arXiv:2609.11977v1 Announce Type: new Abstract: Co-work agents execute complex workflows that combine information gathering, tool use, coding, and file manipulation across many model invocations. Because cost and latency accumulate over the full episode, their practical value depends not only on peak capability but also on how efficiently that capability is delivered. Yet many steps in everyday work emphasize state tracking, coordination, recovery, and follow-through rather than frontier-scale reasoning. We present Occamy-1.0, a cost-efficient co-work model obtained by further training the post-trained Qwen3.6-35B-A3B checkpoint. We construct execution-grounded data and environments, capture replayable long-horizon trajectories across multiple harnesses, and use staged post-training to develop and consolidate complementary execution capabilities. Across a broad suite of co-work benchmarks, Occamy-1.0 is consistently among the strongest comparably sized models and remains competitive with substantially larger frontier systems on several tasks. Under our stated evaluation and pricing protocol, its aggregate performance across four representative benchmarks places it at the low-cost knee of the observed cost--performance Pareto frontier. Supporting evaluations in tool calling, coding, and instruction following further show that this specialization preserves broad agentic capability. We release the model weights and a subset of the training data to support research on practical co-work agents and agentic post-training.

arXiv:2609.12373v1 Announce Type: new Abstract: Persona drift remains a central challenge for personalized language models, as user profiles evolve over long interactions rather than remain permanently fixed. Models must therefore revise persistent persona states when preferences genuinely change, while avoiding updates driven by transient, ambiguous, or unresolved observations. We propose CORE, which separates turn-local evidence from persistent persona-state revision and selectively updates grounded user preferences through uncertainty-aware belief revision. We also introduce PERSIST, a held-out post-anchor benchmark for persona-state robustness under sequential interaction stress, covering ambiguity, conflict, and controlled social influence. Across ALOE, PersonaChat, and PERSIST, CORE improves personalized alignment and robustness, with complementary gains in normalized closed-slot state fidelity. Human evaluation and mechanistic controls further support explicit update control beyond stronger generation or persistent memory alone.

arXiv:2609.12404v1 Announce Type: new Abstract: Learning from trial and error is a promising way to improve language agents on complex tasks such as computer control. Reflexion introduced verbal reinforcement learning, which turns failed trials into text that guides later attempts without updating model parameters. We introduce VRL-Bench, a harness for fair evaluation of trial-and-error learning under finite trial budgets. Across three models on MiniWoB and WebShop, we evaluate updates from several prominent verbal-memory methods spanning Reflexion and later work: each improves observed success over memory-free retry in some settings but reduces it in others. Replay experiments show that using reflection can reduce success rates, revealing a trade-off between exploiting experience and continued exploration. We propose VEX$^2$, a verbal exploration--exploitation scheduler that uses a language model to jointly select policies and allocate the remaining trial budget. VEX$^2$ is the only evaluated update to achieve positive observed success-rate gains over retry in all six settings.

arXiv:2609.12459v1 Announce Type: new Abstract: Open-ended reinforcement learning often relies on rubric-based rewards for tasks without directly verifiable answers. Yet the policy and reward system form a dynamic feedback loop: as the policy optimizes the current reward, an initially useful reward system may become unreliable due to reward hacking or reduced response discriminability. The reward system should therefore evolve rather than remain fixed during training. Existing dynamic-rubric methods adapt evaluation criteria, but reward failures can also arise from scoring mechanisms or signal composition. We introduce EvoRS, a self-evolving RL framework that evolves the reward system from on-policy experience, representing it as an executable Reward-DAG. Specifically, an agentic designer updates this system from on-policy rollouts and reward traces to maintain train-time reliability. Across writing and roleplay, EvoRS achieves the best quality under all three judges, outperforming the policy by \(2.107\) and \(4.767\) points, respectively, while reducing reward hacking and coverage failures and preserving reward informativeness. Ablations confirm that a comprehensive fixed reward system cannot remain reliable in open-ended tasks and must evolve throughout training.

arXiv:2609.12482v1 Announce Type: new Abstract: We aim to characterise the value of artificial intelligence in the workplace. Current studies largely measure this value in terms of the current automation capabilities and public adoption of AI. However, such metrics ignore the greater impacts of human--agent collaboration in transforming the nature of work. To account for this, we must expand the scope of our analysis beyond atomised tasks of today, and instead focus on how AI can augment entire workflows of the future. To ground this analysis, we establish a precise definition of AI augmentation comprising six conditions, spanning durable net value, meaningful human control, accountability and recovery, and long-term human development through learning, career pathways, and job purpose. We elaborate on these conditions and apply the framework in a case study of AI-mediated social surveys. We conclude by outlining how organisations, researchers, and government leaders can use this framework to make sense of the future of work.

