This paper tackles endogenous nonstationary stochastic bandits where actions drive an unobserved latent linear system and rewards are bilinear in the action and latent state. Prior work achieved only $\widetilde{\mathcal{O}}(T^{2/3})$ regret via explore-then-commit (ETC) because the infinite-memory reward process couples learning and planning. The authors show that under stable dynamics the memory can be truncated geometrically, reduce the problem to a block-level linear bandit via cyclic approximation, and propose an optimistic block-UCB algorithm (Block-OFUL) that achieves $\widetilde{\mathcal{O}}(\sqrt{T})$ regret. The result is theoretically appealing but leans heavily on an exact block-maximization oracle and on knowing the dynamical stability constant $\rho$.

Long-horizon probabilistic forecasting of dynamical systems is computationally demanding because traditional flow matching requires integrating along an auxiliary generative time axis. This paper proposes Variational Streaming Flow (VSF), which augments a physical-time velocity field with a single latent variable sampled once per rollout, enabling efficient multimodal forecasting with one network evaluation per step. VSF improves long-horizon accuracy and distributional fidelity on chaotic and stochastic systems and can plug into existing JEPA world models to boost planning success.

RPTune addresses product search for small merchants whose catalogs fit inside long-context LLMs. Rather than relying on retrieval pipelines, the authors show that feeding the full catalog works only when items are learned to be pruned, ranked, and positioned with downstream LLM feedback, after which the LLM itself is post-trained on these curated contexts using purely synthetic supervision. The result is a fully automated pipeline that achieves large accuracy gains and latency reductions across 7 merchants and 9 model families.

STEER attacks the high inference cost of relational foundation models by shrinking their graph-sampled context using schema semantics instead of random dropping. The approach prompts an LLM once per task to rank foreign-key edges into relevance tiers, then probabilistically steers neighborhood traversal during sampling. Evaluated on RelBench across three state-of-the-art RFMs, it cuts average context size by about 40% while maintaining or slightly improving accuracy, offering a practical, model-agnostic optimization.

Test-time reinforcement learning (TTRL) lets language models adapt on unlabeled problems using their own samples as supervision, but a diffuse initial policy wastes the limited adaptation budget concentrating probability mass instead of converting existing capability into reliable output. This paper proposes entry-state sharpening: use data-free training before TTRL to place the checkpoint in a concentrated state that subsequent label-free adaptation can exploit more efficiently. The core insight is that checkpoint preparation should be treated as a state-control problem—where entry entropy is a label-free readout and reachable capability is the constraint—rather than as a choice of upstream training recipe.

Biological reasoning models fuse large language models with foundation-model representations and biological text to predict properties of DNA, proteins, and cells. This paper asks whether high benchmark accuracy actually reflects use of these biological inputs, or merely exploits overlapping text annotations. Through perturbation tests, evidence conflicts, linear probes, and reasoning-trace analysis across six models, the authors find that predictive representations are often ignored and that post-training gains can mask persistent over-reliance on text. The findings argue that evaluating input-specific reasoning must become standard alongside predictive accuracy.

Continuous diffusion language models have historically lacked two key features for practical deployment—variable-length generation and KV caching—while also trailing autoregressive and discrete diffusion in quality. This paper introduces Clock Diffusion, a framework that reparameterizes global diffusion time into position-dependent local clocks to enable semi-autoregressive denoising over token embeddings. Together with vectorized training masks and Cache Grab samplers, ClockDLMs close much of the perplexity gap on OpenWebText and unlock efficient inference, though downstream gains remain uneven across tasks.

Quantized LLMs are increasingly deployed on edge devices for efficiency, but aggressive quantization collapses safety alignment and leaves small models highly vulnerable to jailbreaks. MOMAT proposes a hardware-aware defense that splits safety knowledge into semantic atlases and performs fast similarity search via a Compute-in-Memory (CiM) engine, paired with a lightweight Mixture-of-Experts detector. By co-designing structured retrieval with low-power acceleration, the work argues that strong guardrails can be restored on resource-constrained hardware without sacrificing benign utility.

In-context learning (ICL) lets LLMs adapt to new tasks from demonstrations, but reprocessing all examples for every query is costly and prior compression methods fail on complex, input-dependent tasks. This paper introduces Task Operator (TO), a training-free method that extracts per-head affine transformations — scaling weights and bias vectors — from the ICL forward pass and replays them during zero-shot inference by updating attention output projections. By treating the ICL effect as a dynamic, state-dependent modification rather than a fixed activation vector, TO substantially narrows the gap between zero-shot and few-shot performance while revealing sparse, task-specific circuits.

The paper tackles the bottleneck of expensive Monte Carlo simulation when designing algorithms for complex network dynamics, such as influence maximization and epidemic control. It proposes a learned, action-conditioned Network World Model that predicts how network interventions unfold over time, and wraps it in an LLM-based coding agent that searches over executable algorithms. The framework reportedly outperforms strong baselines across eight tasks and five diffusion models while rolling out up to 14.5 times faster than direct simulation.

