Agregador

arXiv:2306.02002v2 Announce Type: replace-cross Abstract: Existing research on robust Graph Neural Networks (GNNs) focuses predominantly on undirected graphs, overlooking the trustworthiness inherent in the link directions of directed graphs. In this work, we analyze the limitations of current approaches from both the attack and defense perspectives and redefine the robustness of GNNs in directed graphs. From the attack side, we introduce a more realistic directed graph attack setting that addresses the shortcomings of existing attacks. From the defense side, we propose a simple yet effective message-passing framework that serves as a plug-in layer to strengthen GNN robustness while avoiding a false sense of robustness. Our findings show that the trust signals encoded in directed graphs can be harnessed to substantially improve the robustness of GNNs. When combined with existing defense strategies, the framework achieves state-of-the-art robust performance alongside strong clean accuracy against both transfer and adaptive attacks. These results point to a novel and promising direction for strengthening the robustness of graph deep learning.

arXiv:2610.22066v2 Announce Type: replace Abstract: Given a state and a set of options, such as intents, tools or interface elements, System One decision models return a distribution over the options in one forward pass, without generated reasoning. Web systems increasingly build them by reading decisions from language models. Two axioms of rational choice are natural requirements for such decisions, because in web systems the listing and the option set are determined by other components and can change or be manipulated: the order in which the options are listed should not matter, and adding an option should not change the relative odds of the others (Luce's choice axiom). We test the standard reads, namely single-choice question (SCQ) prompting, with shuffled-order training, order averaging or sorted options, and invariant set architectures, and find that each violates at least one axiom: one shuffle changes 12-20% of SCQ answers, sorting only freezes an arbitrary convention, and a well-chosen added option steers 4-34% of decisions. By Luce's theorem, a read satisfies both axioms only if it is a softmax over scores that each depend on one option alone, so in a transformer they hold by construction only if no token that scores an option sees another. We implement this as Prism-1 (Position- and Rival-Independent Scoring for System One Models): every option is read in its own block at shared positions, with the model's usual left-to-right attention, in one forward pass. On five benchmark sets with Qwen3-8B and Gemma 4 12B, SCQ prompting trained on the same data still changes 7% of its answers under one shuffle, and an added irrelevant option steers 12% of its decisions. Prism-1 stays within one point of that baseline's accuracy and is 2-4 points more accurate once only answers that survive a reordering are counted, while no shuffle changes any of its answers and no added irrelevant option moves its choice among the others.

arXiv:2610.21411v2 Announce Type: replace Abstract: Multi-agent LLM systems rely on generative models for expert execution, workflow planning, and artifact review. Yet many coordination operations require only bounded decisions, such as selecting the next expert or judging artifact quality. Profiling three representative MAS frameworks, we find that routing and review account for 31.7-43.5% of generative-LLM tokens. However, replacing these operations with low-cost decision models introduces two interface gaps: generative planners produce execution plans and handoff instructions (planning gap), while reviewers provide actionable feedback for repairing flawed artifacts (review gap), which bounded decisions alone cannot provide. We introduce Jev-LiteMAS, a multi-agent framework that bridges both gaps by combining a lightweight decision model (Jev) with generative execution and feedback. To address the planning gap, Jev selects experts dynamically from the task and prior expert outputs, using accumulated context to ground subsequent execution without a pre-generated trajectory. To address the review gap, Jev screens intermediate artifacts against task criteria: passing artifacts proceed directly, whereas flagged ones undergo LLM re-review for acceptance or corrective feedback. Across four benchmarks and two backbones, Jev-LiteMAS reduces generative-LLM tokens by 12.7-54.6% over LAS, maintaining accuracy within 1.34 percentage points and lowering latency in seven of eight settings. Grounding routing in substantive expert outputs prevents up to 18.0 points in accuracy loss.

