Search arXiv⌕ Search

arXiv subjects

Xiaodong Liu

Publications and source records attributed to Xiaodong Liu.

At least 19 recordsLinked to original sources
arXiv2026

SEMA-Auto: Sighted and Efficient Multi-Turn Attack with Autonomy

Existing jailbreak attackers fall into two classes: static planners fix their single- or multi-turn adversarial plans in advance, remaining simple but losing sight of the victim's replies, wasting turns and limiting transferability; interactive generators read each victim reply to generate the next-turn attack but require in-loop evaluators for success signals or hints, incurring substantial costs and inflated performance. Bridging this gap, we propose SEMA-Auto, a sighted and efficient multi-turn attacker with autonomy, interacting with the victim model and terminating the session by itself upon success. To stabilize its behaviors and boost its capabilities, SEMA-Auto is trained in two stages. Synthetic bootstrap tuning installs the notion of attack targets and conforming decisions by fine-tuning the base model with bootstrapped trajectories. Decision-supervised reinforcement learning then optimizes two objectives jointly yet separately, reinforcing the attack with higher jailbreak reward while supervising the decision at each turn against an absolute target. Our method achieves state-of-the-art (SOTA) attack success rates (ASR) across multiple datasets, victims, and judges, outperforming all static and interactive baselines, within almost the fewest turns, demonstrating both effectiveness and efficiency. For example, SEMA-Auto performs a $76.0\%$ ASR@1 within an average of $3.0$ turns against DeepSeek-V4-Flash on AdvBench, while the best static baseline is $54.8\%$ with fixed $7$ turns and the best interactive baseline is $43.8\%$ in $3.7$ turns. Against safety-hardened frontier models, GPT-oss-120B, GPT-5.4, Claude-Haiku-4.5, and GPT-6-Astra, our counter-trained attacker achieves an average $59.6\%$ ASR@1 on HarmBench, $13.8\%$ over prior SOTA. Our code is available at: https://github.com/microsoft/SEMA

cs.CL↗
arXiv2026

CoCarry: Contact-Support-Structured Retargeting for Dual-Humanoid Cooperative Carrying

Recent advances in large-scale human motion data, motion retargeting, and motion imitation have enabled increasingly capable whole-body control for individual humanoids. Cooperative carrying is more challenging because successful coordination requires not only plausible individual motions, but also consistent cross-agent and agent-object relations, including shared grasp, relative configuration, and whole-body support. We introduce CoCarry, a cooperative-carrying dataset containing 220 synchronized two-person sequences across 21 task schemes, five shared-object geometries, four terrain types, and approximately 61 minutes of motion. We further propose Contact-Support-Structured Retargeting, which starts from nominal individual motions and jointly refines both humanoids around the same prescribed object trajectory. Cooperation-aware object-local hand anchors preserve compatible four-hand grasp relations, while complementary upper object-interaction and lower support structures retain object-relative geometry and coordinated support. Across all 220 CoCarry sequences retargeted to two A3 humanoids, our method achieves 0.9995 contact preservation, reduces penetration duration by 67.0% and 71.0% relative to GMR and OmniRetarget, respectively, and maintains a 100% retargeting success rate. On CORE4D with Unitree G1 humanoids, it achieves 0.9906 contact preservation with zero measured sliding. We further validate the generated references through physics simulation and multiple real-world cooperative carrying experiments on two physical A3 humanoids, demonstrating their usability for downstream dual-humanoid control.

cs.RO↗
arXiv2026

Post-perihelion dust activity and a candidate icy-grain halo in long-period comet C/2023 A3 (Tsuchinshan--ATLAS)