This paper identifies empty commitments: promises that LLM agents make about future actions their runtime cannot actually execute. Unlike broken promises, these are structurally impossible from the moment of speaking because the agent lacks the required tools, scheduling, memory, or delegation affordances. The authors define a formal taxonomy of failure types and propose a measurement protocol, though no empirical results are presented.

Multi-agent LLM systems are usually judged by end-task accuracy, which conflates genuine information sharing with extra reasoning or fortunate architecture. This paper introduces Independent–Communicate–Revise (ICR), a controlled audit that freezes each agent’s initial trajectory and measures answer revision conditional on both agents’ initial correctness. By separating correction from preservation and comparing against a no-message control, the work shows that aggregate accuracy can hide large, policy-dependent trade-offs between fixing errors and corrupting correct answers.

Voting over multiple LLM responses is a standard test-time scaling primitive, but discovering a correct answer does not guarantee it wins the final plurality under a fixed call budget. This paper formalizes the discovery-to-decision gap through the realized vote state and remaining budget, deriving sharp reachability thresholds, exact finite-horizon endpoint probabilities, a gold-free exact locking certificate, and demonstrating that representation diversity can dramatically improve plurality accuracy without changing single-call correctness.

This paper tackles the problem that LLM-generated economic policy can sound plausible yet be dynamically inconsistent. It grounds an instruction-tuned language model inside six DSGE simulators via a common RL interface, using PPO and GRPO to learn multi-turn policy actions with delayed rewards. The core idea is to replace linguistic plausibility with simulated economic consequences, testing credit assignment, semantic-shift conditioning, and cross-simulator transfer. Results matter for any setting where language agents must make sequential decisions with long-horizon structural feedback.

EEG foundation models are typically pretrained on fixed channel layouts, so they struggle when electrode montages differ at test time. This paper proposes CortexBridge, a lightweight adapter that routes arbitrary scalp montages into a fixed cortical atlas space using electrode coordinates and sparse attention. By injecting this anatomically grounded representation into frozen backbones, the authors show consistent accuracy gains across three models, five datasets, and three BCI paradigms.

Inverse design of microwave absorbers traditionally demands rare cross-disciplinary expertise and lengthy simulation cycles. AbsorbEvo tackles this with an autonomous agentic framework that translates natural-language performance goals into candidate designs, screens them with a low-cost physics prior, and verifies select candidates with full-wave simulations. The core idea is to marry large language model reasoning with electromagnetic physics feedback so that expensive simulations are spent only on promising candidates. If robustly validated, such a pipeline could lower barriers to designing broadband, angle-tolerant absorbers.

Decision models like Jev return probability distributions to drive routing, abstention, and human review, yet average calibration cannot distinguish whether uncertainty stems from chance or from missing knowledge. The authors audit this distinction in a black-box decision model through roughly 575,000 API calls across paired interventions that vary supplied information while holding items fixed, plus targeted follow-up questions about the case and the model’s own familiarity. Their core finding is that confidence tracks correctness on familiar material but fails at knowledge boundaries—assigning up to $p_{\max}=0.80$ to salient options with no basis and growing overconfident past an observed temporal boundary—while apparent self-knowledge largely evaporates once surface cues are controlled. The work matters because it provides a practical, behavioral checklist for black-box knowledge audits and shows that querying case properties directly can be more reliable than reading a single output distribution.

A long-term assistant must recall memories whose cues are associatively related to, yet not semantically similar to, the current user turn. Madeleine reframes this involuntary recall as a learnable relevance—the pointwise mutual information of memories under simulated life trajectories—and distills it into a query-side residual adapter, $s_\theta(q,m)=\cos(E(q),E(m))+\cos(E_\theta(q),E(m))$. The system is trained offline on synthetic (trigger, cue) pairs written by an LLM life simulator, and at runtime it plugs into existing vector memories with zero LLM calls, cutting answer context by roughly $20\times$ while setting a new state of the art on LoCoMo-Plus.

Holyoak and Monti tackle the question of AI consciousness by developing a causal framework for evidential analogy. Their central idea is that behavioral similarity to humans carries far less weight than shared causal mechanisms plausibly generating subjective experience. The paper argues that animals inherit strong analogical support from evolutionary and neurobiological homology, whereas contemporary AI—despite impressive performance—lacks established causal correspondences with human consciousness. This makes the work a careful attempt to redirect a debate often mired in hype toward principled, mechanism-first reasoning.

Many Bayesian inference problems involve implicit priors known only through samples, such as generative model outputs or historical ensembles. This paper proposes performing posterior sampling in the Gaussian source space of an improved MeanFlow (iMF) transport map, using parallel tempering with pCN or hybrid split-HMC updates. Its central theoretical advance is proving Wasserstein stability bounds for the implemented few-step posterior in terms of the joint population training loss, removing the need for vanishing ODE discretization error.