arXiv:2609.12897v1 Announce Type: new Abstract: Multimodal model merging aims to consolidate task experts into a single model that retains their complementary capabilities. Most unimodal model merging methods combine expert updates within individual layers, and multimodal approaches largely follow this design. However, an expert update changes the representations passed to subsequent layers, allowing its influence to propagate across depth and affect how visual and textual information interact. When visual and language updates are combined, later updates act on inputs already modified by earlier ones, coupling their effects. This poses two challenges: (1) how to characterize the multimodal influence of individual expert updates across depth, and (2) how to jointly combine expert updates based on their multimodal influence. To address these challenges, we propose TAC-Merge for tracing and coordinating cross-layer influence in multimodal model merging. It contains two modules, i.e., multimodal influence mapping (MIM) and coupled merge control (CMC). MIM constructs graphs of update effects and uses Ricci curvature together with expert predictions to define a shared fusion objective. CMC models interactions among coefficient adjustments and jointly optimizes regional weights to synthesize one shared model. Experiments across diverse multimodal tasks demonstrate the effectiveness of TAC-Merge in consolidating complementary expert capabilities and supporting generalization to unseen tasks.

arXiv:2609.13009v1 Announce Type: new Abstract: Low reported scores on leading physics benchmarks, including those featured in the Artificial Analysis Intelligence Index (2026), suggest that frontier language models still struggle with advanced physics, a demanding test of their scientific reasoning and quantitative problem-solving abilities. Yet this impression does not always align with domain experts' experiences using these models in their work. We revisit these reported findings by evaluating frontier models on six widely used physics benchmarks and auditing them with experts, focusing on text-only problems with verifiable final answers. For each subfield of physics, faculty and graduate researchers with relevant expertise carefully review problem statements, reference solutions, and model responses to distinguish genuine model errors from grader errors, incorrect reference solutions, and ambiguous or underspecified questions. Most audited cases initially evaluated as incorrect reflect these benchmarking issues rather than errors in the models' physics reasoning. We then ask experts to address these benchmarking issues by correcting erroneous reference solutions and repairing or excluding flawed questions. We find that GPT-5.6-Sol's measured mean@4 rises from 47.3% to 78.7% on HLE-Physics and from 61.0% to 87.2% on CMT-Benchmark, while its corrected pass@4 reaches 94.4% on the 54 retained CritPt challenges. Corrected scores are computed on the retained evaluation subsets following expert review. Scores on the audited subsets of UGPhysics, PRISM-Physics, and PHYBench also rise substantially after correction. These findings suggest that current benchmarks substantially understate frontier models' ability to solve well-posed physics problems. Near-saturation on these closed-ended tasks highlights the need for more demanding, expert-validated evaluations.

arXiv:2609.13082v1 Announce Type: new Abstract: Agentic systems offer a promising way to automate embodied benchmark construction, but existing approaches typically cover isolated stages or remain specialized to predefined environments and task families. More importantly, multi-step construction produces dependent intermediate artifacts that are often passed downstream without artifact-specific verification, allowing local defects to propagate into the final benchmark. We present Embodied-BenchForge, an agentic framework that transforms user-specified evaluation intents into complete embodied benchmark artifacts. It formulates construction as Closed-Loop Benchmark Synthesis, integrating forward artifact synthesis with backward verification and repair. Skill-Orchestrated Artifact Synthesis composes typed and reusable skills into executable workflows, while an artifact dependency graph records intermediate outputs and their dependencies. Requirement-Guided Verification and Repair applies artifact-specific contracts throughout construction and uses provenance to trigger local re-execution or upstream rollback when verification fails. Embodied-BenchForge constructs six benchmarks covering diverse embodied scenarios in the Offline EQA Track, together with one interactive benchmark containing 220 executable tasks in the Interactive Embodied Track. Evaluations of representative MLLMs and embodied agents show that the benchmarks distinguish model capabilities in both observation-based understanding and closed-loop execution. Quality assessment and ablations validate benchmark quality and the effectiveness of verification and repair, while repair and skill-reuse analyses demonstrate efficient localized recovery and cross-benchmark reusability.