We analyze the post-perihelion coma of the Great Comet of 2024, C/2023 A3 (Tsuchinshan--ATLAS) to characterize dust activity and assess the contribution of sublimating icy grains to a candidate near-nucleus halo. Using archival Zwicky Transient Facility images from 15 February to 26 May 2025, we performed aperture photometry within a fixed projected radius of 40,000 km and derived azimuthally averaged surface-brightness profiles. The comet faded from 12.86 to 14.77 mag as heliocentric distance increased from 2.64 to 3.90 au, with two short-lived brightenings. The effective dust cross section decreased by a factor of 2.4, following $C_{\rm e}\propto r_{\rm h}^{-3.1}$, while the dust mass production rate scaled as $\dot{M}_{\rm d}\propto r_{\rm h}^{-3.41}$, consistent with a contribution from water-ice-driven activity. Extrapolating the fitted relation to perihelion implies a model-dependent cumulative dust mass loss of $3.0\times10^{11}$ kg, equivalent to a globally averaged erosion depth of $\sim1.4$ m for an assumed nucleus radius of 5.9 km. Coma profiles were shallower than the canonical steady-state expectation, suggesting radial changes in dust distribution or scattering properties, possibly due to delayed aggregate fragmentation. A persistent central brightness excess, coincident with less-red inner-coma colors, is consistent with an icy-grain halo. Among the models explored, icy grains of radius $\sim10~μ$m with carbon fraction $\sim0.1\%$ yield halo radii comparable to those observed during enhanced activity on 21--25 February 2025, with grain lifetimes of $2.8\times10^5$--$3.2\times10^5$ s. No single fixed grain size and composition reproduces the full halo evolution; an increasing carbon fraction could explain the broad halo-radius trend, possibly reflecting progressive refractory enrichment of near-surface material.

astro-ph.EP↗
arXiv2026

Dust Activity Evolution and Constraints on Icy Grains in the Interstellar Comet 3I/ATLAS

We present Zwicky Transient Facility observations of the interstellar comet 3I/ATLAS to characterize its dust-activity evolution before and after perihelion. Before perihelion, the effective scattering cross section $C_{\rm e}$ brightened across the inner $2\times10^4$ km as $C_{\rm e}\propto r_{\rm H}^{-γ}$, with $γ$ increasing from $1.63\pm0.14$ to $1.88\pm0.34$ with aperture size. After perihelion, the heliocentric index decreased from $2.44\pm0.09$ in the $5\times10^3$ km aperture to $1.54\pm0.09$ in the $8\times10^4$ km aperture, indicating faster fading of the inner coma. Under adopted grain-size and residence-time assumptions, the implied dust mass-loss rates are $\sim123$--$203~{\rm kg~s^{-1}}$ before perihelion and $\sim596$--$1412~{\rm kg~s^{-1}}$ after perihelion. The morphology yields a sunward ejection-speed scale of $v_{\rm ej}\sim(190\pm3)a_{μ{\rm m}}^{-1/2}~{\rm m~s^{-1}}$ and an effective perpendicular velocity of $v_\perp=(79\pm6)a_{μ{\rm m}}^{-1/2}~{\rm m~s^{-1}}$. Post-perihelion surface-brightness profiles transiently steepened to $k\sim-2.7$ in late November and early December, then became shallower and approached $k=-1.5$ by January. Matched $g-r$ profiles show that this phase coincided with an anomalously blue outer coma that disappeared by January. We characterize the fading component with a projected destruction length of $\ell_{\rm DE}\sim(6.4$--$7.2)\times10^4$ km. Thermophysical sublimation calculations indicate that this scale, together with the order of magnitude of the water production near the main imaging epoch, is consistent with $a_0\sim5$--$10~μ{\rm m}$ icy grains containing a small absorbing carbonaceous fraction of $f_{\rm C}\sim0.1\%$. These results suggest that the early post-perihelion coma likely contained a short-lived, volatile-bearing icy-grain component whose fading contributed to the outer-coma brightness and color evolution

astro-ph.EP↗
arXiv2026

AgentCIScope: Grounded Contextual Integrity Evaluation for LLM Agents

LLM agents are becoming increasingly capable of handling daily workspace tasks by interacting with application environments through tool calls. However, as agents read and write sensitive user data across email, documents, and other applications, a central privacy question is whether they preserve contextual integrity (CI), that is, whether the information flows they produce comply with context-specific disclosure constraints. Existing work either focuses on model-level privacy leakage or evaluates agents in limited application environments with manually constructed disclosure constraints. In this work, we introduce AgentCIScope, a unified platform and benchmark for evaluating agent-level contextual integrity through executable, multi-step tasks across diverse, realistic application environments. AgentCIScope transforms public and synthetic privacy cases into executable agent tasks, with disclosure constraints grounded in three criteria: governing privacy policies, persona-based agreement, and a predefined sensitive-attribute taxonomy. Based on AgentCIScope, we evaluate 12 agents on 936 tasks and find that strong task-completion capability does not guarantee contextual-integrity preservation: single-run leakage rates range from 32.5% to 94.4%, while repeating each task five times further increases leakage by 4-19 percentage points. Leakage varies substantially across attributes: personal preferences and booking details have average leakage rates of 84.7% and 76.5%, compared with 17.1% for credit-card information and 29.4% for SSNs; environments: calendar has the highest average leakage rate as an information source, while WhatsApp ranks highest as an information destination; and governing privacy policies. AgentCIScope provides deep insights into agent privacy leakage and serves as a unified testbed for developing privacy-preserving agents.

