-Language Model (VLM) plans artist-aligned seams using a set of edge-selection tools, conditioned on domain-specific UV-unwrapping knowledge expressed in natural language and refined with a feedback loop. We design a queryable mesh representation together with a domain-specific language (DSL) that enables the agent to retrieve mesh information on demand, express a seam plan as a compact program of edge-selection operators over topological, geometric, and semantic mesh attributes, and iteratively refine it from UV quality feedback. On Adobe Substance 3D and Toys4K meshes, MeshQuery produces 2.9x/4.29x fewer charts and 1.63x/1.7x shorter seams than the strongest baseline, and professional artists prefer its results in 80.9% of comparisons. Ultimately, decoupling high-level intent planning from low-level edge selection and compact mesh representation lets MeshQuery run on different backend VLMs and scale to meshes an order of magnitude larger than autoregressive seam prediction

Co-designing ML models and the accelerators that run them is an unusual reasoning task: architects must draw confident, high-stakes conclusions about systems that do not yet exist, and the pace of both model evolution and hardware cadence means the analysis burden grows every quarter. The evidence behind each decision--hundreds of gigabytes of fresh simulation sweeps over novel design points--is by construction absent from any LLM's pretraining corpus, and there is no external literature to retrieve; naive "chat-with-your-data" approaches hallucinate exactly where correctness matters most. We present Coco (Copilot for Codesign), an agentic platform deployed with TPU architects that accelerates the co-design lifecycle of setting up experiments, sweeping simulators, and deriving insights. Coco is built as four layers: (i) a datastore that automatically registers every simulation sweep into a normalized relational schema, so agents ground every number in a SQL query rather than scraping heterogeneous files; (ii) a library of tools with typed APIs that agents compose without human orchestration; (iii) agents that encode recurring analysis workflows--most notably iso-execution analysis, which compares systems at matched execution configurations, including swept-but-dominated points off the Pareto frontier; and (iv) a platform UX whose navigation state doubles as agent context. We report early deployment experience toward a reduction in time-to-simulation and time-to-insight, and argue that co-design is a distinct agentic domain: its data must be retrieved rather than memorized, its workflows are recurring but context-dependent, and expert adoption hinges on UX that balances IDE-style control with interactive exploration.

Language-model agents increasingly rely on harnesses that manage bounded context, persistent memory, tools, verification, and repeated execution, yet existing notions of model capability do not quantify the computational resources these mechanisms consume. We introduce the Language Model Agent Machine (LAM), a resource-bounded abstraction that fixes the underlying semantic model while explicitly charging harness-level resources. We establish four classes of results. Communication: LAM execution is instancewise equivalent to red--blue pebbling under simultaneous call--transfer budgets, transferring classical I/O lower bounds to context--memory traffic. Access: memory interfaces induce asymptotic separations, including a $Θ(n)$ gap between random and non-speculative sequential access on pointer chasing. Recomputation: bit-reversal DAGs require $Θ(n^2/(C+S)+n)$ model calls with context capacity $C$ and persistent-memory capacity $S$, quantifying when stored intermediate state avoids repeated semantic computation. Reliability: we derive tight stage-local sampling bounds, exact imperfect-verification costs, and a Young--Daly-type checkpoint law with a closed-form optimal verification interval. Controlled and held-out experiments on GPT-6 Astra test communication and reliability predictions, including checkpoint optima, policy selection under programmatic checking, and tradeoffs among call granularity, logical input traffic, and reliability on chained MATH tasks. Together, these results provide a resource theory for the computational cost of language-model agent harnesses.

AI coding agents are untrusted system components, yet they require autonomy on the developer machines they run on. This contradiction is a security problem. Sandboxes provide an isolated environment, but for local macOS development, the existing local, open-source options for AI coding agents are few in number and cumbersome to use. I conducted a formative online user survey which indicates that fewer than 40% of AI coding agent users run their agents in a sandbox and identifies the top usability barriers hindering AI coding agent sandbox adoption. These findings are used to develop SideKernel: an open-source, local, microVM-based macOS sandbox for AI coding agents designed for usability. To evaluate SideKernel, I compiled a list of sandboxes available on the market and filtered it against five inclusion criteria. Then I performed a comparative analysis between SideKernel and the sandboxes that satisfy these criteria, across 23 capability tests derived from the usability barriers revealed by the user survey. I discovered that only a few sandboxes are similar to SideKernel, and that among those, Docker Sandboxes and SideKernel score highest on capability features related to usability. A secondary contribution of this paper is a survey of the existing solution space for local, open-source, microVM-based macOS sandboxes for AI coding agents.

