Papers

Retrieval-augmented language models are expected to answer from the retrieved evidence, but in practice they often keep answering when that evidence is missing. We trace this behavior to the training signal: answer-focused fine-tuning assigns no target to unsupported contexts, so it cannot distinguish a reader that abstains from one that guesses, and unsupported answering stays near 100% even as supported accuracy improves. We introduce Regime Boundary Alignment (RBA), which trains a single reader on matched variants of the same question and gold answer. The reader is trained to produce the gold answer when the context supports it, including when conflicting evidence is also present, and to abstain when the correct support is removed; inference is ordinary decoding, with no verifier, threshold, or regime label. On three multi-hop QA datasets across three seeds, RBA reduces the unsupported-answer rate by more than sixty percentage points relative to conflict-focused training while matching its supported accuracy. On a held-out TriviaQA retrieval-miss slice, the same reader reduces unsupported answering from 100% to below 1% while also improving supported accuracy. These results indicate that evidence-gated answering must be learned on both sides of the support boundary.

Large-scale pervasive sensing increasingly relies on high-resolution satellite imagery, yet task-specific onboard vision is constrained by costly annotation and limited computation, memory, energy, and communication resources. Existing approaches largely rely on either data-hungry supervised learning or large vision-language foundation models, limiting efficient adaptation and deployment under these constraints. We present SatLabel, a resource-aware learning framework that transforms limited satellite labels into progressively refined onboard models through adaptive sample acquisition and semi-supervised model adaptation. Rather than repeatedly training on uniformly sampled labels, SatLabel closes the loop between model uncertainty, class imbalance, and pseudo-label quality to selectively acquire informative samples while exploiting abundant unlabeled imagery. This enables a compact student to adapt to target sensing domains with reduced annotation and inference costs. We further introduce an optional Mixture-of-Experts (MoE) student with graph-based feature refinement to enhance representation capacity while retaining a lightweight footprint. We evaluate SatLabel on 11 remote-sensing datasets spanning core, extended, and unseen domains against RemoteCLIP zero-shot inference. SatLabel improves Macro-F1 on most core and extended datasets while maintaining strong cross-dataset transfer to unseen domains. More importantly, the Balanced student contains only 11.2 M parameters and occupies approximately 42.8 MB, compared with 151.3M parameters and 577 MB for RemoteCLIP, while requiring 3.65 versus 5.89 GFLOPs. Across four efficiency benchmarks, it achieves approximately 2x higher GPU-forward throughput and reduces energy per image on datasets.

Behavioral tests measure how a language model reads evidence. We ask whether those measurements help choose a recommendation interface. We evaluate six small instruction-tuned checkpoints across four recommendation domains with chronological evaluation and 3,426 evaluation users. Each request ranks eight candidates. A baseline selector chooses among history-only prompting, prompting with collaborative evidence, and score fusion. It uses observable features and six stability prompts that vary wording and candidate order. An augmented selector adds features from six evidence-reading prompts that ask the model to compare support counts. An interface chosen once on development (validation) data for each domain and checkpoint scores 0.5524 NDCG@5, compared with 0.5447 for the baseline selector and 0.5428 for the augmented selector. Adding the diagnostic features changes NDCG@5 by -0.0019 (95% interval [-0.0046, 0.0004]). The interval includes zero, and its upper bound is below the analysis plan's 0.005 improvement target. Matching the selectors' hyperparameters also leaves the interval upper bound below that target. Evidence from retrieved similar users improves prompting by 0.0999 NDCG@5 over a control using randomly selected users matched for activity. The evidence-reading tests also reveal answer-position and tie-response biases. These results concern the tested selectors and candidate sets. They illustrate why diagnostic measurements should be evaluated by whether they improve recommendation choices beyond existing features and a fixed interface.

