Energy-based models can represent distributions over discrete structures such as molecular graphs, but an energy that is accurate at equilibrium need not yield accurate samples when the sampler stops after a fixed number of steps. We introduce finite-horizon energy learning, which adapts the acceptance energy of a Metropolis--Hastings sampler to the distribution it returns after a prescribed number of steps, with initialization, proposals, and annealing schedule held fixed. For graph generation, a frozen pretrained model supplies initialization and proposals, and a learned energy governs acceptance. A training-only discriminator scores completed samples, and coupled continuations of the accepted and rejected branches of a proposal give an acceptance-gradient estimator that is unbiased for a fixed discriminator under stated conditions, without equilibrated negative samples or differentiation through discrete states. Generation uses the learned energy in the original single-trajectory sampler, without discriminator evaluations or reranking. On twelve pairwise binary targets with exactly evaluated terminal laws, learned energies have lower median terminal total variation than the equilibrium-correct energy in every tested short-horizon setting, and than its numerically tuned scalar multiple in most settings. On MOSES, a learned two-coefficient combination of pretrained Graph Energy Matching (GEM) potentials lowers FCD by 3.7--10.5\% relative to scale-calibrated GEM at matched sampling steps, with validity gains at the shortest budget and a sub-point validity trade-off at higher budgets.

Sampling multiple chain-of-thought rationales from a language model can uncover correct solutions missed by a single attempt. However, these rationales are typically lengthy, making repeated autoregressive generation costly. Continuous latent reasoning offers a compact alternative, but point-valued methods condition repeated answer sampling on a single rationale, which can limit exploration of diverse paths and answer coverage. We thus propose rationale distribution distillation (RDD), training a conditional flow over fixed-length latent sequences by distilling from multiple textual reasoning paths. Furthermore, we expand the distillation targets through within-query mixup, interpolating between complete latent rationales for the same query. The flow nonautoregressively generates the entire latent sequence, and a frozen language model autoregressively decodes answers from sampled rationale contexts. Empirically, the resulting distributional reasoner achieves higher answer coverage than the evaluated point-valued latent reasoning baselines, particularly on advanced mathematical tasks.

Spatio-temporal forecasting is fundamental to many real-world systems, yet deployment environments are inherently varying: temporal distributions may evolve, spatial domains may change, and observation availability may shift from training conditions. Existing models are often tightly coupled to their training environments through node-specific representations, predefined spatial support sets, and reliance on consistently available observations, limiting generalization to changing environments. To this end, we propose VaryST, a compact spatio-temporal forecasting model trained from scratch that achieves strong generalization by dynamically constructing predictive context from available long-term observations. To accommodate temporal changes, VaryST derives node representations from long-term histories, capturing current behavior in the context of longer-term patterns. To adapt to spatial changes, it dynamically selects functionally relevant support nodes beyond predefined neighborhoods and integrates their information with recent and long-term target states and global context. To handle varying observation availability, VaryST selectively masks historical patches on which the model relies most during training, encouraging it to exploit alternative temporal and spatial dependencies for accurate forecasting when key observations become unavailable. Extensive experiments on six real-world datasets against seventeen baselines show that VaryST achieves strong in-domain forecasting accuracy, substantially improves zero- and few-shot generalization under spatial and temporal changes, and remains robust to varying observation availability.

Large language models (LLMs) hold broad knowledge in one set of weights, but lack interpretability and trustworthy reasoning, especially in high-stakes use cases. A neuro-symbolic model, with its interpretable architecture and System 2 reasoning capacity, is a promising alternative if built at the scale of LLMs; however, its symbolic backbone is usually constructed with human effort, so existing neuro-symbolic models are bottlenecked by the scope of the symbol component and usually domain-specific. A data-driven method could instead build a larger symbolic system by aligning and merging existing ones. We target its first, foundational step: matching units across these heterogeneous systems. Our method, SAE-IDF, encodes a symbol in its native context into a sparse code with a sparse autoencoder (SAE), re-weights each dimension by its rarity and matches across systems. On 12 tasks across 6 kinds of symbolic system, SAE-IDF outperforms the same LLM's dense baseline on all tasks with Gemma-2-9B and all but one with Llama-3.1-8B, by up to 45 points, consistently across SAE layers and configurations. SAE-IDF is also interpretable: every dimension of the sparse code has a human-readable meaning, so each match decomposes into named concepts (features). Our work paves the way to a universal symbolic backbone.

