SEARCH · Searcharxiv

Search Searcharxiv

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 757 records · Page 42Linked to original sources

arXiv2026

ASCEND: Personal AI Agents for Autonomous Scientific Computing Across HPC Clusters and GPU Workstations

Traditional scientific computing requires researchers to translate computational intent into environment configuration, resource requests, and executable jobs, then diagnose failures from scheduler state and application logs. We present ASCEND (Autonomous Scientific Computing Engine and Novel Discovery), an AI-powered agent interface that runs the agent on the researcher's own laptop, reaching Slurm-managed clusters and a GPU workstation over a multiplexed authenticated connection, with site-specific execution policies checked by locally executed tools; the language model is hosted remotely and holds no credentials. No facility-scale service is required: an account on each resource is sufficient, and the public installer lets users link additional Slurm clusters or workstations of their own. We report four recorded cases: (1) the agent closed a failure-recovery loop on a planted tensor-device fault, submitting, diagnosing, repairing and resubmitting with job-level artifacts preserved; (2) it reproduced the published evaluation of a weather-forecasting model from the author's released forecasts, agreeing with the published curves to 2.1% (z500) and 2.4% (t850) while identifying a unit discrepancy in the paper's prose and an initialization-field discrepancy in its released data; (3) it parallelized a released 12,693-line geophysical solver under a bit-for-bit identity requirement, reducing wall-clock runtime from about twelve hours to about two; (4) that requirement exposed two instances of undefined behaviour in the published solver, both repaired and reported upstream. Separately, a pre-specified evaluation of the policy layer found the deployed validator rejected 29 of 30 constructed violations and held the remaining one for approval, while denying 3 of 14 legitimate requests. Autonomy was exercised under author supervision; an end-to-end recovery benchmark remains outstanding.

cs.DC↗

arXiv2026

Multimodal LLMs Outperform Pathology Foundation Models in Cross-Domain Histological Similarity

State-of-the-art pathology foundation models, trained on millions of histology tiles, can fail to preserve tissue similarity when comparisons cross slide or institution boundaries. We show that general-purpose multimodal LLMs, without being trained as pathology foundation models, consistently outperform these specialized models in cross-domain histological similarity judgments. Using a relative similarity framework that we release as the MOSAIC (Model Similarity Assessment across Institutions and Cohorts) benchmark, we evaluate 17 models across 6 datasets and find that pathology encoders often rank same-institution, different-disease tiles as more similar than same-disease, different-institution tiles, a clinically dangerous failure mode invisible to standard within-domain evaluations. LLMs appear less susceptible to this failure, likely because they perform semantic visual comparison of morphology and tissue architecture rather than relying on shortcut features tied to acquisition context. Scaling training data does not resolve the problem for pathology encoders, implicating the learning objective rather than data coverage. Our results expose a fundamental robustness gap in current pathology foundation models and establish multimodal LLMs as a viable alternative for cross-institutional retrieval, dataset harmonization, and multi-site quality control. Code and data will be released upon acceptance.

cs.CV↗

arXiv2026

The Commit-Abstain Circuit: Why Language Models Hallucinate Instead of Abstaining

Language models (LMs) often hallucinate by committing to confident answers rather than abstaining, even when they do not have enough information to answer reliably. A large body of existing work mitigates hallucination through detection or abstention mechanisms, but leaves open how models internally arrive at the decision to commit or abstain in the first place. We study this decision through mechanistic analysis, framing hallucination as unsupported commitment: the model commits despite exhibiting signals of unanswerability. Using causal gating, we identify a Commit-Abstain Circuit (CAC), a sparse, causally localised subset of attention heads and MLP sublayers underlying this decision. Across ten LMs (3B-14B) from five families and three benchmarks, the CAC exhibits a recurring accumulate-yet-undercorrect pattern: commitment-promoting components build up commitment in earlier layers, while abstention-promoting components act later as corrective signals that are often insufficient to overturn the accumulated commitment. Building on this finding, a lightweight policy trained on CAC activations improves decision accuracy by 12.2 points over the model's intrinsic commit-abstain margin, reduces false abstentions by 2.5 times, transfers to unseen benchmarks, and extends to larger models (27B-35B). The CAC is both diagnostic, clarifying how models overcommit, and practical, enabling improved abstention decisions.

