Artificial Intelligence Papers

ALT Knowledge is how understanding accumulates across people and generations: durable records that outlive their producers and that others can check, combine, teach, and correct. AI agents are now built and run by many independent users and organizations, and each agent is upgraded, replaced, or retired within months. Yet what an agent learns stays trapped in model parameters, a transient context window, or a system-specific memory store that is appended to and retrieved from rather than processed. We argue that the next generation of AI should be knowledge-centric, built around an explicit, continuously evolving knowledge layer independent of any single agent. In this loop, agents discover knowledge from their environments and trajectories; the layer internalizes it by turning fragmented, heterogeneous records and experience into composable, revisable understanding; and agents across systems and generations use the result and return new outcomes for revision. While discovery and use have

ALT Despite recent advances in CUAs, their development remains constrained by the limited diversity, controllability, and reliability of interaction data. Moreover, conventional optimization pipelines lack iterative feedback, while existing recursive improvement approaches often rely on self-generated experiences, limiting ability expansion and yielding diminishing returns. To address these challenges, we introduce CUA-Master, a nested double-loop recursive improvement framework. At the system level, an outer world-data-model flywheel continuously incorporates open-world corpus and leverages evolving model weaknesses to guide subsequent data construction and optimization iterations. At the data level, an inner flywheel couples open-world seeding and autocatalytic propagation. The former mines authentic workflows as seed tasks from instructional videos, and employs visual-semantic dual-path trajectory reconstruction; The latter transforms these seeds into reusable primitives for controllabl

ALT Assessing regulatory compliance for high-risk AI systems requires systematic identification of technical gaps such as missing controls, in- adequate processes, or shallow evaluation of practices. Compliance officers typically admin- ister structured questionnaires collecting evi- dence of current practices, where organizations respond with descriptions of their existing pro- cesses, technical capabilities, and architectural choices. However, translating these compli- ance questionnaire responses into typed, ac- tionable gap diagnoses remains unsystematic. In this paper, we present a literature-grounded taxonomy of technical compliance gaps cover- ing areas such as accuracy, robustness, logging, and human oversight, and embed it in GapTo- Compliance, a two-stage agentic framework coordinating two specialized agents: a Gap Extraction Agent that performs hierarchical rea- soning from compliance areas to specific gap types, and a Remediation Planning Agent that ranks remediation actions fr

ALT Large language models (LLMs) are driving autonomous agents toward real-world environments, with the Web emerging as one of the most representative interaction scenarios. However, training Web agents with naive exploration remains challenging: successful trajectories are rare, and the sparse terminal rewards make it difficult for agents to obtain useful feedback from failed trajectories. Inspired by skill acquisition theory, we propose Skill-Composed Progressive Exploration (SCOPE), a short-to-long learning framework for long-horizon Web agents that decomposes complex task exploration into a gradual expansion process from local skills to complete task-solving capability. Specifically, SCOPE iteratively explores around local skills: Skill Discovery extracts reusable local skills and failure experiences from historical rollouts; Skill Orchestration composes discovered skills into high-level skill chains; and Skill Expansion leverages failure experiences aligned with the current skill chai

ALT An experimental agent can succeed for the wrong reasons. Evaluations, however, often focus on the outcome, not the experiments, evidence, and inferences that produced it. We introduce LUCA, a configurable synthetic world for evaluating this process under fully known ground truth. Agents learn unknown regulatory systems through budgeted experimentation, then predict unseen interventions, diagnose hidden faults, and attempt rescues. This setup allows us to evaluate experiment selection, prediction, diagnosis, and intervention separately. Across seven frontier LLMs and three baselines, these capabilities dissociate sharply. Agents frequently rescue malfunctioning systems while diagnosing the wrong fault; diagnosis varies 7x across models while prediction varies only 1.4x. Models also adopt surprisingly different experimental strategies, and greater exploration does not reliably yield better performance. In one failure mode, agents often perform the experiment needed to distinguish competi

