Artificial Intelligence Papers

ALT Computer-use agents act through graphical interfaces, command lines, APIs, scripts, and Model Context Protocol servers. A policy decision can be interface-invariant while its executable authorization is not: another route can bypass mediation, alter a security-relevant default, or commit after the authorized state has changed. We present a profile-bounded protocol for a fixed, versioned computer-use deployment. It enumerates effect-bearing routes and durable sinks, checks a route-to-sink enforcement cut, normalizes each concrete request to a canonical effect, issues a route-bound prepare ticket, and verifies the route, effect, grant, trace, profile, inventory, and authoritative state again at commit. A committed result requires an agreeing sink receipt. Under explicit assumptions, we prove profile-bounded refinement, matched-effect decision invariance, resistance to alternate-route laundering and declared cross-surface recomposition, commit-time state safety, and receipt-grounded outco

ALT Evidence-grounded NLP systems often verify nested text regions sequentially, so verifying one region constrains others. We formalize this as Online Evidence-Containment Prediction (OECP): each candidate is predicted before exact verification and queried at most once. Span containment is exactly a triangular 2D product order, making OECP distinct-query online isotonic regression. With multiple admissible targets, worst-case regret is near-linear, widetildeΘ(m_eff), in the effective scale given by endpoint-rank compression; a single fixed target, as in standard QA, admits an explicit polynomial-time learner with optimal Θ(log m_eff) regret, run on real NQ episodes. On Natural Questions, containment yields a large deductive gain plus a smaller learned gain on unresolved candidates, reproduced across two backbones and DPR hierarchies. Expected Search-space Reduction (ESR) turns these probabilities into decisions, localizing evidence in fewer verifier calls on SciFact, ERASER, and DPR hiera

ALT Parallel LLM agents tackle complex tasks by exploring multiple trajectories, yet useful discoveries remain isolated in individual execution histories. Existing sharing methods often select or summarize information before other agents' needs become clear, potentially overlooking details that become important later. We propose Ask on Demand (AOD), a communication framework that enables agents to seek targeted peer assistance when specific information needs arise. Upon an approved request, AOD retrieves relevant evidence from peer execution histories, selects a suitable peer, and generates a response tailored to the request. To determine when such assistance is worthwhile, we train a lightweight gate using paired team continuations, with supervision derived from final team outcomes and inference cost. Experiments on AppWorld and WebShop demonstrate that AOD consistently improves task performance over independent parallel execution while achieving lower inference cost than existing informa

ALT Choosing among the hundreds of thousands of available large language models (LLMs) requires a thorough understanding of each candidate model's properties. In practice, each property is measured by its own benchmark suite, so profiling a model on many properties means paying for many separate evaluations. To address this, model embeddings compress each model into a fixed-length vector from which many properties can be predicted. Existing methods, such as EmbedLLM, build these vectors from correctness patterns and question features, and often need large probe batteries to do so. However, many behaviors that are important when choosing a model, such as its verbosity, safety and style, show up more in how it answers than in whether it is correct. We introduce BULLPEN (Behavioral Understanding of Large Language models via Profile ENcodings), a framework that extends EmbedLLM in three ways. First, BULLPEN organizes the downstream tasks that prior work uses and adds 20 task benchmarks we buil

ALT Overly restrictive eligibility criteria contribute to widespread enrollment failure in clinical trials, yet published recommendations for how specific criteria should be broadened remain disconnected from trial design at scale. We introduce RECITE (Revising Eligibility Criteria Incorporating Textual Evidence), a framework for automated discovery, extraction, and implementation of evidence-based eligibility criteria revisions. RECITE uses protocol amendment documents from ClinicalTrials.gov to construct a dataset of 11,913 curated instances across 5,735 trials, each pairing original criteria with documentary evidence and target revisions. We benchmark fifteen LLM configurations under truncated-to-context-window and retrieval-augmented generation conditions, on a 3,116-instance sample under an LLM-as-judge protocol validated against ten domain experts (judge vs. human quadratic-weighted Cohen's κ_qw = 0.694 ± 0.096). The best open-weight model, Gemma 2 9B, achieves κ_qw-aligned ordinal s

