Agregador

arXiv:2503.00128v2 Announce Type: replace-cross Abstract: Language models offer a way to scale costly, labour-intensive expert annotation, but their ability to reproduce expert judgements remains uncertain. This is particularly challenging in law, where annotators must distinguish the reasoning supporting judicial decisions from other legally relevant discussion. We present AnnoCaseLaw as a densely annotated benchmark comprising $471$ U.S. civil-negligence court opinions with more than $12,000$ expert highlights across five annotation categories. We evaluate proprietary frontier, open-weight, legal-specialised, and decision models on their ability to reproduce these annotations. Models perform better on Facts and Outcome than on Application of Law to Facts, Procedural History, and Relevant Precedents. On Application of Law to Facts, proprietary frontier models achieve the strongest balance of reasoning coverage and precision, while the open-weight model Gemma 4 achieves comparable Macro-F1 to proprietary frontier models at a fraction of the estimated inference cost. Our findings highlight the importance of evaluating annotation coverage and cost alongside aggregate scores when assessing the feasibility of automated legal annotation.

arXiv:2411.17983v2 Announce Type: replace-cross Abstract: We study data-driven score construction in conformal selection, which uses conformal p-values and multiple testing to select "interesting" instances with large unobserved labels from a pool of unlabeled data, while controlling the FDR in finite sample. While existing solutions require the score function to be constructed independent of the calibration and test data, it is desirable to select or construct powerful conformity score in a data-driven manner and to leverage all labeled data for score training when presented with many score choices and limited labeled data. We propose Optimized Conformal Selection (OptCS), a general framework that allows valid multiple testing after flexible data-driven score construction. We introduce general conditions under which OptCS constructs valid conformal p-values despite substantial data reuse and handles complex p-value dependencies to maintain finite-sample FDR control. We instantiate this general recipe to propose three FDR-controlling procedures, each optimizing the models differently: (i) selecting a powerful score function among multiple candidates, (ii) training the score with all labeled data without sample splitting, and (iii) combining full-sample training and model selection. We demonstrate the efficacy of our methods via simulation studies and real applications in drug discovery and large language models.

arXiv:2109.08644v3 Announce Type: replace-cross Abstract: We consider the problem of fairly allocating a set of indivisible goods to a set of strategic agents with additive valuation functions. We assume no monetary transfers and, therefore, a mechanism in our setting is an algorithm that takes as input the reported -- rather than the true -- values of the agents. Our main goal is to explore whether there exist mechanisms that have pure Nash equilibria for every instance and, at the same time, provide fairness guarantees for the allocations that correspond to these equilibria. We focus on two relaxations of envy-freeness, namely envy-freeness up to one good (EF1), and envy-freeness up to any good (EFX), and we positively answer the above question. In particular, we study two algorithms that are known to produce such allocations in the non-strategic setting: Round-Robin (EF1 allocations for any number of agents) and a cut-and-choose algorithm of Plaut and Roughgarden [SIAM Journal of Discrete Mathematics, 2020] (EFX allocations for two agents). For Round-Robin we show that all of its pure Nash equilibria induce allocations that are EF1 with respect to the underlying true values, while for the algorithm of Plaut and Roughgarden we show that the corresponding allocations not only are EFX but also satisfy maximin share fairness, something that is not true for this algorithm in the non-strategic setting! Further, we show that a weaker version of the latter result holds for any mechanism for two agents that always has pure Nash equilibria which all induce EFX allocations.

arXiv:2106.06060v5 Announce Type: replace-cross Abstract: Traditional competitive markets do not account for negative externalities; indirect costs that some participants impose on others, such as the cost of over-appropriating a common-pool resource (which diminishes future stock, and thus harvest, for everyone). Quantifying appropriate interventions to market prices has proven to be quite challenging. We propose a practical approach to computing market prices and allocations via a deep reinforcement learning policymaker agent, operating in an environment of other learning agents. Our policymaker allows us to tune the prices with regard to diverse objectives such as sustainability and resource wastefulness, fairness, buyers' and sellers' welfare, etc. As a highlight of our findings, our policymaker is significantly more successful in maintaining resource sustainability, compared to the market equilibrium outcome, in scarce resource environments.