cs.AI↗

arXiv2026

Relic: From Multi-Agent Collaboration to Persistent Organizational Capability

Multiple agents may often conflict in an organization: for example, one coding agent changes an interface in a repository, but another continues to develop on the old version where existing tests become stale. A conversation can resolve the episode, but when the participants change, what makes the lesson continue to govern the team? We introduce Relic, which turns recurring collaboration failures into organization-owned, executable protocols. Members reflect on visible work, propose rules, and govern their adoption. Adopted protocols bind triggers, responsibilities, required evidence, and execution consequences to the runtime, while remaining open to revision and retirement. In one traced case, repeated integration friction produces an interface-review rule that governs later pull requests and is revised as work continues. Across 360 controlled runs over ten software workloads and three models, Relic raises complete-contract delivery from 14.06% to 19.76% (+5.71 percentage points) over a matched structured team without the protocol lifecycle, improving all four verified production endpoints in every model stratum. Under fresh-member transfer, behavioral correctness is 25.4% with no inherited protocol, 34.6% with the same rules provided as readable text, and 41.2% with executable bindings, a +6.5-point advantage over text alone. On the full CooperBench benchmark, after excluding 183 broken benchmark pairs, Relic achieves 371/469 (79.1%), establishing the best reported result among peer-structured systems. On the 47-pair same-model subset, Relic also exceeds Solo (28/47 vs. 26/47), reversing the coordination loss exhibited by the official peer baseline. Together, these results show how collaboration experience can become persistent organizational state that remains useful beyond the members who created it.

cs.AI↗

arXiv2026

Obtaining Game-Stationary Points for Smooth Nonconvex-Nonconcave Minimax Problems via First-Order Methods

Minimax optimization is a fundamental framework in machine learning, robust optimization, and game theory, yet finding first-order stationary points of general nonconvex-nonconcave minimax problems remains challenging without additional structural assumptions. Existing guarantees often rely on global PL- or KL-type conditions that connect max-player stationarity to global inner optimality, or on Minty-type conditions that impose a global relation on the game gradient field relative to a reference solution; local KL variants relax the former requirement but typically require initialization and tracking within a near-optimal region. Such conditions may be difficult to satisfy in many applications. In contrast, we develop a first-order method that finds an $ε$-stationary point within $\widetilde{O}(ε^{-2})$ first-order iterations under a local inverse-Lipschitz regularity condition around approximate max-player stationary points, together with a compactness condition on a penalty sublevel set. Our condition places no optimality requirement on stationary points of the inner maximization problem: they need not be globally, or even locally, maximizing. We further provide sufficient conditions for the required regularity. In the unconstrained setting, it follows from uniform nonsingularity of the maximization-variable Hessian near stationary points; for constrained upper Moreau envelopes, it follows from standard KKT regularity conditions. These results establish first-order complexity guarantees for classes of nonconvex-nonconcave minimax problems not covered by the above PL-, KL-, or Minty-type frameworks.

math.OC↗

arXiv2026

Global classification of oscillatory dynamics in symmetric zero-divergence 3D piecewise-linear Filippov systems with a visible--visible two-fold