ALT Theoretical limitations of transformers on state tracking—the ability to track information about entities or variables over long contexts—have motivated new recurrent language modeling (LM) architectures such as Gated DeltaNet (GDN). These architectures have, in particular, been benchmarked against the S₅ word problem, a theoretically hard state-tracking task that captures abilities such as code evaluation under arbitrary variable assignment. It, however, remains open whether other, simpler forms of state tracking might both be more relevant in practice and already explain observed differences between these architectures. We propose evaluating state tracking using a hierarchy of word problems with four increasing levels of difficulty: r-trivial, corresponding to immutable assignment to variables in programming; aperiodic, where assignments are mutable; soluble, where assignments are self-referential; and general finite state tracking. Theoretically, we show that the class of problems t

ALT Personal AI agents are increasingly capable of handling long-horizon tasks across applications, yet users often need to invest substantial effort in specifying goals, resolving ambiguity, and verifying outcomes. We argue that progress should be measured by how effectively agents amplify human agency: enabling people to pursue their goals with less routine supervision while retaining control over consequential decisions. We advocate Avatar Intelligence, a paradigm of persistent personal agents that represent users' goals, values, and constraints through sustained decision delegation across contexts and time. We describe a maturity roadmap from human-directed execution to autonomous operation within delegated domains, and introduce the Agentic Oversight Index (AOI) as a framework for evaluating delivered value against agent-side operational cost and human oversight burden. We identify three core research challenges: identity-continuous personalization that carries user preferences across

ALT Large language model applications are increasingly being organized as tool-using and multi-agent workflows rather than as isolated chat interfaces. This perspective paper examines the architectural problem that follows from that shift: agents may reason, invoke tools, and delegate work, but dependable deployment still requires interoperability across frameworks, runtimes, data boundaries, and organizational control domains. We study this problem through the lens of the Internet of Agentics (IoA), an emerging service-computing view in which heterogeneous agents are treated as governable service participants rather than only as stand-alone model endpoints. The paper organizes the landscape as a three-layer progression: from today's fragmented agent ecosystem, to interoperable agents, and ultimately to trustworthy and governable autonomy. First, it examines the protocol stack centered on the Agentic AI Foundation, including MCP for agent–tool interaction; A2A for agent–agent coordination;

ALT Recent advances in Artificial Intelligence (AI), particularly large-scale deep learning, have been driven by monolithic or offline training on massive curated datasets. While successful, these approaches face structural limitations: escalating data and computational demands, limited online adaptability, and a lack of system-level intelligence in open, non-stationary environments. This paper presents Networked AI - a networked intelligent system composed of interacting, heterogeneous, and continuously evolving AI agents. We establish a hierarchical layered architecture comprising an Agent Layer for heterogeneous capability construction, an Interaction Layer for signal-processing-guided online data extraction, and a Regulation Layer for stability-constrained collective evolution. Foundations in data science, signal processing, and system control are hereby synthesized into a unified theoretical framework of Networked AI, providing superior data efficiency, intelligence efficiency, interp

ALT Feedback-driven iteration is widely used to improve LLM-generated scientific ideas, but existing systems either leave revision decisions implicit in generation, align revisions with feedback-localized weaknesses, or restrict action selection to system-specific operations. This is problematic because problems, hypotheses, and solutions are interdependent: the location where a weakness manifests does not itself determine the revision scope that will produce a better successor. We term this phenomenon diagnosis-intervention mismatch. We introduce Predictive Routing of Interventions by Modeling Effects (PRIME), a plug-and-play feedback-to-revision decision layer for existing scientific ideators. PRIME operates in three stages: (1) Structural Attribution interprets feedback over the problem-hypothesis-solution structure without fixing a revision target; (2) Counterfactual Routing constructs alternative scope-conditioned interventions and compares their projected successor utility and risks