arXiv:2610.26453v2 Announce Type: replace Abstract: Self-improving agents aim to continuously improve their behavior by learning from experience after deployment. However, accumulating and reusing more experience does not necessarily lead to better decisions, particularly when generation, interaction, and memory resources are jointly constrained. Under such stringent constraints, we find that several existing lifelong-memory methods provide limited benefits over simple retrieval or even no-memory agents. This reveals a fundamental challenge for resource-efficient self-improvement: agents must learn not only which past experiences are relevant, but which are actually worth reusing to improve future decisions. When memory capacity and opportunities for reasoning and recovery are limited, retrieving an ineffective experience can consume scarce resources and hinder downstream execution. To address this challenge, we propose TokenWorth, a lightweight feedback-driven memory adaptation framework that learns query-dependent memory worth from sparse execution feedback. Without updating the backbone model, TokenWorth uses the learned worth to guide both experience retrieval and bounded memory management, enabling the agent to continually adapt how it reuses accumulated experience. Across three LifelongAgentBench environments and both local and API-based deployments, TokenWorth achieves the highest task success rate while using the fewest output tokens among the evaluated methods under the specified resource budgets. These results suggest that effective self-improvement under resource constraints depends not on accumulating more experience, but on learning what is worth remembering. Our code is publicly available at https://github.com/AIGNLAI/TokenWorth.

arXiv:2610.26261v3 Announce Type: replace Abstract: RNA molecules often function through multiple experimentally observed conformational states. A central challenge is to capture ensemble diversity without sacrificing structural fidelity: samples may collapse toward averaged representative structures or drift into unsupported conformational regions. We introduce REFLEX (RNA Ensemble generation calibrated by FLEXibility), a sequence-conditioned generator for RNA backbone-frame ensembles based on a heteroscedastic stochastic bridge on SE(3). During training, experimental B-factors calibrate residue-wise bridge widths, exposing each observed conformer through local perturbation neighborhoods with residue-specific scales while keeping constrained regions sharper. A learned flexibility condition guides the bridge-field network to recover target conformer-specific frames from these calibrated noisy states. At inference, REFLEX uses only the input sequence, requiring no MSA-subsampling heuristics. On a multi-conformer RNA benchmark, REFLEX achieves the best precision-recall trade-off for ensemble coverage across evaluation thresholds, while recovery-stress ablations indicate gains in target-frame recovery under stronger perturbations.

arXiv:2610.25402v2 Announce Type: replace Abstract: Large language models (LLMs) have achieved strong performance across diverse reasoning tasks, yet it remains unclear whether this performance reflects an understanding of underlying logical structure or a reliance on shallow semantic cues. A key indicator of such understanding is whether models treat logically equivalent inputs consistently, producing the same predictions despite differences in expression. Through systematic evaluation on curated data, we show that even strong LLMs often fail this test: they do not consistently preserve predictions across logically equivalent inputs and generalize poorly to unseen logical forms. To address this limitation, we propose LoGIcal STructure-guided reasoning (LoGIST), a framework that guides LLM reasoning with explicit logical structure. LoGIST maps each input instance to a decision diagram, a directed acyclic graph that captures the underlying logical structure, and encodes this graph into a logical embedding that conditions the LLM's reasoning process. Across multiple training settings, LoGIST reduces inconsistency under logical equivalence and improves generalization to unseen logical forms, suggesting that logical invariance is a useful target for building more robust and generalizable logical reasoning in LLMs.