Industrial standards often encode the same engineering concept through incompatible hierarchies, identifiers, roles, and structural constraints, so the nearest lexical or embedding match can still be technically inadmissible. This article presents CRASM, a deterministic constraint- and role-aware semantic mapping method, and CRASM-Gate, its selectively model-assisted extension. The framework separates standard-specific canonicalization, bounded retrieval, deterministic rules, destination-versus-origin role interpretation, semantic and structural ranking, ambiguity refusal, and target validation. CRASM-Gate adds a confidence/disagreement gate that may invoke a candidate-constrained large language model, while final authority remains with deterministic validation. A controlled artifact covers six directed industrial-standard pairs, three difficulty levels, and ten configurations, yielding 14,400 sample-level decisions. With a fixed local model endpoint, CRASM-Gate reaches mean F1 0.9938 and an implemented structural-validity rate of 1.0000; deterministic CRASM reaches 0.9931 without generative-model calls; and the model-only baseline reaches 0.5347. Relative to the model-only baseline, CRASM reduces top-1 errors from 670 to 10 while exhibiting 0.0688 s/sample rather than 24.5263 s/sample observed latency. CRASM-Gate improves CRASM by one additional correct decision out of 1,440, with observed latency increasing to 15.7666 s/sample. The results support a deterministic-first interoperability architecture in which model assistance is optional, measurable, candidate-bounded, and unable to bypass structural validation.

SEC 10-K filings contain substantial financial information that is not consistently captured in structured datasets, creating a missing-data problem affecting over 70% of firms and half of total market capitalization. This can disproportionately bias quantitative analysis against smaller firms, which may be excluded due to limited available data. Traditional financial extraction methods such as Regular Expressions (Regex) and BERT, have been widely used. However, they are highly brittle when parsing complex SEC 10-K filings, which leads to data that is existent in the files being lost since these methods do not consider that a data attribute could be located in a different section or a footnote. This study evaluates several Large Language Models (LLMs), including Llama-3 8B, Qwen-2.5 14B, and Llama-3.3 70B, to figure out individual model strengths and weaknesses when extracting specific attributes from SEC 10-K text. The extraction quality was evaluated across four financial variables of varying structural complexity: Cash and Cash Equivalents (tabular), Short-Term Debt (hybrid), Credit Facilities (narrative), and Research and Development (hybrid). Results show that while smaller models like Llama-3 8B experience performance degradation under complex negative prompting, aligning parameter scale with document complexity yields high zero-shot accuracy. Qwen-2.5 14B excels as a tabular specialist with an 83.33% F1 score on Cash, whereas Llama-3.3 70B effectively navigates dense narrative footnotes, achieving a 76.92% F1 score on R&D. This scalable framework addresses critical information gaps in quantitative finance datasets and eliminates missing-data bias through a more thorough analysis of the SEC 10-K files.

Modern bioacoustic foundation models like Perch and BirdNET can identify species with high discriminative accuracy, yet their confidence scores are often uncalibrated and difficult to interpret as probabilities of real-world occurrence. This limits their use for ecological inference beyond threshold-based detection. We leverage a global annotated acoustic dataset (WABAD) to produce calibration priors for an acoustic model, optionally incorporating species-level information. We introduce new methods of fusing the acoustic predictions with geopriors, which empirically improves calibration while preserving discrimination. Together, these results suggest a path to simpler and more reliable acoustic monitoring for broad biodiversity.

Sampling based consistency is widely used for hallucination detection, yet aggregate performance can conceal systematic differences in which errors are detectable. This work studies that heterogeneity across four language models and three factual question answering datasets. Partitioning hallucinations by answer agreement reveals high agreement (Ghost) and low agreement (Flickering) regimes with an apparent detectability gap of $0.35$ to $0.46$ AUC. Because the statistics used to define the regimes and measure this gap are strongly coupled ($|\rho|\approx0.94$ to $1.00$), the raw result is treated as a property of agreement based detection rather than independent evidence. After freezing regime assignments, lexical and semantic response dispersion preserve the asymmetry, with bootstrap $95\%$ intervals excluding zero in all $12$ model and dataset settings. A stricter test using individual diffusion trajectories and no cross seed information preserves the asymmetry across all three LLaDA datasets ($p<0.005$) and directionally across all three Dream datasets, with one reaching significance. The hard regime varies substantially in prevalence across models ($16\%$ to $77\%$), and matched prompts frequently change regimes between models. These findings show that aggregate detection metrics conceal persistent, model dependent heterogeneity in language model failures and motivate regime conditioned evaluation.

This research describes the adaptation of Large Language Models (LLMs) for economic monitoring in the public sector to automatically determine whether an article discusses Economic Policy Uncertanity (EPU) and to identify its specific type. Previous studies either rely on keywords, which often result in a high count of false positives, or use machine learning approaches that require a large number of quality human labeled data that is costly and time consuming to acquire. In this study, we propose approaches based on weak supervision techniques, using generative LLMs to create synthetic labels through prompting, making the approach both cost-effective and scalable. Additionally, we propose methods for for multi-label and hierarchical classification of articles related to EPU.