We propose DAGFormer, a Transformer language model whose cross-layer connections are planned by a jointly trained topology predictor. Beyond the residual connections in a standard Transformer, DAGFormer adds direct connections from earlier layers to later ones, and the predictor controls the strength of every connection based on input tokens. Unlike existing cross-layer routing architectures, which set each layer's connections separately, DAGFormer plans the routing of the whole model at once. On matched OLMo-2 pairs from 75M to 1B parameters, DAGFormer lowers WikiText-2 perplexity by 17% to 25% over the vanilla Transformer, and a 1B DAGFormer trained on 5B tokens outperforms the vanilla model trained on 10B. Against four routing baselines with the same data and budget, it reaches the lowest perplexity at 75M, 300M and 1B. The gain carries over to 13 commonsense, science, reading and math evaluation tasks (2.0 to 2.5 points higher mean accuracy at 300M and 1B) and to instruction finetuning (63% to 70% AlpacaEval win rate against the vanilla Transformer, leading every routing baseline), and under structured pruning DAGFormer degrades the least in five of six settings.

Repeated event forecasting requires extracting predictive signals from noisy evidence and evaluating their value across successive decisions. We introduce JockeyBench, a benchmark and evaluation protocol that studies this problem through historical Japanese horse racing. The protocol combines time-gated evidence, priced tools, paired frozen-program controls, and two workflows: executing an LLM-written predictor or acquiring evidence for a fresh per-race LLM forecast. Evaluation separates forecast quality, benchmark-specific net utility, and retrospective betting returns and risk under fixed decision rules. Across 28 model--scaffold configurations on 324 races, paired tests identify seven revision gains and two declines after multiple-testing correction. Yet every configuration has negative mean profit under capped-Kelly settlement. In a four-model comparison, the reusable-program workflow has higher mean betting profit and lower research fees, although both workflows lose on average. Further diagnostics reveal that mean probability bias reverses on selected bets and that profitable individual runs can depend on concentrated returns. These findings motivate evaluating predictive competence, adaptation, resource use, and decision value separately when assessing agents for repeated event forecasting.

Multi-session agents can switch between LLMs to balance performance and inference cost. Such switches require transferring a history for continuity, yet their effects on the recipient remain underexplored. Through controlled experiments with multi-session tasks, we uncover behavior transfer: recipients tend to adopt reasoning and action patterns from the models that generated their histories. This effect is most evident with raw-history transfer but is substantially reduced by summarization. Based on these findings, we propose Direction- and Authorship-aware Summarization of History (DASH) that preserves stronger-model behavior while minimizing weak-to-strong transfer via summarization. Experiments with repeated swaps show that DASH outperforms raw-history transfer and naive summarization baselines. These results suggest that effective multi-model orchestration requires considering not only which model to use, but also which behavioral patterns to carry forward.

Instruction-Conditioned Motion Control (ICMC) separates parameter specification, instruction generation, and code synthesis for language-driven robot control, making execution outcomes traceable to instructions and programs. We compare one-shot generation with ICMC under o1 and o4-mini on cube pick-and-place and letter-reshaping tasks for a UR5e arm in MuJoCo. We then train an open-weight instruction policy by GRPO through a frozen code generator on cube placement onto two- and five-cube letter layouts, averaging the rewards of five programs per instruction. The logged positive-reward rate rose from 31.6% to 35.3% (253/800 to 282/800) between the first and last five training steps. A log audit identifies positive binary labels associated with geometric-failure messages: at least 19 in that run, 18 in the dense-reward run, and 5 in the run with one program per instruction. In one case, all five rewards were 1.0 while the log reports a 0.9515 m miss against a 0.05 m tolerance; the verdict came from the program's own output stream. We distinguish logged reward rates from independently verified task success and report descriptive results for each configuration's single training trajectory. We introduce an independent evaluation protocol that checks task completion against fixed specifications, separating robot control from success assessment to support reproducible evaluation.

Large language model agents increasingly undertake long-horizon tasks in complex environments characterized by fragmented evidence, partially completed states, and dependencies across resources and artifacts. Existing agents may satisfy individual requirements while failing to maintain these relationships, producing locally correct but incomplete outcomes. These failures arise because task completion depends on relationships among environmental evidence, consequential decisions, and required effects. To address this completion gap, we propose Interlock, a framework for task synthesis that represents each task as a typed completion graph. Grounding edges connect public evidence to decisions, coupling hyperedges impose joint constraints across components, and realization edges connect decisions to all required downstream effects. Interlock compiles this graph into a resettable workspace, a public request, and an evaluation rubric. A source-coverage review checks whether the original requirements survive generation, while a public-input review checks whether the rubric is supported by the materials available to the solver. An agent-as-judge inspects execution artifacts and runs verification scripts, retaining trajectories judged to satisfy all mandatory requirements. To evaluate training utility, we fine-tune two Qwen3.6 backbones on their own accepted trajectories. Across the two backbones, training improves AutomationBench task pass rates by 4.00-4.50 percentage points, JobBench weighted scores by 3.20-6.64 points, and Harvey LAB criterion pass rates by 3.89-4.16 percentage points. These results demonstrate the training utility of the synthesized experience across external task environments.