A global classification of the asymptotic oscillatory dynamics is established for a symmetric zero-divergence class of three-dimensional piecewise-linear Filippov systems, up to a set of initial conditions of zero Lebesgue measure. The affine fields are related by an involution, and the switching plane contains a visible--visible two-fold. In canonical coordinates, the eigenvalues are $μ\pm i$ and $-2μ$, while $H$ measures the focal-line inclination. For every $μ>0$, a simple-period crossing cycle exists if and only if $H\in\mathcal I_μ$, and is unique, symmetric, hyperbolic, and orbitally asymptotically stable. Its half-period parametrizes $\mathcal I_μ$ and determines the crossing points, period, and Floquet multipliers. Global dissipation excludes crossing cycles with any higher number of crossings and makes the classified cycle the $ω$-limit set of every crossing-only trajectory. If attractive sliding has no interior pseudo-equilibria, sliding is transient unless the trajectory reaches the two-fold. The initial conditions leading to the two-fold lie in a countable union of analytic surfaces and curves. Under sufficiently small perturbations in the Whitney $C^1$ topology, the cycle persists as the unique simple-period crossing limit cycle and remains hyperbolic and orbitally asymptotically stable.

math.DS↗

arXiv2026

Byzantine-Robust Federated RAG via Aligned Calibration and Fixed-Membership Conformal Prediction

Retrieval-augmented generation (RAG) lets language models answer questions more accurately by consulting relevant documents. Many valuable collections, such as medical records, cannot be pooled because of privacy rules. Federated RAG leaves each collection with its owner, or node, which scores candidate answers from its own documents; a central hub combines the scores. Some nodes, called Byzantine, may be compromised, faulty, or misled by instructions hidden in documents, and report arbitrary scores. Conformal prediction returns a set containing the correct answer with a chosen probability, using a cutoff set in a calibration step on questions with known answers. An unknown group of nodes, no larger than a declared bound, may misreport both in this step and at query time. Existing methods assume every node is honest or protect only the calibration step. We observe that the honest nodes are the same in both steps. The hub therefore has all nodes score the same calibration questions, and keeps a candidate only if some plausible group of honest nodes, using its own scores in both steps, would keep it. We prove that the resulting sets contain the correct answer with the chosen probability in finite samples, whatever the Byzantine nodes report. No method using the same information can return smaller sets without risking the loss of an answer the honest nodes support. If nodes fail at random, the guarantee weakens only by the probability that more nodes fail than declared. In simulations, on real question-answering tasks including medical exams, and with language models as nodes, some hijacked, our sets reached the target whenever no more nodes misbehaved than declared, while plain averaging could miss it. They were also clearly smaller than those of simpler methods with the same protection, most of all when the declared bound was generous, so a cautious bound costs little.

stat.ML↗

arXiv2026

Hierarchical Secure Distributed Linearly Separable Computation with Arbitrary Heterogeneous Data Assignment

This paper studies secure distributed linearly separable computation over a three-layer hierarchical network, where clustered users communicate with a central server through relays. The server aims to recover Kc linear combinations of K intermediate outcomes, where each intermediate outcome is a separable function of one dataset. We consider a more general setting with arbitrary heterogeneous data assignment across users, where ''arbitrary'' means that the data assignment is given in advance (which can be in any form) and ''heterogeneous'' means that the users may hold different numbers of datasets. Under this assignment, each user computes the intermediate outcomes of its assigned datasets and sends masked messages to its associated relay. The relays subsequently process and forward the received messages to the server. We impose two security constraints: (i) security against server, requiring the server to learn only the desired task function without gaining any additional information about users' inputs; and (ii) security against relays, ensuring each relay learns nothing about users' inputs. Moreover, the server or any relay may collude with a subset of users. For Kc=1, the underlying computation reduces to distributed gradient coding. We propose a secure scheme tolerating user dropouts and user collusion, achieving the optimal two-layer communication rates in one regime and order-optimal communication rates within a factor of 2 in the other regime. For Kc>1, we extend the proposed construction to multi-dimensional linearly separable tasks under the no-dropout setting.

cs.DC↗

arXiv2026

The Breakdown of Classical Minicrypt Equivalences in the Quantum-Computation Classical-Communication Model

