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:2609.12116v1 Announce Type: new Abstract: Editing a knowledge graph embedding (KGE) model to promote a desired answer can displace correct answers from the returned list. Locality tests based only on facts that reuse the edited parameter can miss this ranking effect. We introduce a common rank-displacement audit at three scopes: facts supported by the edited parameter, other correct answers to the target query, and correct answers across queries with the same relation. We also derive dimensional and geometric conditions for an update to improve the target while exactly preserving selected scores. On FB15k-237 with DistMult and ComplEx, direct promotion always moves the target into the top ten, but does so without damage in only 23.0--23.2\% of edits. Strict preservation causes no measured damage, yet succeeds in only 1.3--1.4\%. Support-regularized entity editing gives the highest joint success, 36.3--37.7\%, while rank-truncated preservation reaches 32.8--34.7\% and reduces the mean number of displaced answers from about 14 to 1.2. Experiments across dimensions, scorers, ranking conventions, and a learned editor show that locality depends on both the protected scope and the editing mechanism. KGE editing should therefore report correction success together with the incidence and severity of rank displacement.

arXiv:2609.12265v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly asked to reason over structured data such as graphs, yet how reliably they can carry out multi-step graph algorithms in language remains unclear. Existing evaluations tend to use simple tasks on small graphs, to score code generation rather than reasoning over the graph itself, or to fix a single input format. We introduce Graph Theory Bench (GT Bench), a benchmark covering 24 classical graph problems in 44 task-structure settings, with over 100,000 examples across four representations: natural language, structured language, adjacency list, and adjacency matrix. Evaluating eight LLMs on GT Bench shows that accuracy is strongly tied to the input representation, that the best representation shifts with graph density, size, and topology as well as with the model, and that this sensitivity persists, attenuated, in the strongest reasoning models. Building on these observations, we propose the Graph Theory Agent (GTA), which pairs a preference-trained representation selector with plan-and-decompose scaffolding around a frozen executor LLM. GTA lifts Phi-4 from 53.5% to 69.1% on the benchmark's easy split and from 33.0% to 41.5% on its hard split, outperforming eight prompting and agent baselines, and transfers without retraining to GraCoRe and NLGraph. Code for benchmark generation and evaluation: https://github.com/xzx34/GTA. The project homepage is available at https://xzx34.github.io/gta/.

arXiv:2609.12304v1 Announce Type: new Abstract: Wrist-worn IMU has been widely used for daily-life health monitoring. Yet, it does not fully represent whole-body dynamics, for which the body center of mass (COM) is considered the physiological reference standard. Therefore, this work proposes a simplified kinematic model (KM), which is designed to map the wrist IMU to the COM acceleration. It is built upon several reductive assumptions that enable the solvability of the dynamic equations based on wrist IMU measurements alone. This work further proposes three types of hybrid AI modeling methods, namely human kinematic model-based neural network (HKM-NN) models, to leverage the power of both grey-box and black-box modeling. The HKM-NN methods include serial learning (ser-) and two approaches of simultaneous learning (sim1- and sim2-). The proposed models are trained and tested using our dataset, which includes wrist IMU measurements and ground-truth COM measurements from 10 healthy volunteers during six gait activities and sit-to-stand (SS) transitional movement. The results demonstrate the feasibility of estimating COM acceleration from wrist IMU measurements. Our KM model yields satisfactory results, with an error ranging from 6.7% to 12.5% for gait activities and 5.6% for the SS. In comparison with the KM model, our HKM-NN models significantly enhance the performance, achieving 5.3% to 9.3% errors for gait activities, and the best error of 3.9% for the SS. In addition, the HKM-NN models demonstrate distinct robustness characteristics under noisy test conditions, with sim1-/sim2- generally maintaining greater robustness under Gaussian perturbations, while the KM model exhibits comparatively strong robustness under salt-and-pepper noise. These findings highlight the importance of combining biomechanical structure with data-driven learning for wearable sensing applications operating under imperfect and noisy measurement conditions.