Optimizing deployed AI systems increasingly amounts to editing prompts, skills, harnesses, and code rather than model weights. Existing approaches commonly optimize these artifacts through propose-evaluate-select procedures, where candidate configurations are evaluated and only those meeting an acceptance criterion are selected. Yet our analysis shows that discarded candidates often contain information critical for subsequent optimization. Discarding them causes later proposals to revisit the same failure modes. We introduce Mara Chain, a refinement procedure that turns rejected candidates into stepping stones. Rather than discarding a rejected candidate, Mara Chain retains and iteratively refines it using evidence accumulated across preceding attempts. The procedure limits each refinement chain to a fixed depth and applies Pareto-filtered Top-N selection to bound the candidate pool. Across AppWorld skill optimization, TerminalBench 2.1 harness optimization, and MuSiQue retrieval-pipeline optimization, Mara Chain delivers greater task-performance gains with fewer rollouts. It outperforms GEPA, ACE, and SkillOpt-Lite by up to 20.5% in relative performance on AppWorld, reaching the target score with 65.5% fewer rollouts than GEPA. It improves the pass rate by 20.2 and 22.5 percentage points over AHE and Meta-Harness on TerminalBench 2.1, respectively, and improves MuSiQue test nDCG@10 and Recall@10 by 0.104 and 0.131 over a hand-written retrieval pipeline.

In the field of Machine Learning, many papers contain empirical results supporting claimed statements or illustrating the performance of a proposed method. However, most practitioners know that (1) results are generally hard to reproduce, and increasingly so, (2) code is not often available to do so, and (3) it hinders the development of research. In this position paper, we analyze and quantify these issues, and make concrete proposals to improve result checkability, if not reproducibility. Code and supporting materials are available at https://github.com/giddyyupp/position-enforce-verifiability.

Pooled statistics of Transformer weights obscure how magnitude is distributed across functional channels, while individual weights are too numerous to compare directly. We study the mesoscopic level between them: row and column scale fields, the median-centred log-RMS profiles of a weight matrix over its channels, which together with a global scale and a full balanced core represent the matrix exactly. Across public Pythia checkpoints at four sizes and controlled runs from three initialization families, balancing reveals similar measured core magnitude profiles. A mixture bridge, with its form fixed before the analysis and its coefficients fitted, predicts the pooled-shape departure from field width on held-out runs and data arms of the controlled grid. The indexed fields retain further structure: they align across projections that share a functional channel, and query/key profiles follow reassigned RoPE frequencies rather than fixed matrix coordinates. Training trajectories show early field formation followed by component-dependent broadening or recession. Extending the channel-based analysis to AdamW's second moment reveals related functional organization in its log-space row and column factors. Finally, edits of a frozen checkpoint separate reciprocal scale balance, which preserves the forward computation, from relative channel gain: flattening the gain increases in-distribution loss while preserving matrix norms and the balanced core. Row and column scale fields thus connect pooled magnitude statistics to channel organization and provide coordinates for tracking and testing trained weight structure.

On-board compression of synthetic aperture radar (SAR) phase history is bandwidth-critical, and block-adaptive quantization (BAQ) remains the operational standard. We test whether a small convolutional autoencoder, with its encoder on the sensor, can compete with BAQ on complex phase-history patches from the AFRL GOTCHA collection. Every method is charged for all transmitted bits, rates are reported in bits per complex sample (b/cs), and detection is scored by one-to-one matching of CA-CFAR detections. The autoencoder (28,656 encoder parameters) loses at every rate. At 16 b/cs it reaches -2.87 dB NMSE, against -35.5 dB for 8-bit BAQ with $\pm 3\sigma$ clipping and -41.0 dB with a tuned clipping range. It also loses to a $16 \times 16$ block Karhunen-Loève transform (KLT), a local linear coder with a tenth of its encoder cost (-5.39 dB). Running the network in a companded Fourier domain helps, but its detection F1 remains bounded at 33%. The evidence points to this model, its normalization, and its objective, not to a fundamental limit of learned coding. Per patch, the data have modest lag-1 coherence ($|\rho| \approx 0.3$) and patch-specific spectral concentration. Two findings concern evaluation itself. First, 97% of CFAR crossings on raw $64 \times 64$ patches are border artifacts of the zero-padded detector. Second, on interior cells BAQ's clipping range decides detection: 8-bit BAQ keeps 69% F1 with tuned clipping but 17% at $\pm 3\sigma$, and at 8 b/cs or less adaptive FFT thresholding preserves more detections than BAQ. We close with an evaluation protocol for learned radar compression.