Classically, it is well-known that several fundamental cryptographic primitives, including one-way functions, pseudorandom number generators, commitments, and signatures, characterize the same cryptographic world, which is known as "Minicrypt". In this paper, we investigate to what extent this picture persists in the quantum-computation classical-communication (QCCC) setting, where parties may perform quantum local computation, but communicate through only classical messages. We demonstrate that the classical Minicrypt landscape breaks down in the QCCC model by oracle separations. We construct two oracle worlds where efficiently verifiable one-way puzzles (EV-OWPuzz) exist. By a known equivalence, QCCC one-time signatures also exist in both worlds. In the first, one-way functions do not exist, even if we allow quantum pseudodeterministic evaluation. In the second, QCCC bit commitments do not exist. Thus, the classical Minicrypt reductions from signatures to one-way functions and bit commitments have no fully black-box counterparts in the QCCC setting. Our proofs develop techniques for analyzing the random phase states, including a concentration theorem and an LOCC decoupling theorem, which may be of independent interest.

quant-ph↗

arXiv2026

Compositional Safety Failures in Harness Evolution: Identification and Runtime Monitoring

Self-evolving agent harnesses continually update persistent components such as memory, prompts, skills, and tools. We call this process harness evolution. However, such evolution could introduce unexpected safety risks. Existing work studies harness misevolution and validates candidate harnesses or attributed individual component updates, leaving safety analysis of cross-component update interactions largely unexamined. To address this gap, we study compositional safety failures in harness evolution, where interactions among individually safe and utility-preserving component updates can produce undesirable or unsafe agent behavior, revealing a safety risk intrinsic to harness evolution. Across three safety-related benchmarks, we identify 43 pairwise and 18 irreducible 3-way compositional safety failures. Conventional solution incurs combinatorial complexity in validating cross-component interactions, leaving the safety checking impractical as the harness evolves. To solve this, we introduced a typed hypergraph that represents component states as nodes and safety-relevant higher-order interactions as hyperedges. When the harness changes, the hypergraph updates only the interaction neighborhood of the changed states rather than reconstructing the global composition space. Building on that, we develop a hypergraph-guided runtime monitoring mechanism. Experiments show that our method effectively mitigates compositional safety risks while preserving task utility and reducing interaction-checking costs, and further reveal an empirical safety-utility-cost trade-off across different safety mechanisms.

cs.AI↗

arXiv2026

Knowing Is Not Choosing: What Explicit Verification Adds Beyond Generative Preference

Generating a correct answer does not mean that a language model will select it. We separate factual recall into three steps: generating a correct candidate, ranking the available candidates, and selecting the final answer. Pre-generation readouts predict factual recall and which questions sampling will cover across three model families, but say little about whether an available correct answer will ultimately be selected. Explicit verification with $P(\mathrm{True})$ improves within-question ranking over mean log-likelihood in Gemma, Qwen3, and Llama, with AUROC gains of $0.08$--$0.12$. In a prospectively defined Gemma cohort, verification raises plurality accuracy by about $5$ points, and still gains about $2$ points over chat-template likelihood, a stronger generative baseline. The advantage is strongest for relations with common-answer priors and depends on access to the entity; masking the entity removes the ranking advantage in larger Qwen models. Finally, the measured benefit depends on how correctness is defined: recall-oriented reference matching can credit option lists favored by likelihood and substantially understate the improvement seen under human semantic judgments. Prior work shows that models can carry latent factual knowledge and judge candidate answers; we show that these capabilities do not collapse into a single notion of ``knowing,'' and trace where information is gained, lost, or mismeasured between availability, ranking, and final choice.

cs.CL↗

arXiv2026

Beyond State-as-Action: Exploiting Command-State Discrepancy for Robot Imitation Learning

Constructing action targets from measured robot motion is an established approach in imitation learning. Under interaction constraints, however, command-state discrepancy may reflect control demands that motion alone does not capture. We investigate when this information matters and how to exploit it. Across three real-robot tasks, task and phase analyses reveal larger supervision gaps under constrained interaction, while selective command retention provides evidence of locally useful command information. Building on these findings, we propose Command-State Discrepancy Weighting (CSDW), which accounts for robot response times and combines subsequent progress, persistent unmet demand, and demand changes into continuous weights for command supervision. The method requires no task-phase annotations or changes to policy architecture or inference. CSDW improves over uniform command supervision on constrained tasks, while methods perform similarly in the less constrained task. Project page: https://seen-e.github.io/CSDW/.