arXiv:2610.24899v2 Announce Type: replace Abstract: While LLM agents are increasingly capable of gathering and synthesizing evidence from a single homogeneous source, such as structured tables or unstructured data, real-world analytical questions frequently span heterogeneous sources. For example, answering one enterprise question may require both a result computed over an internal database and evidence found on the web. Recent evaluations on benchmarks like HybridDeepResearch show that even frontier agents struggle when evidence must cross this boundary. While these benchmarks have exposed the limitation, methodologies to explicitly teach cross-source reasoning remain absent. To address this, we introduce HybridResearcher, a 4B agent trained to bridge evidence across the structured and unstructured boundary. To build it, we synthesize cross-source bridge trajectories by starting with validated single-source tasks-such as existing text-to-SQL or web search queries-and fabricating the missing source around a bridge entity drawn from the seed's own output. We retain a sample only when strict construction gates confirm that neither side alone suffices, ensuring the data requires true cross-source interdependence. Finally, we train on this curated dataset using supervised fine-tuning followed by reinforcement learning. Evaluated on the existing HybridDeepResearch benchmark, HybridResearcher improves over our base model, Qwen3.5-4B, by 30.0 points pass@8 and surpasses the far larger Qwen3.5-397B-A17B by 8.3 points, while also improving over its base model on established, held-out single-source benchmarks (BrowseComp and BrowseComp-Plus), demonstrating that this complex cross-source reasoning can be taught directly to small models without triggering catastrophic forgetting.

arXiv:2610.24061v2 Announce Type: replace Abstract: As teams of AI agents take on larger projects and long-standing open problems, agent collaboration offers another dimension for scaling inference-time compute. To understand what makes such collaboration effective and scalable, we develop Software World, a framework for simulating multi-agent coworking in realistic software ecosystems. It comes with a pipeline to create environments of real, interdependent Python packages of different topics, sizes, and dependency structures, which we call software worlds. In a simulation, agents maintain packages in the world with a high-level goal of improving software efficiency, and they are free to discover tasks to work on and collaborate with others. We evaluate agents' work in a world collectively by measuring speedup in hidden dependent packages. The framework allows us to study different elements of collaboration by varying communication, ownership, and resource allocation. We run simulations in three different worlds, totaling more than 10,000 hours of agent work across eight models. Overall, performance improvement scales with inference-time compute, with the best model improving downstream efficiency by up to 31%. We show that most agents can find meaningful tasks via collaboration, but some frontier models can prematurely stop looking for improvements and make little progress. We release the simulation framework and traces to support future studies of agent collaboration at https://szj.io/sw.

arXiv:2610.23670v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) monitoring offers actionable evidence for oversight AI systems, with the potential to enable early detection and intervention. However, existing approaches are focused on specific tasks, whereas the regulation of AI, particularly reasoning models, requires monitoring a broader range of tasks. We introduce Factor for CoT monitoring, a strategy that supports customizing monitoring requirements in the prompt, which enables a single monitor to cover different tasks by relying on different factors. Furthermore, we introduce two types of factors, fine-grained and coarse-grained (e.g., monitoring whether a specific email address has been leaked versus monitoring privacy leakage), to accommodate diverse user monitoring needs. Based on this, we develop a CoT monitor named OwlSight that relies solely on factor to monitor behaviors related to multiple dimensions, including capability, safety, and trustworthiness. Experiments across 15,971 reasoning trajectories show that OwlSight surpasses general-purpose LLMs by 1.32-30.57 and 11.71-27.81 points at fine and coarse granularity, respectively, and achieves state-of-the-art results on OpenAI's CoT monitorability benchmark. It also generalizes to unseen models' CoTs and remains robust to Factor rephrasings, CoT compression, and obfuscation, offering a promising paradigm for CoT monitoring that can contribute to the oversight of frontier AI.