We present a constructive atlas of finite simple groups with proofs of their orders, simplicity, and structural properties. The eight completed families are cyclic groups of prime order, alternating groups, the classical series $A_r(q)$, $B_r(q)$, $C_r(q)$, $D_r(q)$, and the exceptional series $G_2(q)$ and the small Ree groups $ {}^2G_2(3^{2m+1})$, $m\geq1$. The fifteen sporadic entries are $M_{11}$, $M_{12}$, $M_{22}$, $M_{23}$, $M_{24}$, $\mathrm{Co}_1$, $\mathrm{Co}_2$, $\mathrm{Co}_3$, $\mathrm{McL}$, $\mathrm{HS}$, $\mathrm{Suz}$, $J_2$, and $\mathrm{Fi}_{22}$, $\mathrm{Fi}_{23}$, $\mathrm{Fi}_{24}'$. The simple parameter ranges and exceptional cases are stated explicitly. The models arise from codes, lattices, forms, algebras, and finite geometries, including the split octonions and the Conway–Parker algebra. They retain natural actions, stabilizers, central quotients, and comparison maps for subsequent group theory. Several classical comparison isomorphisms relate the models, while involution-class counts distinguish the equal-order orthogonal and symplectic families in odd characteristic and rank at least three. Drawing on classical sources and companion mathematical work, the project develops the construction side of finite simple group theory, not the exhaustiveness proof of the classification. The completed models and stated proofs are formalized in Lean for verification and reuse.

Macroeconomic productivity metrics, such as Total Factor Productivity, register technological breakthroughs with multi-year reporting lags due to administrative survey intervals and national accounting conventions. This paper introduces Hyperspherical Semantic Trajectory Analysis (HSTA), an unsupervised quantitative methodology that tracks technology diffusion directly from unstructured scientific and commercial text streams. We analyze 30,000 filtered document records spanning academic preprints from arXiv and patent application records from the USPTO. By projecting high-dimensional Transformer sentence embeddings onto unit hyperspheres using Spherical K-Means clustering across eight primary sub-topics and UMAP manifold reductions, HSTA formalizes two quantitative metrics: (1) Semantic Centroid Vector Drift, which tracks vocabulary shifts between temporal sub-corpora to identify structural paradigm transformations; and (2) Commercialization Offset, which evaluates cross-corpus peak density alignments between scientific discovery and intellectual property filings. Linking quarterly topic volume velocity with physical hardware metrics from the Epoch AI database, Vector Autoregressive F-tests demonstrate that quarterly paper volume velocity alone does not Granger-cause frontier compute allocation surges at conventional statistical significance levels, highlighting the necessity of conditioning textual signals on physical capital constraints. Empirical results reveal that sub-topics covering Large Language Models (with a drift metric of 0.332) and Artificial Intelligence Systems (with a drift metric of 0.234) undergo the highest rate of semantic evolution, offering an objective, real-time mechanism to complement traditional economic statistics.

Pair arithmetic omits the renormalization stage performed at the end of each operation of multi-component multiple-precision arithmetic, reducing the operation count and, by eliminating conditional branches, easing SIMD vectorization. Renormalization cannot be omitted entirely, however, because iterative solvers may then fail to converge. We propose RenormBF-pair, a branch-free fixed-trip-count renormalizer parameterized by the word count \(K\) and the input length \(n\): a VecSum sweep, a tail fold, and \(r\) rounds of a FastTwoSum chain, costing \(6(n-1)+(n-K)+3r(K-1)\) flops. Over \(200{,}000\) trials per condition, the smallest round count producing no non-overlap violation was \(r=1\) for \(K \leq 3\) and \(r=2\) for \(K=4\), whereas the same cost spent on a VecSum\(K\)-style TwoSum chain fails for \(K=4\). We delimit with explicit counterexamples both the input condition under which the sum relation holds and the fact that the scheme does not, in general, guarantee a correctly rounded lowest component. Integrating it into CG and BiCGStab over pair arithmetic in binary64 and binary32, we sweep \(240\) paired runs including real matrices screened from SuiteSparse. The proposed scheme and VecSum\(K\) returned bitwise identical words wherever both succeeded, so they are indistinguishable for CG in binary64; differences appear only where VecSum\(K\) breaks, namely binary32 and BiCGStab. There the \(22\)–\(16\) win–loss record is not significant (sign test, \(p=0.42\)); the clear bias is structural, non-overlap violations dropping from \(66\) rows to \(37\). The cost is \(+3.4\%\) for the whole CG solver.