ALT Long-horizon tasks require large language model (LLM) agents to coordinate interdependent actions, a capability central to automating complex workflows. Stepwise group-based reinforcement learning provides finer credit than trajectory-level supervision, but reliable comparisons must account for differences in interaction history. Enforcing this consistency within the limited rollouts of each task can leave insufficient support for estimating action preferences. We propose Beyond-Local Policy Optimization (BLPO), which estimates task-progress advantages from experience shared across tasks and training updates. We summarize trajectory prefixes into task-progress states and abstract actions by their function, allowing corresponding decisions from different tasks to contribute to shared estimates. To control bias and noise from heterogeneous tasks, we accumulate context-relative returns in a global memory with balanced aggregation and reliability weighting. These global advantages compleme

ALT The multi-turn checker of the Berkeley Function Calling Leaderboard (BFCL) evaluates final state correctness but ignores the effects of intermediate calls: extra calls are free, function documentation does not describe side effects, and the scripted user never responds to proposals. Consequently, models asking for confirmation before destructive actions are penalized; 260 of 734 reference turns in the base category perform destructive actions without confirmation. We make BFCL effect-aware without replacing it. We infer effect declarations for all 128 functions by executing them in BFCL simulators and comparing state changes, with destructive writes identified by three annotators. A judge-free replay scorer reproduces official results across all 800 reference trajectories while reporting unrequested destructive calls, duplicate writes, redundant reads, surplus steps, and their token costs. We also introduce a confirmation-aware protocol with a deterministic simulated user. Across 11 op

ALT Language model agents increasingly act on users' behalf by manipulating external environments through tools, often from high-level instructions that leave critical task- and environment-specific context unstated. To prevent resulting misaligned actions, recent work verifies proposed actions before execution, largely by establishing whether the conditions supporting them hold. We argue that this confirmation-oriented view leaves a fundamental blind spot: a wrong action often passes every check that asks whether it is right. This motivates a different question for verification: rather than asking what evidence supports an action, can the agent find evidence that refutes it? We pursue this direction with BlackSwan, a refutation-oriented, expect-suspect-test procedure that predicts the intended effect of each state-mutating action, formulates specific and empirically testable hypotheses for how it could be wrong, and tests them using existing observations or additional non-mutating actions

ALT Given a relational database (RDB) storing heterogeneous tabular information, how can we predict missing (or future) values in some target column of interest? As candidate targets are numerous in enterprise settings, it is preferable to avoid learning a new model from scratch each time there is a new prediction task. Frozen foundation models (FMs) based on in-context learning (ICL) and RDB-specific pre-training provide a viable solution, but the ideal design still remains largely unresolved. Perhaps unexpectedly, preliminary evidence has recently shown that existing single-table FMs (aka TFMs), when combined with suitable parameter-free relational encoders, can be quite competitive in practice despite zero exposure to RDB pre-training or relational data of any kind. In this work we first empirically confirm this phenomenon with a more diverse array of experiments. We then turn to our main contribution, namely, surfacing multiple complementary explanations for why TFMs behave so effectiv

ALT Online political discussions increasingly involve AI-mediated participation, as users invoke LLMs to assess contested claims, arbitrate disputes, and respond to opposing viewpoints. As these systems become participants in online exchanges, they may alter which speakers and argumentative strategies receive validation within the discussion. We study this interactional dimension by reconstructing 5,376 Debate.org debates as LLM conversations and running nearly 150,000 controlled multi-turn conversations that vary user political orientation, expertise, rhetorical strategy, and defended position, including conversations with competing users. Across naturalistic and controlled debates, we find that LLMs are systematically more receptive to left-leaning than right-leaning users. The asymmetry persists when users with different political orientations defend the same position and when opposing users appear in the same conversation, indicating that it is not fully explained by stance agreement o