cs.RO↗

arXiv2026

Which Self-Improvements Should We Trust? Reliable Self-Improvement When Agents Reuse Their Benchmarks

As recursive self-improvement (RSI) rapidly advances, reliable evaluation becomes critical for guiding adaptive search. RSI typically relies on finite evaluation resources, such as fixed benchmarks, to determine which modifications are retained and what is proposed next. However, when these finite resources are repeatedly reused, new candidates are proposed based on feedback from the same evaluation set, so the search trajectory can adaptively overfit and empirical improvement may not reflect genuine population improvement on the underlying task distribution. Some existing methods account for multiple comparisons but assume that candidates are chosen independently of the evaluation set, and therefore do not control this adaptive dependence. To address this, we propose REUSE (Risk-controlled Evaluation Under Sequential Evolution), a certified evaluation and promotion framework that allows a fixed evaluation set to support repeated adaptive decisions while providing statistical guarantees. For a user-specified error level $α$, with probability at least $1-α$, every promoted modification is a genuine population improvement on the underlying task distribution. REUSE achieves this by strictly limiting the evaluation feedback returned to the search process and accounting for possible promotion histories within the error budget. We develop detailed statistical theory for RSI evaluation in this setting, including simultaneous error control, valid lower bounds on cumulative improvement, and a characterization of the fundamental limits of adaptive evaluation reuse. In live self-improvement experiments, REUSE commits substantially fewer false promotions than evaluation frameworks from current RSI systems and error-controlled baselines, reducing the proportion of false promotions from up to 20.7% to 0%, while achieving final true population performance comparable to the best baselines.

stat.ML↗

arXiv2026

Teach Yourself Where to Look: On-Policy Attention Self-Distillation for Reasoning

On-policy self-distillation trains reasoning models on their own trajectories using dense token distribution guidance from a privileged teacher with access to a verified solution. This supervision transfers what the teacher predicts without directly transferring where it attends within the preceding context. We introduce On-Policy Attention Self-Distillation (OPASD), which complements token-level supervision with solution-conditioned attention distillation. Because the privileged teacher can attend to verified solution tokens unavailable to the student, OPASD projects teacher attention onto student-visible positions and renormalizes the resulting distribution before alignment. Across three model sizes and four competition-level mathematics benchmarks, OPASD consistently outperforms token-only OPSD, improving average accuracy by 4.98 to 8.40 percentage points. OPASD also avoids the response-length inflation and performance degradation observed with token-only distillation, reducing generated rollout tokens by 73.9% and estimated model compute by 72.6% while training 1.53x faster. These results show that solution-conditioned attention provides a complementary supervision signal that makes on-policy self-distillation more accurate, stable, and compute-efficient.

cs.LG↗

arXiv2026

PARSEE-VAD: Efficient Training-Free Online Video Anomaly Detection via Proposition-Aware Reasoning and Streaming Evidence Escalation

Training-free online video anomaly detection (VAD) with frozen multimodal language models faces two coupled challenges: extracting reliable current-window semantics under causal and computational constraints, and maintaining temporal continuity without repeatedly transmitting high-dimensional history. Encoding history through text can compress visual evidence and introduce semantic bias, whereas retaining visual history expands multimodal context. We introduce PARSEE-VAD, a two-module framework that separates semantic evidence acquisition from score-state evolution. Proposition-Aware Reasoning (PAR) extracts structured propositional evidence from the current causal window and conditionally activates more specific queries when coarse evidence warrants further refinement. By sharing a reusable causal visual prefix across queries, PAR reduces redundant computation through selective execution. Streaming Evidence Escalation (SEE) maps the acquired proposition evidence into a compact score-domain event state through current evidence escalation, then propagates only the resulting bounded state across decisions to support temporal continuity. Experiments on four benchmarks demonstrate strong training-free online performance while selective routing reduces specialist computation and score-state propagation remains sparse. These results support a current-first principle for streaming multimodal inference: resolve present semantics first, then use compact historical state only to repair residual continuity gaps.