Temporal dynamics in learning behavior can be revealed through period segmentation in Transition Network Analysis (TNA). Cristea et al. demonstrated that segmenting courses into halves and quarters reveals how learning strategies evolve and relate to academic performance. Building on this approach, we investigate whether Topological Data Analysis (TDA), specifically connected components ($\beta_0$) change points from Zigzag Persistent Homology, can provide data-driven period boundaries that identify intervention windows. Analyzing 22 courses from the Open University Learning Analytics Dataset, we find that $\beta_0$-based segmentation captures greater between-period variation than time-based segmentation (median variance ratio (VR) = 4.10$\times$; 21/22 courses show VR $>$ 1.1). Permutation tests confirmed significance ($p < 0.05$) in 18% of individual courses, with 73% showing positive improvement over random breakpoints. Only one course showed better performance with time-based segmentation. However, analysis of academic outcomes reveals a key insight: final-period behavior shows lower correlation with outcomes in $\beta_0$-based segmentation than in time-based segmentation, reflecting a marked behavioral collapse where engaged learners rapidly disengage. We interpret this as evidence that final-period behavior reflects rather than causes outcomes: students who will pass maintain engagement, while those who will fail disengage. This reframes the value of $\beta_0$: rather than improving prediction, change points identify intervention windows. These are periods where behavioral structure shifts and targeted support may be most effective.

Powered by expert guidance, agents can operate in interactive environments; however, it is unclear whether they can learn autonomously from their own experience. To evaluate such self-improvement methods, we introduce GameBoyWorlds, a testbed for agentic self-improvement in video games. GameBoyWorlds-Execution evaluates task execution on a collection of 5 distinct game series. Agents are allowed access to dedicated training games but are provided no demonstrations, documentation, or rewards. Agents must ground themselves in the environment through self-directed exploration and by inferring actionable knowledge from their own experience. At test time, agents must complete short-horizon tasks that evaluate their ability to navigate, interact, and engage with game-specific mechanics in unseen games. Out-of-the-box frontier models complete fewer than 50% of the 500 tasks due to failures in multimodal grounding, establishing that self-improvement methods have room to push performance. We demonstrate that contemporary approaches to self-improvement are lacking, with world modelling and autonomous skill discovery failing, and a novel strategy that uses curiosity-based exploration to write guides achieving only partial success. GameBoyWorlds-Playthrough tests end-to-end game completion in two fan-made Pokémon games. We show that while frontier models have been pre-exposed to official releases such as Pokémon Red, they lack essential information on the games in our testbed. Instead of relying on their parametric knowledge to succeed, agents must learn from their own experience and autonomously improve over the course of the playthrough. We show that a sophisticated agentic pipeline with multimodal memory and hierarchical subgoals fails to reach even the first major milestone in both games, establishing GameBoyWorlds as an ambitious target for self-improving agents.

We present a framework for evaluating and improving a large-scale, multi-agent shopping assistant in production, and report lessons from its use. Offline evaluation of such a system faces three obstacles. (i) A logged conversation cannot be replayed against a modified system, because a different response changes every turn that follows. (ii) The unchanged system itself varies from run to run. Its LLM components are stochastic, and in product search the available products, their prices, and the customer's personalization signals change. (iii) Aggregate quality scores combine distinct behaviors, so they show that quality has changed but not which behavior caused the change. Our framework addresses each obstacle in turn. For a reported behavior, an Evaluation Harness generates targeted assertions and a fixed cohort of customer scenarios. It then reproduces the behavior in a local instance of the assistant through grounded user simulation. Instead of replaying the log, the simulator writes new customer turns conditioned on the recorded messages and context. Repeated runs of the unchanged system form a stored baseline. An Improvement Orchestrator turns the assertion results into hypotheses, implements each as an isolated modification, and compares it with the baseline using paired percentile bootstrap intervals over scenario-level differences. When an investigation ends, the harness may propose revisions to future evaluations, subject to human approval and without altering past decisions. We report production investigations with this framework. Assertion profiles showed which positions of a product carousel a failure affected, and repeated runs distinguished a real improvement from run-to-run fluctuation. Audits of the evaluation itself found a judge that lacked the evidence it needed and a model setting that was configured but not applied.