ALT An agent that explores, whether it generates conjectures or research ideas, must decide which of them are worth keeping. This judgment of interestingness is usually delegated to a hand-picked proxy or to a language model, neither of which is known to correspond to what humans actually value. I study it for mathematical theorems, by observing which results mathematicians single out in formal libraries and in papers. I model each way of singling out results as an evaluator that weights features of a result's statement, its proof and dependencies, and split its weights into a shared and a subjective part. In formalized mathematics, ex-ante features predict these selections as well as a large language-model judge, and the two complement each other. Interestingness is also largely shared. One set of weights, carried mostly by structural features such as the length of the statement and of the proof and the subfields the proof draws on, accounts for most of the signal and transfers in part ac

ALT Remote sensing image fusion and semantic interpretation are usually optimized separately, so reconstruction quality need not preserve downstream retrieval utility. We propose LANCE, which uses structured language as an explicit, indexable semantic state. A frozen vision-language model maps the input to a closed-vocabulary text record; a language-conditioned generator fuses the imagery; and a dense verifier with a differentiable continuous summarizer re-describes the output. Text-text consistency and anti-collapse contrastive text-mask losses with negative queries close the loop without dense annotations or VLM fine-tuning. A variational EM formulation yields a per-step contraction result under regularity assumptions, distinguishing semantic faithfulness from verifier overfitting. Across seven test sets on GF2, QuickBird, WorldView-III, and WorldView-II, LANCE improves reduced-scale reference metrics by up to 11.7% (median 2.1%) over the strongest learning baseline. Independent evaluati

ALT High-quality annotations are essential for training and evaluating artificial intelligence (AI) systems. Quality control (QC) often acquires additional human or AI judgments before accepting a label. Nevertheless, shared biases can cause correlated judgments, leading conventional methods to mistake repeated agreement for independent evidence of correctness. To address this challenge, we propose JABER (Joint Alias-Preserving Belief for Evidence Routing), a bias-aware sequential QC framework that maintains a joint Bayesian posterior over label correctness and shared biases to guide evidence acquisition and termination decisions. Building on this posterior, we develop a finite-horizon algorithm that selects evidence-acquisition and termination actions to minimize expected QC loss under resource constraints. Our theoretical analysis shows that conditional-independence updating can become arbitrarily confident in an incorrect label under persistent shared bias. We further identify when repe

ALT Reclamation of saline-alkali land requires management plans that account for soil and water conditions, treatment evidence, and financial constraints. This study develops Wenyao, an agricultural decision-support system integrating domain adaptation with retrieval-augmented generation. A bilingual corpus of 8,664 research papers was processed using a 110-indicator schema to construct SA-Bench, comprising 4,860 paper-level planning instances. A QwQ-32B model was adapted through low-rank supervised fine-tuning and combined with case retrieval for budget-conditioned planning. Evidence extraction achieved an F1-score of 0.83 on 300 expert-annotated papers. Without retrieval, Wenyao achieved 95.83% accuracy on 936 source-disjoint multiple-choice questions, compared with 87.93% for the strongest general-purpose baseline; removing explanatory supervision reduced accuracy to 89.42%. Matched-evidence comparisons across 69 region-budget cases supported complementary contributions from adaptation

ALT Sampling and selection spend test-time compute inside a candidate pool, but they cannot recover a correct answer that never enters it. We introduce ValueFormation, a test-time policy that decides after each primary-model draw whether to stop, continue sampling, or acquire one proposal from a heterogeneous reasoning specialist. The three actions are compared on one cost-regularized value scale learned from vote-state features; the calibration is frozen across tasks and primary models, and acquired proposals are accepted only through a frozen posterior comparison. On held-out MATH-500, one Llama-fitted calibration improves over the strongest of eight identically evaluated baselines by more than fifteen points for each of three 8B primaries and transfers unchanged to Qwen3-14B. Removing acquisition lowers Llama MATH accuracy by 20.43 points, while same-trace and same-access replays attribute the gain to state-conditioned acquisition rather than specialist access alone. Where primary cover