ALT Length-aware scheduling reduces request latency in LLM serving by prioritizing shorter requests. However, despite their large model sizes, length predictors can suffer degraded ranking performance under domain and task shifts, and adapting them can require costly retraining. Their prediction overhead can further offset the benefits of scheduling. To improve the generalization and efficiency of length-aware scheduling, we propose LEAP, a length prediction system with fast online adaptation and asynchronous CPU execution. LEAP reuses the serving model's prefill hidden states, which contain information about the output length, and extracts this signal through a linear readout. To adapt to substantial domain and task shifts, it updates the readout at test time through recursive least squares, using completed requests as supervision without gradient computation or historical-data replay. Prediction and updates run asynchronously on CPU, while prediction and initial batch ordering overlap th

ALT Existing visual preference evaluation relies on costly human annotations or preference reward models, whereas online marketplace transaction prices are readily available and reflect real purchasing behavior, offering potential low-cost supervision. However, transaction prices conflate visual preferences with non-visual factors such as provenance, demand, and competition, making aggregate accuracy insufficient to distinguish model errors, unreliable price signals, and protocol confounds. To address this identifiability challenge, we introduce MarketImage, a diagnostic framework that identifies when transaction prices reflect visual preferences, where they fail, and whether multimodal language models can recover human-supported visual preference signals. MarketImage comprises three components: (i) MarketImageArt, 266 six-image comparison sets with transaction prices and price-blind human rankings; (ii) MarketImageLens, a tie-preserving protocol that partitions 3,990 within-set image pair

ALT Language-model agents now carry out long scientific work in biology, but their judgements about conventions, skills, errors, evidence and stopping are made inside the reasoning that does the work, where they cannot be measured, replaced or improved on their own. Here we present Operon-S1, a fast decision system, a System 1 for the agent, that separates judging from doing. A decision harness poses the agent's recurring judgements as closed questions at 13 decision points and acts only through fixed messages that never contain an answer, so any model that answers the questions can serve as the judge. Across seven life-science benchmarks, a local decision model took over these judgements in 0.6 s at the median for an in-loop request on CPU at no request cost, with no measurable change in the agent's score on five of six benchmarks, whereas the general language model that drives the agent, asked the same questions, accounted for 8.0% to 35.2% of task cost. Every decision is recorded with i

ALT Large language models increasingly generate structured outputs consumed by programs and downstream systems, where semantic correctness alone does not guarantee reliable execution. We introduce SERIAL-7, a Korean-English benchmark built around an executable verification framework for machine-verifiable generation across seven representations. Using 177 validated canonical artifacts, SERIAL-7 separates semantic derivation (Derive), constrained artifact generation (Realize), and cross-representation preservation (Preserve). Its 43 atomic representation constraints are paired with executable checks over format, structure, and task-specific semantics, enabling progressively stricter verification from representation compliance to full artifact validity. Across ten models, REALIZE-L3 HSR ranges from 42.0% to 93.9%, while Full Compliance exposes additional artifact-level failures beyond correct final answers and valid representations. These results show that reliable structured generation requ

ALT Subliminal learning, the transfer of a model's trait through data with no semantic trace of it, has been shown for students trained on a teacher's text. Post-training relies on group relative policy optimization with a language-model judge, where the student learns only from its own outputs and one judge's scores. We show this suffices: a student writes invented syllables or numbers, a judge made to prefer one animal scores them, and the student's preference moves toward that animal relative to a run whose judge prefers another. Of 48 design cells, two fail the validity gate and 17 establish the trait at 5% false-discovery rate, numbers-only cells included; elsewhere, our account gives the reason. Removing only the reward difference between judges removes transfer. We establish the principle as a chain of four stages: the trait must show in the judge's scores, favour strings that move the student, accumulate and reach the answers. Judges with the same preference built from other data,