arXiv:2610.21591v2 Announce Type: replace Abstract: Machine learning (ML) for analog IC design is constrained by limited open data and the absence of standardized evaluation: results reported in different papers are typically obtained on bespoke, often closed, datasets and with ad-hoc metrics, leaving comparisons across methods unreliable. We address both gaps with a large opensource dataset and a suite of standardized benchmarks. The dataset contains more than 100 operational amplifier (opamp) topologies (1-, 2-, and 3-stage) in the SkyWater130 PDK, each shipped with structural and functional annotations, topology-specific sizing constraints (symmetry and sizing rules), an Ngspice testbench, and a multi-objective NSGA-II sizing run producing around 103 Pareto-optimal and 106 intermediate sizing-performance pairs per topology. On top of this data we define six benchmark tasks with precise protocols: inverse sizing, topology selection, sub-circuit classification, structural circuit generation, Pareto-membership prediction, and multi-objective optimization. Thus, the data presented here constitutes the most comprehensive dataset for ML development in over four decades of analog IC design automation. The dataset, ground-truth annotations, and reference implementations of the metric-defining routines are released under an open license, enabling reproducible and directly comparable evaluation across heterogeneous analog design automation methods.

arXiv:2610.21449v2 Announce Type: replace Abstract: Large language models (LLMs) can reason over both structured measurements and free-text records, which makes them attractive for emergency department (ED) prediction. However, most existing LLMs still fall short of conventional ML methods like trees on EHR-based prediction tasks. Our controlled analysis traces this gap to two weaknesses: LLMs do not select informative features, and they misjudge what numerical values imply for risk even when given the right features. We propose TIR-EC, a tool-integrated reinforcement learning framework that addresses both. TIR-EC exposes EHR feature groups as tools the LLM can call. It trains the LLM with rewards from a gradient-boosted tree teacher, which provides a reference set of informative tools and a graded risk target. TIR-EC also distills task-specific clinical skills into the model weights through a reverse curriculum that gradually removes the skills from the prompt during RL process. Evaluation on three clinical prediction tasks shows that our 4B agent achieves the highest macro F1 of all compared models, outperforms conventional ML baselines, and is competitive with much larger frontier LLMs. Further analysis shows that TIR-EC selects more useful evidence with fewer tool calls and combines measurements more effectively.

arXiv:2610.20926v2 Announce Type: replace Abstract: Agent skills turn procedural knowledge into reusable artifacts, allowing LLM agents to accumulate and refine expertise through experience. Building on this, skill evolution iteratively improves skills using execution feedback. However, improvement may require several interdependent edits, so low-reward versions can still be worth developing. Requiring immediate reward gains can discard useful partial repairs before their benefits emerge. Non-elitist evolution allows new versions to receive further edits despite scoring below earlier ones. For agent skills, this calls for evidence of what to preserve and repair next. We introduce SkillNEO (Non-Elitist Evolutionary Optimization for Agent Skills), which separately selects a version to use and versions to keep improving. Comparing how related versions perform the same task reveals working steps to preserve and remaining failures to fix. It can also revisit and revise earlier versions using later evidence. Across 86 SkillsBench tasks in eight domains, including software engineering and office work, SkillNEO raises GPT-5.4 Mini's average reward from 49.1% to 66.4%, within GPT-5.5 and GPT-5.6 Luna's original-skill range. Mini executes tasks, proposes revisions, and edits skills; final evaluation uses the same task instances. Gains span all eight domains. The same skills improve stronger models without further editing. On the 41 tasks with modified skills, reuse improves Luna by 10.5 percentage points and places GPT-5.5 10.6 points above its published original-skill reference. Execution records show these skills can benefit stronger models even when Mini still fails some task requirements. Search histories also show lower-scoring versions leading to skills ultimately selected for use. Together, these findings show that skill evolution can turn a weaker model's partial progress into reusable procedural knowledge for improving more capable agents.