We study proportional cake cutting under an equal-length constraint, where each of $n$ agents must receive a bundle of length exactly $1/n$ that is worth at least $1/n$ to that agent. Our main result determines the exact worst-case number of cuts needed to guarantee such an allocation, namely $2n-2$ for every $n$. This improves on the previously known quadratic upper bound. The proof combines the constrained necklace-splitting theorem with a recursive assignment argument based on Hall's theorem. The same bound extends to the stronger requirement of envy-freeness when $n$ is a prime power, and an $O(n^{1.525})$ upper bound holds for arbitrary $n$. We then ask whether such allocations can be computed. We first show that no deterministic protocol in the Robertson--Webb model terminates after finitely many queries on every instance and always returns an exact equal-length proportional allocation, even for two agents with identical valuations. For every $\varepsilon>0$, however, $O(n^2/\varepsilon)$ queries suffice to produce an allocation in which every agent receives a bundle of length exactly $1/n$ and value at least $1/n-\varepsilon$, again using at most $2n-2$ cuts. Finally, we augment the Robertson--Webb model with two-knife queries. We show that recursive balanced halving attains the optimal bound of $2n-2$ cuts when $n$ is a power of two. For arbitrary $n$, we give a procedure using $O(n\log n)$ cuts.

In this work, we reframe agentic trajectories as paths through a shared embedding space of actions and environmental observations. We show that successful and failed rollouts of the same task separate in this space, with simple per-task discriminators predicting held-out rollout outcomes at up to 0.95 AUROC across three agent benchmarks and three policy models. To exploit this signal across tasks, we introduce Precog-RM, a transformer-based model that meta-learns a representation in which outcome prediction can be performed in a few-shot setting. We show that Precog-RM generalizes to unseen tasks and models, and gives confident predictions of trajectory success long before termination. Deployed as an early stopping controller for Group Relative Policy Optimization (GRPO) on Tau2-Bench, Precog-RM cuts training FLOPs by up to 47.3\% while maintaining performance comparable to baseline GRPO.

As large language models become widely used in scientific review and manuscript revision, AI scores are increasingly serving as feedback for assessing paper quality and guiding edits. Yet whether a single AI score reliably reflects the reviewer's judgment, and whether revision gains based on that score are endorsed by other reviewers, remain understudied. Using 200 papers from ICLR 2025 and 2026 and approximately 14,000 AI reviews, we study score reliability, score-distribution estimation, and cross-model agreement on revision gains. Repeated reviews fluctuate even under identical conditions. Finer-grained scoring protocols reduce score variance but also systematically shift mean scores, while the gains assigned to manuscript revisions depend strongly on the reviewer.

Multi-agent reinforcement learning (MARL) provides a powerful framework for learning coordinated behaviors through interactions with the environment. Developing MARL policies requires balancing expressive modeling of complex and multimodal action distributions with efficient training and execution. Generative policies, particularly diffusionbased policies, can faithfully capture complex and multimodal behaviors, but costly iterative sampling hinders their scalability in online multi-agent settings. We propose an Online MARL framework via one-step Flow model (OMAF) that combines expressive generative policies with efficient one-step action generation. OMAF employs a Transformer-based flow policy to capture complex coordination behaviors, while its approximate path score surrogate provides a principled route to synchronized flow policy optimization. To enable stable and sampleefficient learning, we further develop a joint optimization scheme coupling softmax Q-value estimation with a joint flow policy objective for coordinated policy learning. By eliminating iterative sampling, OMAF dramatically reduces training overhead without sacrificing policy expressiveness. Extensive experiments across 10 standard tasks from MPE and MAMuJoCo show that OMAF consistently achieves superior performance, with up to 3.4x higher returns and 10.5x sample efficiency improvement compared with baseline methods. These results validate the effectiveness of OMAF as an expressive and computationally efficient one-step flow policy paradigm for online MARL.

Quasi-Newton (QN) methods have long been among the most effective methods for large-scale unconstrained convex optimization. Two obstacles have limited their use in deep learning: non-convexity and enormous parameter sizes. We introduce SoftServe, a family of QN methods designed to overcome these obstacles without line searches or ad hoc curvature corrections. SoftServe derives positivedefinite curvature estimates from the variational objective of Berglund et al. (2025), even in the presence of negative curvature. We develop diagonal and Kroneckerfactored variants that preserve positive definiteness by construction and scale to massive neural networks. Finally, SoftServe relies on the stable coupled Newton-Schulz iteration for the required matrix operations, replacing costly matrix decompositions with GPU-friendly matrix multiplications. SoftServe excels on problems that are severely ill-conditioned, including tasks such as recurrent networks, deep autoencoders, physics-informed neural networks, and a 136M-parameter physics-informed diffusion model, often achieving lower losses than established baselines including Adam, Muon, and SOAP.