arXiv:2609.11559v1 Announce Type: cross Abstract: Large language models (LLMs) and AI-enabled software increasingly participate in systematic-review decisions, yet the information needed to audit these workflows is reported inconsistently. We analyze SciLitBench, a corpus of 888 review-automation papers with 14,726 annotations, to characterize changes in methods, review-stage use, evaluation and reported limitations. Automation has shifted toward LLM- and software-facing workflows, including stages that can alter the evidence base. Since 2023, 38.0% of software/product papers reported no evaluation, compared with 9.3% of LLM papers. Reporting coverage increased with LLM workflow complexity, yet 52% of positive-only LLM evaluations still reported an unmet reliability or performance requirement. From these patterns, we introduce PRISMA-LLM, an empirically grounded framework separating implementation disclosure from consequence-sensitive evaluation and limitation reporting.

arXiv:2609.12136v1 Announce Type: cross Abstract: Prequential adaptation of frozen tabular foundation models under temporal drift, with each label revealed only after prediction, helps some deployments and harms others, yet current practice does not predict which. We study the sources and limits of these gains. A diagnostic anatomy attributes gains to four recurring mechanisms under a streaming protocol that removes three optimistic biases and quantifies a fourth. Within an agnostic total-variation drift class, the target conditional is only partially identified: its identified-set diameter, the \emph{wall}, is irreducible from unlabeled data uniformly in sample size. A second, orthogonal $L^2$ projection wall quantifies what the frozen representation cannot express. Two canonical mechanism priors collapse the first wall. Under stated nuisance-rate conditions, the wall can be estimated from labeled historical windows at a $\sqrt N$ rate above the margin threshold $\gamma^\star=d_0/(2\alpha_s)$. At $\gamma=0$, the conditional lower-bound program depends on an open affinity estimate; the positive-margin lower branch also remains open. Semi-synthetic data illustrate the finite-sample mechanism with calibrated exponents. Stream-level proxies on eight industrial streams fall on the difficult side under a stated roughness bound, while the equality case $\gamma=\gamma^\star$ remains unresolved.

arXiv:2609.12154v1 Announce Type: cross Abstract: Distant speaker diarization remains challenging due to difficult acoustic environments, varying numbers of speakers and overlapping speech. Model-driven methods are proposed to exploit the speech source features in multi-channel recordings that help diarization. This paper generalizes a neural model that jointly learns to perform blind source separation and diarization over speech mixtures (neural FCASA) with heavy-tailed models. The popular Gaussian distribution has been applied for variance modeling in the original source separation model, which we replace with two families of heavy-tailed models (Leptokurtic Generalized Gaussian distribution and Student's t distribution) to better capture the heavy-tailedness in speech signals. Thanks to the Gaussian scale mixture model, we are able to unify the proposed method and the original one under the same form of learning objective. Our experiments show consistent large improvements in Diarization Error Rate (DER) and Jaccard Error Rate (JER) compared to the baseline on various corpora.

arXiv:2609.12184v1 Announce Type: cross Abstract: Experimental TCAD calibration is essential for predictive technology modeling of emerging oxide semiconductor transistors. However, it remains time-consuming and expert dependent because of model ambiguity. Multiple physical models and parameter sets can reproduce the same measured transfer characteristics, while local fitting alone cannot uniquely identify the underlying device physics. We present the first demonstration of an agentic TCAD calibration workflow for a fabricated bottom-gate In--W--O (BG-IWO) transistor. Starting from the measured transfer curve and device information, the workflow uses measurement--TCAD residuals and local sensitivity tests to select bounded parameter corrections or evaluate additional physical models, and accept only updates that improve device metrics. The LLM agent orchestrates the workflow, while Sentaurus governs the device physics. For the 2\%-W reference device, five agent-suggested updates yield a fixed calibrated model, reducing the multi-metric device objective $J$ by 14.3$\times$. Maximum $V_{\mathrm{th}}$/$I_{\mathrm{on}}$ errors are 36.1~mV/0.022 decade for varying-drain-bias tests and 46.2~mV/0.062 decade for varying-channel-length tests, demonstrating model transferability across bias and geometry rather than a local parameter fit. W-composition tests provide process-sensitive insight. This agentic workflow provides a faster route to model development for emerging device technologies.