cs.AI↗
arXiv2026

LLM-based User-Product Relevance Evaluation for Dynamic Product Advertising

Dynamic Product Advertising (DPA) retrieval systems are a core component of modern e-commerce advertising; however, their evaluation remains challenging. Conventional offline engagement metrics are limited by sparse, biased feedback, while online evaluation is costly and time-consuming. In this work, we propose a user--product relevance metric for offline evaluation of DPA retrieval systems. The metric first compresses the engagement history into a compact set of intent representatives via Semantic-ID-grouped, event-stratified segmentation, then assesses the relevance of a recommended product to each individual intent and aggregates them as a user-level relevance score, yielding a stable and interpretable measure of retrieval quality. To compute this metric at scale, we leverage large language models (LLMs) as semantic relevance judges, capturing nuanced functional and semantic relationships that heuristic methods often miss. We propose an agentic, human-aligned prompting framework that generates multi-category relevance guidelines and distills teacher-model judgments into an efficient student model for scalable evaluation. The resulting metric strongly correlates with offline and online business metrics, enabling faster and more reliable DPA retrieval iteration before A/B testing.

cs.IR↗
arXiv2026

The Interior Inverse Scattering Problem from Backscattering Data: Spectral Comparison and Uniqueness Results

We study an interior inverse scattering problem for the two-dimensional Helmholtz equation with backscattering data, where the source and receiver coincide. Such data are common in applications, yet existing uniqueness results are almost exclusively established for full multistatic data with separated sources and receivers. We consider two main measurement regimes. In the first regime, data are collected on a closed curve inside the unknown domain. Exploiting the meromorphic dependence of the backscattering field on the wavenumber, we show that the residues at the poles determine the diagonal of the spectral projection kernel on the curve, and hence the \emph{visible} part of the Dirichlet spectrum. This yields an unconditional spectral comparison: the symmetric difference of the two Dirichlet spectra is contained in the spectrum of the interior domain enclosed by the curve. If, in addition, the common visible eigenvalues have either matching multiplicities or matching restriction ranks, we obtain an area estimate bounding the discrepancy of the two domain areas by the area of this interior domain. In the second regime, data are given on a nonempty open subset of the domain, and a single non-resonant frequency already uniquely determines a bounded connected Lipschitz domain. The proof combines interior real-analyticity of the regular part of the Helmholtz Green function with its boundary blow-up.

math.AP↗
arXiv2026

DeepSeek Elastic Compute (DSec): A Sandbox Infrastructure for Effective Agentic Training at Scale

Large-scale agentic training and evaluation with large language models (LLMs) rely on isolated, stateful execution environments in which models inspect repositories, invoke tools, execute commands, and interact with task-specific services. These workloads create sandboxes in large bursts, span heterogeneous functionality and isolation requirements, retain state across long interactions, and draw from large image corpora with limited reuse. Supporting them therefore requires an elastic execution platform rather than a single sandbox runtime. This report presents DeepSeek Elastic Compute (DSec), a production sandbox platform that exposes FnCall, container, microVM, and full-VM sandbox backends through a unified SDK. DSec coordinates placement and lifecycle management across the cluster, composes environments from independently versioned layers, combines memory sharing, reclamation, and CPU scheduling for high-density execution, and loads image data on demand from Fire-Flyer File System (3FS), a cluster-wide distributed filesystem. DSec is co-designed with the reinforcement learning (RL) framework, decouples stateful rollout execution from preemptible GPU training, coordinates sandbox lifecycle with training to preserve rollout state while reclaiming idle resources, and mitigates agent misbehavior such as reward hacking. A single production-scale unit of DSec spans around 160 nodes, serving about 3 million sandboxes per day; in production, it supports over 380,000 concurrent sandboxes and sustains over 5,000 sandbox creations per second. Our evaluation and deployment experience show that these mechanisms reduce environment setup and image-distribution overhead, improve memory efficiency, and preserve latency-sensitive performance under high-density overcommit.