arXiv:2610.21147v2 Announce Type: replace Abstract: Large language models increasingly rely on external memory to answer queries grounded in long-horizon histories such as multi-session dialogues and lengthy documents. However, existing memory methods often optimize retrieval and memory construction separately, without a shared reward space for evaluating search, writing, and stopping decisions. To address this, we propose All-in-One Memory (AiO-Mem), which organizes these operations as transitions over a shared evidence state and directly evaluates the semantic quality of each action in a unified reward space. AiO-Mem compiles heterogeneous histories into source-traceable multi-view events, providing a shared substrate for retrieval and memory writing. A unified memory policy actor then rolls out complete interaction trajectories over this shared evidence state. A separate trajectory-conditioned process reward model is trained through evidence-grounded supervised fine-tuning and trajectory-level DPO to assign process scores to the collected trajectories. These scores are aggregated into an action-balanced trajectory reward and used by Process-Aligned DAPO (PA-DAPO) to optimize the memory policy. Across long-context memory benchmarks, AiO-Mem consistently improves answer accuracy over both static memory systems and RL-trained memory agents.

arXiv:2610.20805v2 Announce Type: replace Abstract: A reasoning trace retained at answer time plays two roles: it can raise accuracy, and it can compete with the current evidence when the two disagree. We disentangle these roles by crossing verified evidence versions with the traces generated from each and answering from the same traces and evidence under two configurations: continuation of the model's own thinking and a separate answer call. Across three model families (gpt-oss, Gemma4, Qwen3) on HotpotQA and MuSiQue, the separate call raises evidence-following over continuation by 29.9 to 60.6 points. On the same pairs, removing the trace lowers accuracy by similar amounts under both configurations. Yet continuation repeats the stale conclusion in most conflicts, and the separate call follows the current evidence far more often. Benefiting from a trace and deferring to it are therefore distinct properties. Further analyses show that the final line of a trace carries most of its value, gold evidence helps most before the trace is written, distractors weaken correction under a separate call, and renewed reasoning, unlike a verification instruction, follows the current evidence in most conflicts. Because trace deletion alone cannot reveal which source an answer follows, evaluations should report both properties together with the answer configuration.

arXiv:2610.20532v2 Announce Type: replace Abstract: A multimodal agent must decide whether visual evidence is worth acquiring, which candidate or resolution to query, and when further interaction can no longer change its decision. We study this problem under a strict free-metadata/paid-observation boundary, stochastic vector costs, and a frozen execution trace, and treat it as decision-certifiable active evidence acquisition. A Counterfactual Evidence Interaction Graph (CEIG) represents unary evidence value, signed second-order interaction, and directed conditional harm while maintaining explicit score enclosures for unresolved interactions; a decision-weighted enclosure objective tightens the bounds that can change action identity. Gap-directed refinement evaluates only interactions that can displace the incumbent acquisition and stops once an $\epsilon$-decision certificate shows that unresolved terms cannot change the selected action beyond a declared tolerance. The certificate is model-relative: it verifies policy-consistent optimality under the pinned learned score, and semantic quality is measured separately through post-freeze labels. Paired continuation rollouts learn the downstream value of paid previews, an online operational cost filter is separated from independent finite-policy-family trajectory certification, and an acquisition monitor with an independently implemented verifier binds every certificate to the frozen trace. On 640 cases split into 384/128/128 training, validation, and test cases, the controller reaches task score 0.842, grounding F1 0.816, evidence recall 0.873, 1.74 accepted calls, 286.5K visual tokens, and 742ms p95 latency. Dense replay of issued certificates shows 0.992 action agreement and a 0.988 certificate rate while evaluating 19.6 instead of 191.4 expensive interaction terms per decision.

arXiv:2610.20473v2 Announce Type: replace Abstract: Opponent histories can mislead after behavioral shifts. SafeAdapt-Poker formulates budgeted adaptation under opponent shift as a dual-counterfactual sequential-control problem using only information available before each decision. At each decision the controller asks two distinct questions: what local downside a deviation from the frozen anchor would induce under matched legal continuations, and what future adaptation value would be lost by consuming part of the remaining deviation budget now. The first question is answered by a monotone strategic-risk model over deviation intensity; the second by a paired budget-state continuation model that prices current budget consumption. The controller selects among support-preserving candidate deviations by trading immediate adaptation value against these two quantities, a pathwise cumulative-KL ledger bounds total anchor-relative deviation, and a finite family of frozen controllers is screened on complete paired calibration sessions before held-out interaction. A finite-candidate perturbation bound shows that the allocation objective degrades continuously with continuation-value estimation error. Evaluation covers exact-game exploitation and safety, four opponent shifts, local-risk calibration, delayed-opportunity allocation, direct opportunity-value estimation, value-error robustness, factorial mechanism attribution, budget sensitivity, abstract-HUNL cross-play, and player/time-held-out public-history behavior. On exact Leduc the full controller attains a matched weak-pool gain of +0.0718 with a worst-opponent delta of -0.0126, raises delayed-opportunity capture from 0.6318 under myopic allocation to 0.7841 under the same session budget, and reaches +42.7 mbb/hand in abstract-HUNL cross-play; the retained public-history screen reports 0.5820 action accuracy and 0.9277 log loss versus 0.5039 and 0.9778 for a public prior.