arXiv:2609.12320v1 Announce Type: new Abstract: Traditional large language models (LLMs) are scoped to individual user sessions, limiting their knowledge to a single conversation and preventing them from learning user preferences that evolve over time. Existing agentic memory systems address this limitation but generally operate at the individual-user level, restricting the public knowledge that could be shared across users to improve downstream responses. We introduce AIM (Agentic Interoperable Memory), a unified, privacy-aware memory framework that enables multi-agent, multi-user LLM systems to persistently manage private and shared memory. AIM dynamically classifies information as private, scoped to one user and inaccessible to others, or public, accessible to all users. It enforces index-level access controls so that private memories are retrievable only by their owner, protecting sensitive data while allowing beneficial shared knowledge to improve coordination and consistency. We also introduce MUMBench (Multi-User Memory Benchmark), a dataset of multi-user interactions containing private and shareable information across four domains. To our knowledge, MUMBench is the first public dataset designed to evaluate multiple memory operations, including retrieval, creation, update, and deletion, in a multi-user environment. Across three independent runs on MUMBench, AIM achieves 96.0% visibility classification accuracy, 58.8% strict operation accuracy, and 70.5% state-aware operation accuracy.

arXiv:2609.12394v1 Announce Type: new Abstract: Mobile GUI agents are shifting from multi-module frameworks to native models trained end-to-end, yet industrial deployment faces three persistent gaps. Sandbox training produces a distribution mismatch with production environments; expensive real-device failures remain underutilized; and fixed benchmarks saturate, losing the power to guide iteration. We present BlueLM-GUI, a 35B-A3B mobile GUI agent built as a real-device-centric flywheel that closes these gaps through three principles. Every Sample Matters: a dual-track pipeline with Heterogeneous Triple-System Consensus evaluation and an Error Correction \& Derivation Module salvages every trajectory into usable supervision. Every Rollout Is Real: a three-stage recipe---continual pre-training, supervised fine-tuning, and agentic reinforcement learning on hundreds of real phones---grounds every rollout in real production environments, so the capability the model learns transfers directly to deployment. Every Query Evolves: a quota-driven benchmark methodology with three orthogonal axes enables precise attribution and allows the benchmark to be systematically upgraded as the model improves. BlueLM-GUI achieves 87.4 on MobileGUI-VBench, surpassing the best closed-source model by 5.1 points, and 84.9 on AndroidWorld, the best result among open-source models and competitive with closed-source models. These results demonstrate that grounding model training and iterative improvement in both real devices and the three Every principles yields strong, robust, and transferable mobile GUI capability.

arXiv:2609.12395v1 Announce Type: new Abstract: Three-dimensional Gaussian Splatting (3DGS) combines explicit primitives with efficient rasterization, yet recent systems increasingly use neural networks to generate or share Gaussian parameters. We characterize this trend along five axes: attribute decoding, spatial sharing, view-conditioned decoding, topology generation, and amortized inference. An analysis of 19 representative methods shows that these choices address different limitations and cannot be reduced to a binary neural label. We also isolate three forms of neural parameterization in a controlled mip-NeRF 360 study. Sharing appearance and opacity improves reconstruction quality, while decoding geometric structure offers no further gain. The evidence favors selective neuralization: shared functions help when they capture reusable correlations without sacrificing the local geometric freedom of explicit splats.

arXiv:2609.12399v1 Announce Type: new Abstract: Generative recommendation (GR) relies on large-beam decoding to generate hundreds of candidate items, creating a new scaling challenge for recurrent linear attention. Existing linear attention serving systems either materialize a full recurrent state for every beam or repeatedly replay shared history, incurring substantial memory and traffic overhead. To address this, we present OneLA, a linear-attention decoding framework that exploits the shared prompt and short divergent suffixes of GR workloads. Specifically, OneLA represents all beam states using a single shared prompt-derived state and compact, append-only records of their divergent transitions. Using this representation, OneLA computes only the state information required at each decoding step, without reconstructing a full recurrent state for every beam. Furthermore, OneLA uses a lightweight ancestry index to track the transition records that make up each beam's history, allowing beams to be updated without moving or copying existing records. A fused GPU kernel further reuses the shared state across beams. Our analysis shows that OneLA achieves 1.54-2.46x end-to-end decode speedups while substantially reducing recurrent-state memory use and data movement.