cs.DC↗
arXiv2026

Register Tokens for Bounded-State Reasoning in Diffusion Language Models

Masked diffusion language models (dLLMs) generate text by iteratively denoising masked tokens with bidirectional attention. Extending reasoning across generation chunks normally requires keeping earlier generated text in context. We ask whether a dLLM can instead continue reasoning after that text is cleared, using only a fixed-size carried state. We implement this state as a small number of register tokens: dedicated fixed-position tokens whose continuous hidden states are trained to carry reasoning progress across generation chunks. We post-train dLLMs to decode a chunk of text, clear it while preserving the register values, and continue decoding from the prompt and carried state. In our main comparisons on LLaDA and Dream, registers outperform discrete-text carry on every benchmark, with gains of up to 8.5 points on math and 19.5 points on code. Registers are especially effective for bounded code generation, where correct programs usually span several chunks. Finally, registers can be further refined with reinforcement learning on long-horizon reasoning tasks.

cs.CL↗
arXiv2026

Reinforcement Learning over Patient Trajectories for Clinical Reasoning in EHR Foundation Models

Electronic health record (EHR) foundation models trained on longitudinal patient trajectories have demonstrated strong performance across diverse clinical prediction tasks. However, their clinical reasoning capabilities remain constrained by next-token prediction on limited and incomplete EHR data. To address this, we propose a reinforcement learning (RL) fine-tuning framework that treats EHR foundation models as generative policies over patient trajectories. We formulate common clinical prediction problems (e.g., hospital readmission) as event-conditioned, time-windowed reasoning tasks. We then design time-aware, rollout-sensitive rewards to account for finite rollout lengths and temporally inconclusive outcomes. We find that RL fine-tuning consistently improves over pre-trained backbones and strong baselines. Notably, it enables smaller models to surpass larger pre-trained models in data-limited regimes and induces positive transfer across tasks. Further analysis shows that RL fine-tuned models generate trajectories with stronger structural and semantic alignment to ground truth and greater downstream utility.

cs.LG↗
arXiv2026

SetMIR: Multi-Interest Retrieval as Set Prediction

Embedding-based retrieval is at the core of industrial recommender systems, but a single user embedding is often too limited to capture a user's diverse interests. Multi-interest retrieval addresses this by using multiple user embeddings, yet existing methods still suffer from two issues: interest collapse, where different embeddings learn the same interest, and static dispatch, where serving uses a fixed retrieval budget even when some embeddings are unnecessary. We propose SetMIR, which treats multi-interest retrieval as a set prediction problem. SetMIR encodes a user's behavior history with a transformer and uses K learnable queries to decode a set of user interests, each producing a retrieval embedding and a presence score. During training, Hungarian matching assigns targets to queries one-to-one, so matched queries learn distinct interests and the presence head learns which queries are active. At serving time, SetMIR uses presence scores and query-level Non-Maximum Suppression (NMS) to issue only active, non-redundant ANN queries. On Snap's Dynamic Product Ads (DPA) data, SetMIR outperforms four learned multi-interest retrievers on every metric while issuing 33% fewer ANN queries per request. Deployed as a new retrieval source in the DPA production stack, SetMIR lifts overall CVR by 3.1%, while lifting CTR by 44% and CVR by 51% over the item-to-item retrieval source with the same item embeddings, ANN index, and retrieval quota.

cs.IR↗
arXiv2026

CAMIE: Co-Engagement-Aware Multimodal Item Embeddings for Snap Dynamic Product Ads Retrieval

Item-to-item (I2I) retrieval is a core primitive in large-scale recommendation and advertising systems. In production Snap Dynamic Product Ads (DPA), I2I retrieval faces two challenges: separate visual, textual, and multimodal encoders fragment the retrieval stack, and content-only training does not align embeddings with the co-engagement behavior that drives downstream conversions. We present CAMIE, a co-engagement-aware multimodal item embedding framework for Snap DPA retrieval. CAMIE builds on LLM/MLLM backbones, using their native multimodal interfaces to represent item images and metadata in a shared embedding space. It then fine-tunes the backbone on co-engaged item pairs mined from user journeys with a symmetric in-batch InfoNCE objective. Offline, CAMIE outperforms the strongest commercial multimodal embedding model on Recall@10 and serves text-only retrieval from the same checkpoint with minimal quality loss. Online, CAMIE serves as a drop-in replacement for two deployed content-based I2I encoders, delivering +0.390% CTR / +10.832% CVR over the multimodal control, +18.958% CTR / +13.12% CVR over the text control, and +0.211% CTR / +1.911% CVR on overall DPA traffic. CAMIE is deployed in production.