arXiv:2610.20191v2 Announce Type: replace Abstract: Medication recommendation (MR) is critical for clinical decision support. While existing MR methods are mostly designed for single-center learning, where only one independent hospital is involved, multi-center MR with hospitals of different scales has become increasingly demanding in practice. In multi center settings, abundant data from large medical centers can improve recommendation performance for low-resource centers. Despite a few preliminary attempts on this task, two critical gaps remain. Gap 1: Existing multi-center methods fail to disentangle transferable cross-hospital clinical experience from hospital-specific prescribing patterns, limiting clinical feasibility and physician acceptance. Gap 2: They commonly overlook multi label safety constraints of MR, including drug-drug interaction risks and local formulary feasibility, which are essential for safe real-world deployment. To address these gaps, we propose HEM-Med, a novel hierarchical agentic memory framework for multi-center MR. To address Gap 1, we design a disentangled hierarchical memory module that builds patient-level medication context attribution records and disentangles them into cross hospital experience memory and hospital-specific residual memory. To address Gap 2, we introduce a safety-aware medication set generation module, which integrates dual-level experience retrieval with safety-aware set decoding to produce clinically relevant, safer, and locally adaptive medication recommendations. Experiments on a real-world multi-center eICU dataset show that HEM-Med outperforms representative transfer learning, LLM-based, and MR baselines in terms of both recommendation accuracy and safety.

arXiv:2610.18566v2 Announce Type: replace Abstract: Large language model (LLM) routers reduce serving cost by choosing which model to call and how many output tokens to grant it for each query. Existing routers rank model-budget actions using a single quality metric. This does not work for mixed workloads. For ordinary queries, a good answer is correct and useful (utility); for security-sensitive queries, a good answer refuses harmful requests or resists malicious instructions (security). These two objectives prefer different models and budgets. We propose SCRouter, a router that learns when to prioritize security and how to allocate the token budget. For each model-budget pair, it estimates the probability that the response finishes within budget. It uses this probability to predict utility and security separately. A small probe determines how to weight these two predictions for each query. SCRouter then selects the model and budget by balancing the weighted utility and security against cost. We also build SCRouterBench, a benchmark of 38,869 utility and security queries spanning nine security dimensions, each answered under all 144 combinations of 12 models and 12 budgets, plus 2,753 out-of-domain queries. SCRouter improves the baselines by 13-29 points in-domain and 19-23 points out-of-domain.

arXiv:2610.17665v3 Announce Type: replace Abstract: Can vision-language models turn 2D observations into 3D understanding that supports precise action? This requires inferring object geometry, anticipating the effects of rotation, and refining actions through visual feedback. We introduce RoTA-Bench to evaluate these abilities through interactive 3D-to-2D projection alignment. Given a target silhouette, a model observes a rotated object and chooses successive rotations to recover the target projection within a limited action budget. Our automated pipeline constructs silhouette-preserving 3D objects from 2D icons and uses reversible initialization to guarantee solvability, yielding 674 tasks and a stratified 100-task test set. Empirically, we find that (i) a substantial human-model gap persists: GPT-5.6-Sol succeeds on only 17% of tasks, whereas 20 undergraduate participants collectively complete the test set four times with a 100% success rate; (ii) image-space and pose-space progress can diverge: at matched states, the model more often improves silhouette overlap while worsening pose alignment than humans (19.4% vs. 10.9%); and (iii) fine-grained control is sensitive to interaction history: removing it leaves 96.8% of the model's actions at a coarse 30-degree step size and sharply reduces observed task success. These findings highlight the challenge of converting visual evidence into precise 3D control, beyond recognizing or matching individual images.