arXiv:2610.18330v2 Announce Type: replace Abstract: Training business automation agents requires executable tasks that connect a natural-language request to an application state and a verifiable end state. Traditional Rubrics requires Authors to recreate application interfaces, initial records, policy evidence, and outcome checks for each task, entangling business logic with repeated infrastructure work. We introduce AssetForge, an asset-augmented task-construction pipeline that pairs a reusable construction-asset library with task-specific Rubrics. The assets provide application interfaces, world-state components, policy/evidence carriers, and native assertion definitions; the Rubric directs their instantiation for a particular business task. Executable checks and an additional model-based review validate each candidate, return targeted feedback, and support bounded repair before acceptance. On AutomationBench v1.0.6 public-600, fine-tuning Qwen3.6-35B-A3B on 6,000 AssetForge examples yields 41.17% on the official strict pass@1 metric, 4.4 times the 9.33% base score (+31.83 points). With the same backbone and GLM-5.3 supervision, AssetForge reaches 41.17% versus 30.33% for traditional Rubrics, a 10.84-point gain (35.7% relative) at the same accepted-example scale (6,000 versus 6,000 examples). Both DeepSeek- and GLM-supervised AssetForge models improve AppWorld completion over the base model on Test-Normal and Test-Challenge. These results establish the advantage of AssetForge's complete construction pipeline on AutomationBench public: the coupled asset-Rubric interface directs Authors toward business logic, while executable checks and model-based review validate their tasks.

arXiv:2610.17093v2 Announce Type: replace Abstract: A model diff credits post-training with whatever separates a base checkpoint from one post-trained descendant, presuming a rerun would land close by. On the sparse co-activation graph of Qwen3-1.7B it does not: two LoRA-SFT reruns sit over half as far apart as either sits from the base. We score each base-to-post contrast against the run-to-run band of its own recipe, and show that $k$ runs certify no better than $p=1/(k+1)$ under run exchangeability, however large the effect, so the band $z$-score is a descriptive scale. SFT leaves a large, reproducible signature: base $\to$ SFT displaces the graph by 17.8 pairwise-distance SDs beyond the mean distance between four independent LoRA-SFT runs, and the pre-registered estimator replicates on Llama-3.1-8B with Llama-Scope. At 29 steps each, four SFT and four DPO runs occupy disjoint displacement ranges, a gap $5.0\times$ and $5.6\times$ the spreads of the two arms, without any band. All bands use graphs built on one GPU architecture. Three other readings stop short of a verdict: DPO band counts (3/4, 1/4, 3/4 contrasts outside at 12, 29, 60 steps) show no consistent dose ordering while its displacement stays flat; light GRPO is a secondary non-detection, not an absence, and we run no equivalence test; and the graph concentration read as an RL signature is already in the zero-RL base. A pre-registered causal sweep at three edge budgets on 4,816 held-out prompts found the displaced sources load-bearing ($12\times$ a matched random control in mean, $3.5\times$ in median at 10,000 edges), but their stage-specificity interaction reversed at two budgets and the third failed its faithfulness gate, so we claim calibrated structural displacement, not a changed mechanism. Scope: one backbone, one SFT recipe and general-text probe states for the full protocol.

arXiv:2610.14489v2 Announce Type: replace Abstract: Reusable wearable PPG representations should capture local pulse morphology and broader physiological regularities. Existing pretraining objectives, however, usually apply supervision at the recording or pair level, overlooking that different concepts become reliable over different scopes of waveform evidence. We propose HiPPT, a physiology-grounded framework that matches each supervision source to its appropriate evidence scope. We construct a PPG-Text corpus of over 4 million wrist-worn recordings from 202K users, pairing recordings with waveform-derived morphology and metadata-derived context descriptions. HiPPT combines record-level morphology alignment, which grounds individual recordings in pulse characteristics, with cross-recording context alignment, which aggregates recordings sharing the same metadata tuple to capture context-consistent regularities. Waveform-guided text modeling further recovers masked contextual concepts from PPG patch representations, providing fine-grained waveform-text supervision. Across six downstream tasks spanning blood pressure, vascular stiffness, physiological attributes, and cross-dataset heart-rate estimation, HiPPT achieves the best result on the primary linear-probing metrics. The aligned space also supports zero-shot profiling of age group, sex, and BMI category, individually and jointly, with performance improving as more recordings are aggregated. These results show that evidence-scope matching yields transferable and semantically accessible wearable PPG representations. Code and pretrained weights will be released.