cs.IR↗
arXiv2026

Öpik-type collision frequency for Kozai-driven projectiles: Target bodies on eccentric and inclined orbits

For high-inclination projectiles undergoing Lidov--Kozai secular evolution, coupled variations in eccentricity and inclination complicate estimates of long-term collision frequencies with a target body. Previous collision-frequency studies for Kozai-driven projectiles have considered target-body orbits that are either circular or confined to the reference plane. The present study considers the general case in which the target body's orbit has both non-zero eccentricity and non-zero inclination. For each complete Lidov--Kozai cycle, the initial relative nodal longitude and the target body's initial argument of periapsis serve as two independent orientation variables. The single-cycle collision frequency is evaluated for each pair of initial values. Under the incommensurability condition considered here, the long-term mean is then obtained by explicitly averaging these values over both orientation variables. For the special cases in which the target body's orbit is circular or lies in the reference plane, the method is shown analytically to reduce to the corresponding formulations of previous studies. Numerical comparisons confirm these reductions. For the general eccentric and inclined case, the resulting collision frequency predicts a projectile survival curve that agrees well with the fraction of projectiles remaining in independent direct dynamical integrations. Finally, it is shown that, for a fixed dynamical setup and under the incommensurability condition, the long-term mean collision frequency associated with a given closed Hamiltonian level curve is independent of both the projectile's initial secular state along that level curve and its initial longitude of ascending node.

astro-ph.EP↗
arXiv2026

Cubit: Token Mixer with Kernel Ridge Regression

Since its introduction in 2017, the Transformer has become one of the most widely adopted architectures in modern deep learning. Despite extensive efforts to improve positional encoding, attention mechanisms, and feed-forward networks, the core token-mixing mechanism in Transformers remains attention. In this work, we show that the attention module in Transformers can be interpreted as performing Nadaraya-Watson regression, where it computes similarities between tokens and aggregates the corresponding values accordingly. Motivated by this perspective, we propose Cubit, a potential next-generation architecture that leverages Kernel Ridge Regression (KRR), while the vanilla Transformer relies on Nadaraya-Watson regression. Specifically, Cubit modifies the classical attention computation by incorporating the closed-form solution of KRR, combining value aggregation through kernel similarities with normalization via the inverse of the kernel matrix. To improve the training stability, we further propose the Limited-Range Rescale (LRR), which rescales the value layer within a controlled range. We argue that Cubit, as a KRR-based architecture, provides a stronger mathematical foundation than the vanilla Transformer, whose attention mechanism corresponds to Nadaraya-Watson regression. We validate this claim through comprehensive experiments. The experimental results suggest that Cubit may exhibit stronger long-sequence modeling capability. In particular, its performance gain over the Transformer appears to increase as the training sequence length grows.

cs.LG↗
arXiv2026

SkillSight: Calibrating Generic Content Bias for Skill Retrieval

As large language model agents gain access to increasingly large skill libraries, retrieving the right skill becomes critical to reliable capability selection and execution. Existing retrievers often treat skill contents as ordinary documents, overlooking their highly regular structure: shared descriptive patterns recur across many skills while providing little evidence for distinguishing the required capability. We show that this shared descriptive background is reflected in dense relevance scores, induces a pronounced energy gap between queries and skill documents, and obscures discriminative signals, especially for structurally similar hard negatives. Based on this observation, we propose SkillSight, a training-free retrieval framework that calibrates shared background in both semantic and lexical spaces. Semantic Background Calibration estimates a background subspace from generic tokens identified by IDF, reducing similarity induced by shared descriptive patterns, while Lexical Evidence Calibration downweights shared background tokens to recover discriminative token-level evidence. Experiments on SRA-Bench and SkillBench-Supp demonstrate consistent improvements across retrieval metrics, with SkillSight improving Recall@10 by up to 20.21 percentage points over the original dense retriever. It is up to 1,248 times faster than the Dense + Reranker baseline. In end-to-end evaluation, SkillSight achieves the best overall performance across three agent models and outperforms LLM Selection by up to 4.97 percentage points. These results identify shared descriptive background as a source of ranking interference in skill retrieval and demonstrate that calibrating it enables accurate and efficient skill selection without additional training. Our code can be found at https://github.com/xiaojinying/SkillSight.