AI agents are stateless across sessions by default and therefore operationally amnesic: each session begins with little durable knowledge of prior failures, repairs, preferences, or successful strategies. As a result, agents repeat the same mistakes and discard hard-won experience. The dominant fix is bespoke memory—retrieval, persistence, and learning logic hand-wired into one agent and bound to one storage engine. This creates a fragmented landscape where memory cannot be swapped, shared, isolated, or reasoned about independently of the agent that owns it. We argue that this is a middleware problem: agent memory deserves a first-class, pluggable layer, just as data access, messaging, and persistence each became middleware concerns. We develop this vision through six systems challenges: two-sided pluggability, host-native interposition, multi-tenant isolation, write-path consistency, federated sharing with provenance, and lifecycle governance. We present ALTK-Evolve, a reference implementation of memory middleware for self-improving agents, and use it to motivate a broader research agenda for future memory middleware.

A square is a word $xx$, where $x$ is nonempty. We show that a circular word of length $n$ contains at most $\lfloor 3n/2 \rfloor$ distinct squares of length at most $n$. The proof combines known results relating squares to circuits in Rauzy graphs. The coefficient $3/2$ agrees with the known lower bound.

Deploying AI systems requires deciding when to delegate tasks and when humans should intervene to monitor and mitigate risk induced by AI operations. These decisions are challenging when failures cluster: a hallucination or harmful output can trigger further errors, creating periods of elevated risk. We introduce a continuous-time framework for learning adaptive human oversight under such turbulent AI risk. Existing oversight and delegation formulations condition on history but do not model incident clustering, or its suppression by supervision effort, jointly with the delegation decision and this study fixes this gap. The self-exciting dynamics capture how risk events increase the likelihood of subsequent events, making their timing and history central to decision-making. We formulate a stochastic control problem combining human actions, monitoring effort, and switching between human-AI-assisted operation and full AI delegation, balancing operational rewards against oversight costs, and cascading AI-failures and induced uncertainty. Human participation is an endogenous component of risk management: the policy determines both when oversight is needed and how much effort to allocate. We study a relaxed switching formulation and propose Hawkes-PPO, a policy-gradient method that uses a bank of exponential filters of observed incident times. In a synthetic environment it attains a higher risk-adjusted objective than either fixed regime and approaches an approximate full-information oracle. We illustrate our results with numerical simulations by examining how cascade risks influence intervention and delegation, connecting reinforcement learning with adaptive human oversight of AI systems. In particular, we illustrate the benefit of our switching strategy and Hawkes-PPO algorithm to monitor the project efficiently along time, reducing turbulent risks occurrences and costs.

Voice agents depend on accurate automatic speech recognition (ASR) to act on what callers say, yet ASR is evaluated on read, English-centric speech with word error rate (WER), which penalizes surface rather than semantic differences. We introduce mu-bench, a dataset of 4,270 caller utterances from 250 phone calls to an AI banking agent in English, Spanish, Turkish, Vietnamese, and Mandarin, centered on form-field inputs such as names, email addresses, and confirmation codes. We release Utterance Error Rate (UER), an LLM judge of whether a transcript preserves meaning, calibrated against human raters, together with an LLM normalizer that makes WER comparable across providers' output formats. On 1,847 human-rated transcripts, UER agrees with annotators at $\kappa$ = 0.78, versus 0.53 for exact-match WER on normalized text. We rank six commercial providers on a public leaderboard; the best reaches 11.9% UER, and Mandarin is hardest for all six.