arXiv:2610.11399v3 Announce Type: replace Abstract: Many applications of language models require estimating the expectation of a test functional under the model. Obtaining precise estimates can be computationally expensive. We show how to improve estimation precision by exploiting next-token conditional probabilities available as a by-product of sampling. Our approach uses potentials: real-valued functions of prefixes that induce an additive decomposition of the test functional. We construct a family of estimators parameterized by these potentials and derive conditions for variance reduction. Across applications including entropy estimation, watermark detection, and rare-event probability estimation, our estimators achieve substantial variance reductions relative to Monte Carlo and importance sampling baselines at comparable computational cost.

arXiv:2610.10513v2 Announce Type: replace Abstract: Language-model agents are increasingly asked to carry out open-ended scientific research, yet their results are usually graded against a known answer, a rubric, or a language-model reviewer, none of which can tell whether a new scientific model is valid. The AI Science Exam for El Nino-Southern Oscillation (SciExam for ENSO) is a benchmark in which agents build low-order stochastic models of ENSO, the dominant mode of interannual climate variability, from real observations. Within a six-hour budget, agents process the observations, write their own diagnostics, which are then frozen, and develop a model using only these diagnostics as feedback. Hidden graders then test whether the model reproduces ENSO's statistics, recovers unobserved variables, and forecasts held-out years, and score a published model in the same way. Across twelve agent systems, six produce models that score higher than the published model, mainly through better reconstruction and forecasting. The simplified forms of the stronger models are each compatible with one of the two competing explanations of ENSO's warm-cold asymmetry, an open debate that the task never mentions. Controlled runs of the top system under varied information suggest that its scores do not come from recalling the dated observational record and that the information it receives shapes how it builds its model. SciExam for ENSO can thus evaluate agent research where no answer is known, and the results suggest that agents can already build competitive models whose structures bear on questions that scientists still debate.

arXiv:2610.06044v2 Announce Type: replace Abstract: Liquid-rocket thrust-chamber design involves interdependent analyses in which downstream constraints can require earlier design decisions to be revisited. Managing these dependencies across heterogeneous tools requires consistent design information and coordinated updates throughout the workflow. We present RocketAgent, a long-horizon engineering agent for multidisciplinary preliminary design of liquid-rocket thrust chambers. A single plan-owning Coding Agent coordinates engineering skills for performance sizing, subsystem optimization, geometry generation, and multiphysics assessment. A provenance-aware knowledge graph supports method selection, while a typed Design Intermediate Representation maintains shared parameters, artifacts, and decisions. Revision-aware checks invalidate affected results and block superseded inputs, with consequential changes subject to engineering approval. In a representative simulation-based design, RocketAgent continued from an infeasible cooling search through an engineer-authorized operating-point revision, identified feasible subsystem designs, and coordinated subsequent geometry generation and multiphysics assessment to support final configuration selection. Separate module tests assessed surrogate predictions and nozzle adaptation. A two-configuration comparison across three controlled scenarios verified the expected dependency invalidations and superseded-input blocking before solver execution. The representative case demonstrates sustained coordination across a multidisciplinary design workflow, while the controlled tests establish the behavior of the revision mechanisms supporting that execution.

arXiv:2610.03098v2 Announce Type: replace Abstract: Codon optimization, the process of selecting synonymous codons to improve mRNA translation efficiency and protein expression, is central to therapeutic protein production and mRNA vaccines, yet it remains a hard problem. The design space is discrete and combinatorially large, precluding gradient-based methods, and existing tools rely on heuristic proxies (e.g., Codon Adaptation Index or GC-content) that poorly capture true expression. We introduce Latent-Space Codon Optimization (LSCO), which recasts this discrete problem as a continuous one by mapping sequences into the latent space of a pretrained mRNA language model, enabling efficient gradient-based search. LSCO combines four components: a data-driven expression objective from an uncertainty-aware predictor, a Minimum-Free-Energy regularizer for structural stability, a naturalness prior from a protein-to-codon back-translation model, and constrained decoding for protein fidelity. On a real-world, wet-lab antibody expression dataset, LSCO outperforms simple frequency-based, as well as modern deep generative baselines in predicted expression, while retaining suitable biophysical properties.