Modern machine-learning models often contain strongly dependent or redundant features, making feature attribution difficult because shared predictive information can be distributed across correlated predictors. Existing methods such as SHAP, LIME, HSIC, MI/CMI, and SAGE may therefore produce unstable rankings under multicollinearity or near-duplicate predictors. We propose the Mutual Correlation Impact Ratio Method (MCIR-M), a dependence-aware global feature-importance approach that quantifies the unique predictive information contributed by each feature beyond a selected dependence neighbourhood. MCIR-M introduces the Mutual Correlation Impact Ratio (MCIR), which conditions each feature on strongly dependent neighbours and computes a normalized ratio of conditional to block-level information. The population score lies in [0,1] and equals zero under exact conditional redundancy. We also introduce a lightweight estimation procedure that computes MCIR using a fraction of the available data and evaluates agreement with full-data explanations. Across controlled synthetic redundancy experiments and the UCI HAR benchmark, MCIR shows dependence-aware ranking behaviour, with its clearest advantage under injected near-duplicate predictors. Comparisons with independent and conditional SHAP, SAGE, HSIC, MI-based scores, and CIR-family baselines are mixed across real-data criteria. Reduced explanation samples lower computational burden in the evaluated configurations, while agreement with full-data explanations is assessed separately through ranking, head-set, and faithfulness diagnostics. Overall, MCIR-M provides a practical dependence-aware diagnostic for global explanation under strong feature dependence.

When developers change one component of an agent, such as its controller, a learned model or its verifier, they usually judge the change by an aggregate task score. That score cannot tell whether improvement was attainable, which component lost value, or what the agent's own checks certify. We introduce a claim-specific verification audit for modular agents that plan, act, check and refine. Instead of scoring the agent, the audit scores the evidence: each conclusion is recorded with the evidence behind it, one of four verdicts (supported, unsupported, unresolved or not evaluated) and the boundary within which it holds. Three tools supply that evidence. Oracle policies measure attainable improvement under an explicitly stated action set, so that a low value can be traced to the evaluation rather than to the environment. Replacing one component at a time with a perfect counterpart locates lost value, with null results read as unresolved whenever a downstream component could mask them. A separate test asks whether the verifier's score identifies the quantity it is read as bounding. Applied to a constrained portfolio-allocation agent in a synthetic market with known hidden regimes, the audit shows that the value of perfect regime information depends on the action set used to measure it, that the scenario generator discards most of the regime signal while better local fidelity does not improve decisions, and that the runtime verifier can be bypassed with no visible change in outcomes. The contribution is the protocol and the evidential distinctions it enforces; the empirical findings are specific to the agent and environment studied.

This paper proposes a novel alternative to existing sim-to-real methods for training control policies with simulated experiences. Unlike prior methods that typically rely on domain randomization over a fixed finite set of parameters, the proposed approach injects state-dependent perturbations into the input joint torque during forward simulation. These perturbations are designed to simulate a broader spectrum of reality gaps than standard parameter randomization without requiring additional training. By using neural networks as flexible perturbation generators, the proposed method can represent complex, state-dependent uncertainties, such as nonlinear actuator dynamics and contact compliance, that parametric randomization cannot capture. Experimental results demonstrate that the proposed approach enables humanoid locomotion policies to achieve superior robustness against complex, unseen reality gaps in both simulation and real-world deployment.

Modern clinical practice increasingly depends on reasoning over heterogeneous, evolving, and incomplete patient data. Although recent advances in multimodal foundation models have improved performance on various clinical tasks, most existing models remain static, opaque, and poorly aligned with real-world clinical workflows. We present Cerebra, an interactive multi-agent AI team that coordinates specialized agents for EHR, clinical notes, and medical imaging analysis. These outputs are synthesized into a clinician-facing dashboard that combines visual analytics with a conversational interface, enabling clinicians to interrogate predictions and contextualize risk at the point of care. Cerebra supports privacy-preserving deployment by operating on structured representations and remains robust when modalities are incomplete. We evaluated Cerebra using a massive multi-institutional dataset spanning 3 million patients from four independent healthcare systems. Cerebra consistently outperformed both state-of-the-art single-modality models and large multimodal language model baselines. In dementia risk prediction, it achieved AUROCs up to 0.80, compared with 0.74 for the strongest single-modality model and 0.68 for language model baselines. For dementia diagnosis, it achieved an AUROC of 0.86, and for survival prediction, a C-index of 0.81. In a reader study with experienced physicians, Cerebra significantly improved expert performance, increasing accuracy by 17.5 percentage points in prospective dementia risk estimation. These results demonstrate Cerebra's potential for interpretable, robust decision support in clinical care.