Empowered by advances in Language Model agents, systems have made substantial strides in code generation and understanding. However, these approaches often rely on read access to the relevant code, an assumption which does not hold when dealing with external APIs. In this work, we introduce the PAU (Python API Understanding) benchmark, where we provide models with black-box, API-level access to code snippets. Models must query the API with exploratory inputs and draw insights from the resulting outputs, with the goal of describing the snippet's true functionality. By treating the code snippets as external tools that must be understood via interaction alone, PAU studies the more general problem of unsupervised tool understanding, specifically for tools implemented as Python methods. Despite recent progress in coding agents, even frontier models struggle to achieve high performance on PAU, with the best model (Claude-4-Opus) failing to understand over 45% of the PAU test set. An investigation into the common error modes reveals that models are overconfident; they often overrate the quality of their current hypothesis, leading to insufficient exploration and premature termination. Finally, we take inspiration from the Asymmetric Actor Critic (AAC) paradigm, frequently used in robot learning, to post-train models for interactive code understanding. Models trained with AAC conduct more active exploration of the APIs, with an AAC-tuned Qwen3-8B model matching the performance of GPT-5-mini.

This work establishes that determinant-based manipulability is an exact objective for fixed-task redundancy optimization, despite its dependence on task coordinates and the choice of task-space metric used for volume measurement. On every regular task fiber, the determinant proxy, its representation in any task chart, and every metric-completed manipulability differ only by positive constants. They consequently induce the same complete ordering, constrained extrema, gradient directions, critical points, and local optimality classifications. For comparisons and trajectory optimization across task fibers, this work introduces fiber-normalized manipulability: the capability attained at an internal state divided by the best capability available on the same fiber. The resulting dimensionless scalar is invariant under coordinate changes on the internal-state and task manifolds and independent of the task-space metric. Its associated loss provides an intrinsic objective for physically admissible cross-fiber trajectories, including problems with prescribed or free task evolution and temporal coupling. Planar-manipulator and redundant aerodynamic-allocation examples demonstrate fixed-fiber equivalence, task-dependent cross-fiber differences, and invariant fiber-normalized trajectory optimization.

Experiments have shown that modifications in communication hardware can enable unauthorized exfiltration of data from transmitters. We study the resulting Transmitter Trojan channel, in which a malicious encoder embedded within a legitimate transmitter perturbs the transmitted codeword on a symbol-by-symbol basis. The model reflects the limited footprint, delay, and computational complexity available to such hardware modifications. We derive achievable rogue message rate and achievable rates for the legitimate message under the mismatch induced by the Trojan. We also analyze decoding error exponents for the legitimate and rogue receivers, including operational exponent lower bounds obtained through channel-resolvability transfer arguments. Finally, we study Trojan detection at the legitimate receiver under different levels of statistical knowledge, including likelihood-ratio detection when the ensemble-averaged induced channel is known and goodness-of-fit detection when only the nominal channel is known. The resulting detection error exponents, together with the achievable rate and decoding error exponents, quantify tradeoffs among rogue message rate, legitimate message rate, decoding reliability, and Trojan detectability. We specialize the analysis to the binary symmetric channel and the additive white Gaussian noise channel, and illustrate the resulting tradeoffs numerically.

Vision–language–action (VLA) models provide strong priors for robotic manipulation but are typically deployed as frozen policies, unable to improve from their own failures. Real-world reinforcement learning (RL) offers a path to continued improvement, yet manual environment resets and task-success supervision hinder autonomous learning. We introduce FIND, an agentic real-world RL framework that closes the loop between scene understanding, weakness-aware practice, self-evaluation, and policy improvement in a persistent workspace. FIND reframes autonomous practice as a scene-conditioned, performance-aware task-selection problem: instead of restoring a predefined scene after each rollout, it uses the resulting scene to determine what to practice next. A vision–language agent identifies feasible tasks from a predefined library, prioritizes those with lower recent success rates, and evaluates outcomes using paired pre- and post-execution observations. We instantiate FIND with a frozen $\pi_{0.5}$ VLA and residual off-policy RL. Across eight real-world manipulation tasks, the independent human-assessed success rate improves from $55\%$ to $71.9\%$. A representative run completes 456 autonomous episodes within 6 hours of interaction, requiring 30 scene-recovery interventions and no human-provided reward labels during online learning. Ablations and systematic evaluations further examine key design choices, agent evaluation accuracy, and human intervention requirements. Our website is made publicly available at: FIND.github.io.