arXiv:2609.12403v1 Announce Type: new Abstract: Cognitive Diagnosis Models (CDMs) play a pivotal role in personalized online learning. Traditional CDMs rely on discrete, ID-based embeddings to represent students, exercises, and concepts. This paradigm diverges from the nature of learner cognition, where knowledge is not stored and retrieved as isolated symbols. As a result, CDMs suffer from semantic limitations when new exercises or concepts appear. In this paper, we propose a Process-aware Language Cognitive Diagnosis (PLCD) framework that uses language-derived structures as cognitive priors and response records to calibrate student posterior states. PLCD leverages large language models (LLMs) to construct concept schemas and cognitive process graphs, and uses target-conditioned semantic memory to retrieve historical responses that are relevant to each target exercise. A process-grounded Language-to-Cognition Mapper with DA-MoE experts and process-level contrastive learning then maps the textual evidence into a unified cognitive space. Experimental results show that PLCD not only outperforms traditional baselines in predicting student performance but also exhibits strong cognitive transfer capabilities. These results connect the computational power of LLMs with the psychometric goal of measuring latent knowledge states, suggesting that structured language priors calibrated by response records can improve cold-start robustness and cognitive grounding.

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:2609.12422v1 Announce Type: new Abstract: Lux AI Season 3 requires agents to act under partial observability, randomized episode level dynamics, and a best of five match structure that rewards both tactical execution and fast adaptation. We present HORIZON, a hierarchical agent that combines symmetry aware spatial perception, dual memory belief tracking, relic centric graph attention, information gain driven exploration, and an opponent conditioned policy mixture. HORIZON separates short horizon control from cross match meta reasoning, while auxiliary belief and world model objectives stabilize learning. Trained with PPO in a large scale JAX simulator, the resulting agent explicitly infers hidden game parameters and opponent style. Experiments show consistent gains in match win rate, episode win rate, adaptation gain, and league rating over strong recurrent and feed forward baselines.

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:2609.12489v1 Announce Type: new Abstract: Test case synthesis is crucial for evaluating and ranking programs generated by large language models (LLMs). However, constructing high-quality test cases remains challenging because reliable expected outputs are often difficult to obtain. We propose Confidence-Gated Transductive Test Generation (CoTT), which first uses an efficient inductive procedure and invokes transductive generation only when inductive confidence is low. This adaptive design improves output reliability while allocating extra computation only when needed. On code reranking benchmarks, CoTT outperforms prior baselines across the reported metrics while reducing cost relative to applying transductive generation to every input. These results show that confidence-based allocation of test-time computation provides a favorable efficiency-effectiveness trade-off with a single efficient LLM.

arXiv:2609.12578v1 Announce Type: new Abstract: A compact controller can coordinate stronger experts by selecting whom to consult, formulating requests, and integrating their responses. We study whether learning from both the controller's decisions and the experts' reasoning and code improves its generation after expert removal. We introduce \textsc{Rivet} for \emph{collaboration internalization}: expert-augmented reinforcement learning applies a shared outcome signal to controller decisions and returned expert spans, and verified trajectory internalization consolidates complete successful interactions through format-aware supervised training. The deployed controller generates reasoning, code, and interaction structure with local Python execution and no external LLM. Across seven competition-mathematics benchmarks, RIVET-1.7B and RIVET-4B achieve average accuracies of $28.25\%$ and $44.16\%$; Stage~II improves RIVET-4B's accuracy after expert removal by $6.49$ points, and GPQA-Diamond results provide evidence of generalization to scientific reasoning. Ablations show gains from ordinary trajectory supervision and additional format weighting, supporting the effectiveness of training on the content and structure of verified collaborations.

arXiv:2609.12718v1 Announce Type: new Abstract: Hallucinations can undermine clinician trust in LLMs, making it important that evaluation methods capture clinically relevant errors. Rubric-based evaluation has become the leading approach for assessing LLMs in medicine, but it is unclear whether rubric scores reflect such errors. We first study this in a controlled setting using MedHallu, finding that more specific rubrics better distinguish correct from hallucinated responses. To test this systematically, we develop a taxonomy of medical hallucination types and a clinician-validated error-injection pipeline that creates matched correct and error-injected responses. Across HealthBench, HealthBench Professional, and LiveMedBench, our clinically relevant hallucinations are missed by rubrics, often leaving scores unchanged. We find that rubrics are most effective when explicitly checking facts, and are less effective for additional or unexpected errors they do not anticipate. A preliminary retrieval-based factuality check recovers some of the rubric-blind errors, suggesting a complementary approach. These findings reveal systematic blind spots in current medical evaluation of LLMs and suggest that rubric scores alone are insufficient to establish clinical reliability, potentially undermining clinician trust and confidence in clinical deployment.