ALT Answer-level rewards cannot distinguish reasoning traces with equally correct outcomes. We study whether auxiliary trajectory preferences improve small-language-model self-improvement and transfer under limited supervision. We compare confidence-based (SC) and entropy-based metrics (UID-Conj.), which combines global entropy variation and local smoothness, through online reward augmentation and offline training on correct responses. Online experiments adapt Qwen3-1.7B on 30 AIME problems without reference answers; offline experiments use historical AIME problems. UID-Conj. improves the online macro-average across the adaptation benchmark and three transfer benchmarks by 2.08 percentage points over unmodified TTRL. The strongest evidence comes from offline weighted SFT: UID-Conj. exceeds uniform weighting on the same response pool by 1.93 points, with a paired prompt-bootstrap 95% CI of [0.44, 3.44]. Benefits are task-dependent: SC rewards judged trace quality and instruction following,

ALT Learning-based approaches have increasingly been explored for SAT solving, with particular attention to improving branching decisions in conflict-driven clause learning (CDCL) solvers. These approaches derive branching guidance either from static structural properties of SAT formulas or from dynamic signals obtained through solver feedback and execution traces. However, these forms of supervision provide limited evidence about state-dependent branching effects, while different outcome measures may favor different branching choices. To address these limitations, we propose SAT-ACT, an outcome-derived learning framework for CDCL branching. We design three complementary outcome comparison criteria to extract action preferences from independent branching action rollouts initiated at the same solver state. The criteria identify preferences supported by the outcomes and leave comparisons unresolved when the evidence is insufficient or conflicting, instead of forcing an ordering using a prede

ALT Turning an engineering request into a simulation requires consistent geometry, physics, boundary conditions, and numerical settings. Recent agent-assisted systems automate simulation setup, but successful execution alone does not establish whether the specification preserves the intended problem or correctly handles missing information. We study whether agents can reliably construct complete executable JSON specifications for automated geometry creation, meshing, PDE solving, and result export. Our workflow combines model extraction with deterministic scientific and capability checks, explicit clarification, and validated local patches that preserve unrelated accepted fields. We evaluate specification correctness, execution completion, and numerical verification separately. On 120 template-related requests, the full workflow achieves 98.3% correct first-turn specification and decision outcomes, compared with 92.5% for schema-assisted single shot and 82.5% for model-only: gains of 5.8 a

ALT Training language-model agents to play long-horizon strategy games is hard because deterministic feedback is sparse and often arrives only at the end of a game. In-game scores can offer dense signals, but they do not reliably predict future outcomes: in 8-68% of position pairs across eight strategy games, the higher-scoring position leads to the worse outcome. We term this phenomenon scoreboard traps. In Freeciv, an open-source turn-based empire-building game where several players manage units, cities, and diplomacy over hundreds of turns, we look into better reward signals for gameplay agents. To facilitate this, we build CivHarness, an open system that saves current game states, branches on different decisions, and replays the game to future turns to provide measurable long-horizon feedback from saved positions. We use CivHarness to train CivTelescope, an LLM Judge that predicts which one of two game positions will yield the better outcome. On scoreboard-trap pairs, CivTelescope is 1

ALT Memory has become central to self-evolving LLM agents, which store and retrieve experience from past rollouts to guide future decisions. Existing systems represent this experience as free-form natural language and maintain it by rewriting, which fits tasks whose experience is narratable. However, in scientific discovery and optimization, experience is often a quantity measured by an oracle under a specific context. Rewriting it as text leaves no index for where a record should be, replaces a measurement with a description, and cannot express how interventions interact. To address this, we argue that agent memory for biomolecule optimization should instead be indexable, quantitative, and structured, and we introduce MEMIG. This memory construction framework realizes these three properties. In detail, MEMIG addresses each insight with a domain-grounded identifier and accumulates the quantitative effect measured by a property oracle, so that updates remain local and retrieval becomes an e