Motion retargeting transfers motion across characters with different skeletal structures while preserving semantic intent and physical plausibility. Despite recent progress, two fundamental questions remain: (i) how can reliable source-motion semantics be learned without high-quality paired retargeting data, and (ii) how should retargeting be formulated when no reliable paired motion can serve as a definitive regression objective? Existing methods commonly preserve semantics by constraining predictions toward copied motions. However, such initializations entangle useful articulation cues with artifacts caused by mismatched skeletal proportions and body geometry. Moreover, directly regressing a final motion in one forward pass is restrictive because retargeting is inherently underdetermined, and the desired solution must balance semantic fidelity with target-specific physical and temporal constraints rather than match a unique paired target. Motivated by these limitations, we propose ReFM, a source-mesh-agnostic, energy-guided model that reformulates motion retargeting as progressive refinement. First, an SO(3) canonicalizer removes redundant global-orientation variations. Second, a cross-character semantic encoder, pretrained through contrastive learning, provides a character-invariant representation for both optimization guidance and semantic evaluation. ReFM then progressively refines an initialized target motion through a learned flow guided by semantic consistency, physical plausibility, temporal coherence, and minimal motion modification. The framework is compatible with different initialization strategies, including both direct motion copying and Autodesk HumanIK, an industry-standard full-body inverse-kinematics retargeting system.

In this paper, an arbitrary Lagrangian-Eulerian (ALE)-based finite element method (FEM) is developed and studied in a monolithic framework for a class of two-phase Stokes flow problems with moving interfaces and jump coefficients, where the mixed finite element approximation to Stokes moving interface problems is established and analyzed in both semi- and fully discrete schemes based on the ALE formulation. The key analytical technique involves a specific H^1-projection associated with the ALE-induced mesh motion due to the evolving interface. Optimal convergence properties of the proposed H^1-projection and its ALE temporal derivative are proved in both H^1 and L^2 norms, with which optimal error estimates are obtained for both semi- and fully discrete mixed finite element approximations to the studied Stokes moving interface problem in both H1 and L2 norms as well. Numerical experiments are carried out to validate all derived theoretical results. The developed analytical approach can be extended to Taylor-Hood and MINI mixed elements, as well as to more general two-phase flow problems.

This paper presents Grasp2Twist, a bimanual dexterous manipulation system that learns to grasp and twist open jar lids using reinforcement learning. Learning this task raises three challenges: learning a unified policy for a multi-stage task, sustaining lid twisting, and sim-to-real transfer. To address the first challenge, we introduce a continuous enclosure measure to guide grasp formation and a binary enclosure indicator to guide the grasp-to-twist transition for unified policy learning. We derive both from the geometric relationship between the object center and the convex hull formed by the hand's palm and fingertips. Kinematic constraints limit how far the hand can rotate the lid with fixed contacts, so sustained twisting requires finger contact reconfiguration. We use a three-stage curriculum to facilitate exploration of these contact changes and also improve robustness for sim-to-real transfer. With our approach, the learned policy demonstrates finger gaiting, reconfiguring hand-object contacts to sustain lid rotation. It transfers zero-shot to the physical system and achieves an 88% task success rate across six household containers, including peanut-butter, vitamin, and instant-coffee jars. Ablations further validate the roles of the geometric enclosure in grasp formation and the curriculum in contact-reconfiguration exploration.

Although $\mathbb{E}[\mathrm{dropout}(x)] = x$, here we show that $\mathbb{E}[\mathrm{LayerNorm}(\mathrm{dropout}(x))]$ is not equal to $\mathrm{LayerNorm}(x)$. Accordingly, the pattern of a Dropout layer followed by a LayerNorm, which is common to many AlphaFold2-based protein structure predictors, produces a systematic bias at evaluation time that can hamper performance. To address this, we derive a closed-form, first-order correction for this gap, which we call a Dropout-LayerNorm Correction (DLC). DLC empirically matches the performance boost of large Monte Carlo dropout ensembles. We evaluate its effect across nine protein structure models (ESMFold, OpenFold, ABB3, FlashABB, Ibex, NbForge, Genie1, Genie2, Genie3) on both paired and single-chain antibody structures as well as one protein-ligand docking model (QuickBind). The correction is computationally negligible and improves accuracy in all ten models tested ($\sim0.3\%-13\%$), with a modest but consistent improvement in ESMFold and OpenFold and a substantial improvement in antibody-specific models. This work identifies the mathematical consequence of chaining together Dropout and LayerNorm and provides a free, principled adjustment to improve the evaluation performance of many pretrained models. Code to reproduce the experiments is available at https://github.com/oxpig/DLC.