cs.AI↗
arXiv2026

SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks

Multi-turn jailbreaks capture the real threat model for safety-aligned chatbots, where single-turn attacks are merely a special case. Yet existing approaches break under exploration complexity and intent drift. We propose SEMA, a simple yet effective framework that trains a multi-turn attacker without relying on any existing strategies or external data. SEMA comprises two stages. Prefilling self-tuning enables usable rollouts by fine-tuning on non-refusal, well-structured, multi-turn adversarial prompts that are self-generated with a minimal prefix, thereby stabilizing subsequent learning. Reinforcement learning with intent-drift-aware reward trains the attacker to elicit valid multi-turn adversarial prompts while maintaining the same harmful objective. We anchor harmful intent in multi-turn jailbreaks via an intent-drift-aware reward that combines intent alignment, compliance risk, and level of detail. Our open-loop attack regime avoids dependence on victim feedback, unifies single- and multi-turn settings, and reduces exploration complexity. Across multiple datasets, victim models, and jailbreak judges, our method achieves state-of-the-art (SOTA) attack success rates (ASR), outperforming all single-turn baselines, manually scripted and template-driven multi-turn baselines, as well as our SFT (Supervised Fine-Tuning) and DPO (Direct Preference Optimization) variants. For instance, SEMA performs an average 80.1% ASR@1 across three closed-source and open-source victim models on AdvBench, 33.9% over prior SOTA. The approach is compact, reproducible, and transfers across targets, providing a stronger and more realistic stress test for large language model (LLM) safety and enabling automatic redteaming to expose and localize failure modes. Our code is available at: https://github.com/microsoft/SEMA.

cs.CL↗
arXiv2026

Öpik-type collision frequency for Kozai-driven projectiles: Target bodies on inclined circular orbits

Existing Öpik-type collision-frequency methods already incorporate the Kozai-driven secular evolution of the orbital elements of high-inclination projectiles. However, these methods generally assume that the target body's orbit lies in the reference plane defined by the orbital plane of the perturbing body. The present paper extends the semi-analytical framework developed by Vokrouhlický et al. (2012) for a target body on a circular orbit in the reference plane to the case of a target body on a circular orbit with a non-zero inclination relative to that plane. The target body's nodal precession rate is prescribed to be constant and may be zero. In this geometry, whether the two orbits intersect depends not only on the secular state of the projectile's orbit but also on the relative nodal longitude between the two orbits. To account for this dependence, the relative nodal longitude is introduced as an additional geometrical variable, and the framework is extended accordingly. When the target body's circular orbit lies in the reference plane, the present formulation analytically reduces to the zero-inclination case described by Vokrouhlický et al. (2012). The numerical results also confirm this reduction. For the two cases with inclined target-body orbits, the collision frequencies computed with the present framework are used to predict semi-analytical decay curves for the fraction of projectiles remaining. These predicted curves closely match those obtained from direct dynamical simulations.

astro-ph.EP↗
arXiv2026

Multimodal Reinforcement Learning with Adaptive Verifier for AI Agents

Agentic reasoning models trained with multimodal reinforcement learning (MMRL) have become increasingly capable, yet they are almost universally optimized using sparse, outcome-based rewards computed based on the final answers. Richer rewards computed from the reasoning tokens can improve learning significantly by providing more fine-grained guidance. However, it is challenging to compute more informative rewards in MMRL beyond those based on outcomes since different samples may require different scoring functions and teacher models may provide noisy reward signals too. In this paper, we introduce the Argos (Agentic Reward for Grounded & Objective Scoring), a principled reward agent to train multimodal reasoning models for agentic tasks. For each sample, Argos selects from a pool of teacher-model derived and rule-based scoring functions to simultaneously evaluate: (i) final response accuracy, (ii) spatiotemporal localization of referred entities and actions, and (iii) the quality of the reasoning process. We find that by leveraging our agentic verifier across both SFT data curation and RL training, our model achieves state-of-the-art results across multiple agentic tasks such as spatial reasoning, visual hallucination as well as robotics and embodied AI benchmarks. Critically, we demonstrate that just relying on SFT post-training on highly curated reasoning data is insufficient, as agents invariably collapse to ungrounded solutions during RL without our online verification. We also show that our agentic verifier can help to reduce reward-hacking in MMRL. Finally, we also provide a theoretical justification for the effectiveness of Argos through the concept of pareto-optimality.

cs.AI↗