arXiv:2609.12579v1 Announce Type: cross Abstract: On-policy self-distillation (OPSD) scores student-generated prefixes with a solution-conditioned self-teacher, yet transfers supervision only through next-token probabilities. We ask whether the aligned final-layer discrepancy offers a useful second channel, and how to test that channel without confusing its geometry with auxiliary strength. SCOPE-OPSD projects the privileged teacher-student residual onto a frozen rank-64 factor estimated from residual covariance and language-model-head Fisher sensitivity. It reuses the forwards already required by OPSD and adds neither rollouts nor inference-time modules. A matched Random control preserves the structured factor's rank and nonzero spectrum and uses per-arm gradient-RMS calibration, isolating the effect of the data-dependent orientation. Across the complete 25/50/75/100-step trajectories for Qwen3-1.7B, 4B, and 8B, Structured is never below Pure OPSD, with strict gains in 11 of the 12 model-checkpoint combinations and an exact tie at 4B step 25. Structured also exceeds matched Random in 10 of the 12 combinations. At step 75 on Qwen3-1.7B, Structured exceeds matched Random by 1.39 Macro Avg@12 points in each of two independent training reruns. A cross-fitted diagnostic also shows 4.40 times greater held-out privileged-gap capture than the matched random orientation. The results support a compact, Fisher-conditioned privileged subspace for short-budget OPSD.

arXiv:2609.12896v1 Announce Type: cross Abstract: LLM-based agents rely on heterogeneous interaction capabilities to accomplish complex tasks. Existing approaches often distribute these capabilities across multiple LoRA adapters, which increases adapter storage requirements and introduces routing overhead during inference. A single LoRA avoids this overhead, but learning from diverse agent trajectories under a fixed rank budget presents two challenges. First, trajectories with different interaction traces and parameter gradients can induce equivalent changes in decision distributions, causing repeated updates to overemphasize redundant behavioral changes. Second, an aggregated update may exceed the rank budget of the adapter, and approximating it in weight space can distort the decision changes that it is intended to produce. We propose BQ-LoRA, a low-rank adaptation framework that organizes trajectory updates through a local behavior quotient manifold. It contains two modules, i.e., behavior quotient balancing (BQB) and decision preserving compression (DPC). BQB constructs the quotient manifold from decision distributions and reweights trajectory update directions according to their local density in the quotient tangent space. DPC projects the balanced gradient onto the intrinsic fixed rank tangent space and refactorizes the resulting target by jointly controlling effective weight error and distortion of decision distributions. Experiments on AppWorld and BrowseComp-Plus compare BQ-LoRA with standard LoRA and recent low-rank adaptation methods, while separate ablations evaluate the complementary contributions of both components.

arXiv:2607.19363v3 Announce Type: replace Abstract: Rotary Position Embedding (RoPE) is widely adopted in Transformers to encode positional information, yet standard implementations enforce a uniform frequency schedule and scaling across all attention heads. Using simplified retrieval tasks and length generalization scenarios, we show -- both empirically and theoretically -- that heads with different functional roles require distinct frequency ranges and attention scaling factors to operate effectively. Ignoring this structure leads to suboptimal utilization of embedding dimensions and degraded performance, particularly under long-context settings. To address these limitations, we propose AdaRoPE, which equips each attention head with learnable rotation frequencies and attention scaling factors. Pretrained LLMs with AdaRoPE consistently outperform existing RoPE variants, including partial RoPE and NoPE baselines. For context extension, we further show that uniform frequency and attention scaling, used in methods such as YaRN, are suboptimal. By applying head-specific scaling, AdaRoPE enables better context extension while better preserving short-context performance in both the extrapolation setting and the long-context continued pretraining setting. These results highlight the importance of optimizing rotary position embedding at the level of individual attention heads.

arXiv:2609.03753v3 Announce Type: replace Abstract: Cumulative culture enables humans to preserve, reuse, and extend knowledge and skills across experiences and generations. Inspired by this principle, we introduce \textit{SimSkill}, a self-evolving agent built around the Simulation of Urban MObility (SUMO) traffic simulator. SimSkill continually identifies capability gaps, generates and solves environment-grounded tasks, verifies solutions through an action--critic loop, and consolidates experience into episodic, procedural, and semantic memory. Through autonomous exploration, it builds a library of reusable skills and knowledge spanning major stages of the traffic-simulation workflow. We evaluate SimSkill on two held-out benchmarks across three backbone LLMs, with each result independently verified. It improves verified success by up to 25 percentage points, and ablations show complementary contributions from procedural and semantic memory. Its benefits remain backbone- and budget-dependent, as memory does not improve every model or uniformly reduce inference cost. More broadly, SimSkill illustrates a natural-language-centered design paradigm for LLM-based agent systems. Its high-level control logic, operating principles, and accumulated knowledge are expressed in natural language, while an LLM integrates them with executable tools and code to realize precise and reproducible execution. All code and experimental data are publicly available at https://github.com/qiliuchn/SimSkill-V1.