arXiv:2609.12808v1 Announce Type: new Abstract: Unlearning benchmarks such as TOFU and MUSE certify forgetting by reading the model's final answer, where a model that refuses to answer already counts as having forgotten. We show that this model-level certificate does not transfer once the model is deployed as an agent. We introduce K-Bench, a benchmark that scores LLM unlearning under agentic deployment. K-Bench inspects all six channels a ReAct agent exposes, including its chain-of-thought (CoT), tool calls and tool observations, and elicited summary. A query counts as leaked if the secret appears in any of them. Each experiment places the secret in exactly one of the agent's three sources (the weights, the prompt, or the retrieval store). The K-Score is computed separately for each source and credits forgetting only when the agent remains usable. Clearing the answer channel does not make the secret unrecoverable. On structured retrieval, the secret stays verbatim in the tool-observation channel and the aggregate leak rate is unchanged. When the secret lives in the prompt or the retrieval store, TOFU and MUSE report no leakage, while the deployed agent still leaks it on 22--86\% of queries. When the secret is in the weights, none of the twenty evaluated published methods demonstrably removes it, and only an input-corruption intervention reaches selective forgetting under the evaluated observer. The top-ranked method changes across base models. A refusal-tuning method resists the evaluated extraction without verified knowledge removal.

arXiv:2609.12851v1 Announce Type: new Abstract: Medical benchmarks are dominated by single-turn, multiple-choice clinical cases that poorly reflect real consultations. Practically, clinicians elicit evidence interactively and patient communication varies widely. We introduce MedRoundsQA, a multi-turn diagnostic benchmark derived from 1,387 board-exam cases across 17 specialties. Each case is converted into a structured 24-slot clinical record, and then instantiated as controlled doctor-patient dual-agent dialogues under varying patient personas, with the underlying clinical content held fixed. We further classify cases by difficulty using model-based uncertainty to enable easy-to-hard analysis. Evaluations of fifteen LLM doctor agents show that (i) moving from a single-turn diagnosis on the standardized records to multi-turn consultations causes large degradations of roughly 13-39 points; (ii) more turns reliably improves question relevance, but diagnostic accuracy exhibits diminishing returns and typically plateaus after 6-12 turns; and (iii) patient persona differences can shift diagnosis accuracy by about 7-8 points (lowest to highest education), highlighting equity risks that single-turn benchmarks miss.

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:2609.13047v1 Announce Type: new Abstract: Humans organize knowledge into a taxonomy of concepts with nested levels of abstraction and a \emph{basic level} at which people recognize and name objects with the least cognitive effort. Cobweb is a classic cognitive account of this ability, an incremental learner that builds a probabilistic concept hierarchy by maximizing category utility. We argue that diffusion models, although designed for image synthesis, implicitly perform the same computation. The noisy marginals of a diffusion model are Gaussian smoothings of the data distribution, and the modes of these marginals form a hierarchy that corresponds to a Cobweb tree of probabilistic prototypes in four respects. Both are hierarchical density models, both are hierarchical-Bayesian models with Gaussian prototypes, both treat categorization as score-following that reduces uncertainty, and in both a basic level emerges. We locate this basic level for a diffusion model at an intermediate noise level, where recent analyses show that the reverse process commits to the class identity of a sample. The two models differ mainly in how they represent and learn the taxonomy. Cobweb learns a discrete tree incrementally, whereas a diffusion model encodes a continuous, interpolable hierarchy in a single learned score field fit to the data distribution. We test the correspondence on MNIST and Fashion-MNIST by recovering the diffusion hierarchy through mode-finding and comparing the basic levels of the two models. This reframes diffusion as a cognitive model of concept formation and offers Cobweb a continuous, scalable instantiation.