Coding agents are extending their reach into the physical world by writing and executing robot control programs. One might expect the agents to use the existing mature software stack that engineers have developed over decades to access sensors and control motion. Yet prior work primarily engineers complex custom harnesses to orchestrate agents for robot use, particularly by prescribing specialized workflows and providing bespoke interfaces. This raises the question: "Is such additional harness engineering necessary?" We introduce OpenRUA, a zero-abstraction harness that bypasses bespoke abstraction layers by providing off-the-shelf coding agents with only terminal access to the robot's native software interface ROS 2. OpenRUA employs a minimalist workspace-as-harness design, only offering ROS 2 documentation and basic tools while leaving the coding agent to organize its own work without orchestrating any agentic workflow. Within this workspace, OpenRUA recasts perception as file I/O and manipulation as coding. With Claude Code powered by Claude Opus 5, OpenRUA achieves success rates of 99.0% on CaP-Bench and 87.0% on LIBERO-PRO, demonstrating that an off-the-shelf coding agent can serve as a zero-shot visuomotor policy through the robot's native interface, without bespoke primitives or task-specific training. Under this minimalist design, further analysis reveals striking emergent behaviors of coding agents: (1) For perception, the agent spontaneously writes programs that process raw sensory inputs and derive metric measurements in 96.80% of episodes. (2) For manipulation, the agent spontaneously builds motion-control clients (e.g., gripper control) in 95.87% of episodes and closed-loop control programs (e.g., adjusting motion based on sensor feedback) in 50.13% of episodes. Our code is available at https://github.com/terminalworld/OpenRUA.

Personalized LLM assistants must recover sparse evidence from long conversation histories across queries of varying complexity. We introduce APDMem (Agent-controlled Progressive Disclosure Memory), a hierarchical long-term memory architecture that applies progressive disclosure to memory retrieval. Rather than relying on a flat memory store or fixed retrieval granularity, APDMem represents conversation history as four progressively detailed layers: thematic summaries, personalized key facts, turn-level evidence notes, and raw messages. At inference time, a controller applies progressive disclosure to the memory hierarchy: it first reads high-level summaries and drills into finer evidence only when needed. This creates an adaptive cost-fidelity trade-off: simple queries can terminate early, while complex temporal, multi-hop, or exact-evidence queries trigger deeper inspection. A note synthesizer converts retrieved evidence into a query-focused structure that consolidates facts, orders events, and flags contradictions before final answer generation. Experiments on LongMemEval show that APDMem achieves strong performance for long-context memory reasoning while accessing only 8% of the total conversations.

Developing cognitive models of algorithmic reasoning from behavioral data is a central problem in cognitive science that challenges current methods. Traditional approaches to cognitive modeling are interpretable and benefit from human expertise, but lack flexibility and scalability. Emerging techniques using large language models (LLMs) for de novo generation of cognitive models are scalable and flexible, but lack a role for human expertise and have mostly been applied to simpler tasks than algorithm recovery. We propose a hybrid system that treats discovery of cognitive algorithms as a program refinement problem. Human-created cognitive models are expressed as probabilistic programs and provided to a system of LLM agents with a mandate to: identify mismatches between model and behavior; propose code-level modifications within researcher-specified constraints; and verify structural fidelity. Revisions propagate to a probabilistic inference module that performs inference for latent variables and data likelihood computations. We evaluate the pipeline on human behavior in a problem-solving paradigm that exposes a variety of cognitive algorithms. Revised models consistently improve model fit relative to ancestral models and reveal a small set of recurring innovations that capture meaningful behavioral variability in this task.

We present OpenGameEval, a benchmark and evaluation framework for agentic game development inside Roblox Studio. It runs language models as agents in reproducible, stateful game-engine sessions and scores each run with executable checks, both on the edited scene and in a simulated play session. Most agentic coding benchmarks require exploration but score only final task success. OpenGameEval separates observation tools from editing tools in its eight-tool action space, so exploration can be measured directly. We measure the pass rates and exploration behavior of 13 frontier models on 84 human-curated core tasks, with 16 attempts per task. The tasks are hard for current models. The best model solves 51.7% of tasks on a single attempt and 39.4% five times out of five, and no tested model solves six of the tasks. Models at the frontier reach similar pass rates by solving different tasks: splitting tasks by the kind of work they require spreads the top five by 5.0pp on script-authoring tasks and 12.5pp on scene-change tasks. Exploration behavior predicts whether a run succeeds. Holding task and model fixed, a run that inspects every object a reference solution touches before acting on it passes 13.4pp more often than a run that inspects none of them on scene-only tasks, and 9.8pp more often on script-only tasks. We release the task suite, its place files, the per-task annotations, a plugin that runs the tasks inside Roblox Studio, and an updated leaderboard under the MIT license at https://github.com/Roblox/open-game-eval.

Medical vision-language model (VLM) evaluation is sensitive to workflow design, prompting strategy, and benchmark construction, yet most studies treat these factors in isolation. We introduce a reliability stress test for chest X-ray interpretation built on two balanced datasets (a private report-backed set and a curated MIMIC subset). Three medical VLMs (CheXagent, MedGemma-4B, and MedGemma-27B) are evaluated across three prompt styles and two workflows (single-VLM and multi-agent), producing 36 configurations. We show that exact-match accuracy alone can overstate the effectiveness of conservative models that default to "Normal" predictions. Diagnostic reliability also depends heavily on model family and scale: multi-agent reasoning helps some configurations but hurts others. Building on these observations, we propose a decision-time routing framework that selectively escalates to multi-agent inference only when beneficial, improving the cost-quality trade-off over fixed workflows. Our results highlight the need for evaluation protocols that jointly consider prompt sensitivity, failure-mode diversity, and workflow choice before clinical deployment.