ALT Sparse MoE mechanism significantly improves the trade-off between model capacity and inference efficiency. However, practical deployment still requires storing all experts, resulting in substantial memory overhead. We show that expert outputs in MoE layers exhibit structured redundancy. Across different models and task categories, the stable rank and entropy effective rank of expert outputs are consistently far below the nominal number of experts, while expert output distributions also exhibit fewer effective modes. Motivated by these observations, we reformulate expert pruning as a structure-preserving expert subset selection problem and efficiently optimize it via a greedy strategy, rather than only independently scoring and ranking individual experts or exhaustively searching over expert combinations. We propose two expert pruning methods under the unified structure-preserving framework: Projection Energy Expert Pruning (PEEP), which preserves the functional subspace by maximizing w

ALT As Large Language Models (LLMs) become increasingly multilingual, distinguishing human-written from AI-generated text is essential for maintaining information integrity. However, research remains English-centric, with limited benchmarks for low-resource languages such as Hindi. To address this gap, we introduce SHAKTI, a large-scale Hindi benchmark covering four genres, eight LLM families, multiple prompting strategies, and adversarial transformations. We evaluate its quality through human annotation and analyze linguistic, grammatical, and sentiment-based differences between human- and AI-generated texts. Building on these findings, we propose TRIDENT, a round-trip translation-based detection framework with three variants: TRIDENT-S (static threshold), TRIDENT-D (dynamic threshold), and TRIDENT-C (logistic regression using multi-distance RTT features). TRIDENT leverages semantic consistency between original and round-trip translated texts to identify AI-generated content. Extensive ex

ALT Large language models offer a promising route to register-transfer-level (RTL) design, but reliable implementations require checking and revision based on electronic design automation (EDA) tools' feedback. Existing RTL-specialized models often lack learned interaction with such EDA tools or rely on separate generation and repair components. We introduce RTL-Interact, a multi-task post-training framework that trains a single RTL-specialized model to generate RTL, construct task-appropriate EDA checks, and revise implementations using tool feedback. The framework combines automatically constructed multi-task demonstrations with staged supervision from chain-of-thought to tool-integrated reasoning. We further introduce Pattern-Aware Policy Optimization (PAPO) for multi-task reinforcement learning. PAPO augments Group Relative Policy Optimization with correctness-gated rewards that favor concise successful checking while rewarding effective revision, and uses task grouping to preserve cov

ALT LLM-guided program evolution can produce mathematical constructions, but validity, generality, and reproducibility require distinct evidence. We develop a researcher-in-the-loop discovery pipeline that combines program evolution, exact evaluation, mathematical generalization, certified nonexistence checks, and formal proof checking. We apply it to entanglement-assisted quantum error-correcting codes (EAQECCs). Starting from tasks that did not specify a family formula, evolved programs produced finite qubit constructions whose structure researchers generalized to the family [[n,1,n-1;n-q-1]]q for prime powers q≥3 at n≥2q+1 and for q=2 at odd n≥5. Lean checks the algebraic certificate underlying this family. Together with entanglement lifting, the family closes 54 gaps in archived EAQECC tables. The released evidence includes 115 verified code records, ten nonexistence results with checked DRAT proofs, family implementations, and preserved search programs for exact checks and seeded repl

ALT The ability to integrate new information and deduce its consequences is central to learning, understanding, and reasoning in large language models (LLMs). Whether information arrives during training or in-context, models must not only store local facts, but propagate their long-range implications globally. To explore information integration in LLMs, we introduce two complementary natural language benchmarks for large-scale evaluation of deductive reasoning as a function of inference depth. The first is a formal graph benchmark enabling controlled evaluation over a wide range of graph topologies and integration tasks; the second is a knowledge composition benchmark grounded in real-world knowledge graphs. We use these benchmarks to compare knowledge integration from information encoded in context versus information encoded in model weights during pretraining, evaluating a set of open models implicitly, without chain of thought. We find that accuracy decays sharply with increased composi