arXiv:2609.11318v2 Announce Type: replace Abstract: Deep research agents are increasingly capable of web search, tool use, multimodal evidence analysis, and information synthesis. However, existing benchmarks mainly evaluate medium-horizon exploration and rarely test whether agents can sustain long, dependency-heavy research processes. We introduce Mr. LHDR (Multimodal real-world Long-Horizon Deep Research), a benchmark for evaluating real-world deep research over long, irreducible chains of interdependent evidence across eight categories. Each question is constructed from a hidden Node-Relation graph and requires an average of 12.1 necessary intermediate conclusions with a mean dependency depth of 10.4 before reaching a short, unique, and verifiable answer. Questions incorporate multimodal evidence, including images, maps, PDFs, logos, charts, tables, and video frames, with at least one non-text element that changes the reasoning state. Mr. LHDR evaluates both final answers and the correctness of intermediate conclusions under annotated dependencies. We evaluate general models, deep research systems, and agent frameworks using Overall Accuracy (OA), Strict Accuracy (SA), Checklist Score (CS), and Dependency-Aware Checklist Score (DACS). Results show that even the strongest system achieves only 43.1% OA and 34.3% SA, indicating that final-answer accuracy substantially overestimates complete research success. Removing images reduces DACS by 12.6 points, demonstrating the importance of multimodal evidence, while SA consistently declines as reasoning chains become longer. These findings reveal sustained, dependency-consistent evidence integration, rather than isolated fact retrieval, as a key bottleneck for current deep research agents.

arXiv:2502.14043v4 Announce Type: replace-cross Abstract: Most learning algorithms with formal regret guarantees essentially rely on trying all possible behaviors, which is problematic when some errors cannot be recovered from. Instead, we allow the learning agent to ask for help from a mentor and to transfer knowledge between similar states. We show that this combination enables the agent to learn both safely and effectively. Under standard online learning assumptions, we provide an algorithm whose regret and number of mentor queries are both sublinear in the time horizon for Markov decision processes with irreversible dynamics and infinite state spaces. Our proof involves a sequence of three reductions, making our result more general than a single algorithm. Conceptually, our result may be the first formal proof that it is possible for an agent to obtain high reward while becoming self-sufficient in an unknown, unbounded, and high-stakes environment without resets.

arXiv:2511.07318v3 Announce Type: replace-cross Abstract: Despite substantial advances, large language models (LLMs) continue to exhibit hallucinations, generating plausible yet incorrect responses. In this paper, we highlight a critical yet previously underexplored class of hallucinations driven by spurious correlations -- superficial but statistically prominent associations between features (e.g., surnames) and attributes (e.g., nationality) present in the training data. We demonstrate that these spurious correlations induce hallucinations that are confidently generated, immune to model scaling, evade current detection methods, and persist even after refusal fine-tuning. Through systematically controlled synthetic experiments and empirical evaluations on state-of-the-art open-source and proprietary LLMs (including GPT-5), we show that existing hallucination detection methods, such as confidence-based filtering and inner-state probing, fundamentally fail in the presence of spurious correlations. Our theoretical analysis further elucidates why these statistical biases intrinsically undermine confidence-based detection techniques. Our findings thus emphasize the urgent need for new approaches explicitly designed to address hallucinations caused by spurious correlations.

arXiv:2609.09625v1 Announce Type: new Abstract: As Digital Twin (DT) systems evolve beyond state synchronization toward task-oriented and knowledge-driven operation, Cognitive Digital Twins (CDTs) have emerged as an extension that incorporates cognitive capabilities into twin operation. Existing CDT studies often focus on specific enabling techniques, such as learning modules, knowledge graphs, and large language models, while providing limited insight into how cognition can be systematically integrated into DT architectures. To address this issue, this paper proposes a four-layer CDT architecture consisting of the physical layer, digital-twin layer, cognitive layer, and task layer. The proposed architecture establishes a self-evolving closed operational loop spanning these four layers, in which physical states are synchronized into digital representations, cognition constructs task-specific cognitive models through knowledge, memory, and attention, and task-level decisions are generated under practical constraints. Operational feedback further refines cognitive experience and updates relationships and annotations in the digital representation, enabling subsequent task interpretation, initiation, and reasoning to evolve with system operation. Based on this framework, two representative operation modes are characterized: user-request-driven cognition and self-driven cognition. We further discuss key enabling mechanisms and deployment challenges associated with semantic communication, knowledge querying, task orchestration, and closed-loop synchronization. A lightweight simulation study illustrates reliable closed-loop task feasibility under limited semantic information and improved operational efficiency through accumulated task experience. The proposed framework provides a structured foundation for the design and development of future CDT systems.