cs.CV↗

arXiv2026

GTRL: Grounding Divide-and-Conquer Value Learning with Temporal Differences

In offline goal-conditioned reinforcement learning (GCRL), divide-and-conquer scales to long horizons by joining two shorter segments at a subgoal. However, under stochastic dynamics, the base case of this rule values the luckiest trajectories through the data. The subgoal must also lie on a shared trajectory, so a state-goal pair that no trajectory connects gets no value update at all. To address both, we present Grounded Transitive RL (GTRL), an offline GCRL value learning algorithm that grounds the divide-and-conquer update with a one-step TD target. Over a single step, TD is correct, as its target averages over the successors and needs no subgoal. GTRL adds this target to the composition rather than replacing it, so every pair receives an update, and the composition still carries the long horizon. GTRL also corrects the bias from hindsight relabeling by reweighting each goal against how reachable it was from other successors. We evaluate our algorithm on nineteen OGBench tasks spanning stochastic, deterministic, and stitching environments, where it achieves the highest average success rate. Code will be released soon.

cs.LG↗

arXiv2026

Prime-Detecting Identities from Dirichlet Inversion

For each integer k >= 1, let sigma_k(n) = sum_{d|n} d^k, let sigma_k^{-1} denote its Dirichlet inverse, and let J_k denote the kth Jordan totient function. Using established prime-power values of sigma_k^{-1}, we first obtain the elementary criterion sigma_k^{-1}(n) + J_k(n) + 2 = 0 precisely when n is prime. At k = 1, this involves Euler's totient J_1 = phi and provides a prime-only comparison for the next equation. Our main result classifies the zeros of sigma_k^{-1}(n) + mu(n) + J_k(n) + 3: for k = 1, they are precisely the primes and 18; for k >= 2, they are precisely the primes. The proof separates integers according to their prime-exponent patterns. Sign and divisibility arguments exclude composite zeros outside the cube-free nonsquarefree case, where an additional divisibility condition isolates 18 at k = 1 and precludes composite zeros for higher k. Standard convolution and Lambert-series identities provide the arithmetic framework, while an intermediate-divisor relation explains the exceptional zero. These criteria are structural characterizations rather than efficient primality tests, since direct evaluation of the multiplicative formulas generally presupposes a factorization of n.

math.NT↗

arXiv2026

AquaWAM: A Dynamics-aware World Action Model for Underwater Embodied Agents

World Action Models (WAMs) are becoming increasingly important and useful for embodied intelligence, as they enable robots to anticipate the consequences of candidate actions before interacting with the physical environment. However, underwater robots are usually subject to passive dynamics, such as inertia, buoyancy, hydrodynamic drag, and persistent drift, which can continue to affect the vehicle even after an action is completed. Existing WAMs, which primarily predict action-conditioned visual observations, are not explicitly designed to capture such passive motion dynamics. In this paper, we present AquaWAM, the first World Action Model designed for underwater embodied agents. Instead of predicting future images, AquaWAM models both action-conditioned and passive physical dynamics, including the thruster dead band, the inertial glide that outlasts each command, and ambient currents. Specifically, it senses through the DVL, IMU, pressure sensor and joint encoders, while cameras supply only semantics for understanding goals and target pose. By modeling compact navigation states rather than high-dimensional visual observations, AquaWAM substantially reduces the model size and computational cost compared with conventional WAMs. Experimentally, AquaWAM achieves a 72.6% task success rate across 20 underwater tasks on the USIM benchmark, outperforming existing methods while making action decisions 2.7x faster than U0 on an NVIDIA Jetson AGX Orin. Our model also remains effective when some onboard sensor measurements are unavailable. For example, without DVL velocity measurements, our method still achieves a 61.6% success rate, compared with 39.4% for U0.

cs.RO↗