arXiv:2610.15882v2 Announce Type: replace Abstract: A stored fact may stop being valid when a user changes a preference or an event replaces an earlier one. We study whether a language model can learn these changes in its parameters and answer correctly from only a question and the current time. Engram Injection stores facts in LoRA adapters and supplies the clock through FiLM conditioning on a frozen Qwen2.5-3B-Instruct model. We compare it with additive clock conditioning, prompting with the full dated history, and retrieving four dated records. We train six matched adapters across three seeds after fixing a sampler that could admit test-age examples into training. The training audit reports no such examples among 127,760 evaluated training inputs. On 62 pairs of questions asked before and after an update, at an elapsed age of seven days excluded from training, both adapter methods answer zero pairs correctly under the primary blinded assistant review with order code 1 held fixed. Full-history prompting answers 59/62 pairs correctly, and retrieval answers 62/62. Separate experiments show that adapters can store facts and that removable memory units can support local deletion. Combining fact selection with time-based version selection remains unsuccessful. These results separate learning a fact from learning when to use it.

arXiv:2610.15463v2 Announce Type: replace Abstract: With the rapid proliferation of social media, harmful memes have become a growing threat to online ecosystems. Their harmfulness is often implicitly conveyed through complex interactions among visual, textual, and contextual cues, making accurate detection challenging. Recent studies have introduced Retrieval-Augmented Generation (RAG) and external knowledge into harmful meme detection. However, existing methods mainly retrieve similar instances or auxiliary information, limiting their ability to capture reusable harmfulness knowledge and underlying reasoning mechanisms, and thus constraining both detection performance and interpretability. To address these challenges, we propose MemeLogos, a knowledge-driven retrieval-augmented reasoning framework for harmful meme detection. MemeLogos abstracts recurring harmfulness patterns and reasoning structures from diverse harmful cases into reusable knowledge units and organizes them into a dedicated star-shaped knowledge graph. By combining structured knowledge retrieval with an explicit multi-stage reasoning process inspired by cognitive mechanisms, MemeLogos leverages retrieved knowledge to guide harmfulness reasoning, improving both detection reliability and interpretability. Extensive experiments show that MemeLogos consistently outperforms existing harmful meme detection methods while generating more coherent and interpretable reasoning, demonstrating the effectiveness of structured harmfulness knowledge for multimodal content understanding.

arXiv:2610.14542v2 Announce Type: replace Abstract: Multimodal benchmarks are central to evaluating whether models can reason over information from multiple modalities. However, existing literature has revealed that some benchmarks may contain shortcut items that can be answered from a single modality or from answer-option regularities alone, thus failing to reflect models' true cross-modal inference ability. Existing methods for assessing benchmarks typically rely either on intrinsic item structure or extrinsic model response behavior, which are not adequate for a comprehensive diagnosis. To fill in this gap, we propose SRCoD, a structure-response co-calibrated diagnosis framework for item-level diagnosis of modality dependence in multimodal benchmarks. SRCoD estimates sample-wise multimodal information structure from benchmark content and target answers, and uses this signal as a soft structural anchor for modality-conditioned item response modeling. The learned model produces a calibrated item-level diagnostic profile that reflects how strongly an item depends on different forms of modality evidence, enabling fine-grained benchmark analysis beyond aggregate accuracy. SRCoD also provides interpretable attribution of the diagnosis results. Extensive experiments under two complementary protocols, i.e., benchmark-refinement oriented validation and human-labeled item validation, demonstrate that SRCoD outperforms state-of-the-art benchmark diagnosis methods.

arXiv:2610.11773v3 Announce Type: replace Abstract: Guard models are increasingly used to safeguard LLM-based agents, primarily by identifying actions that agents are forbidden to perform. However, identifying forbidden actions alone is insufficient to ensure agent safety. In this paper, we argue that agent safety also depends on identifying required yet unperformed safety-critical actions, which we call obligations. Our preliminary study on a popular benchmark for evaluating safety shows that 56.92% of GLM-5.3 trajectories contain unfulfilled obligations, compared with only 30.00% containing forbidden actions. This finding reveals unfulfilled obligations as a major and previously overlooked source of safety risk. However, to our knowledge, no existing benchmark evaluates whether guard models can identify these obligations. To close this gap, we introduce ObligationBench, the first benchmark for evaluating the capability of obligation identification, comprising 240 expert-validated trajectories covering issue resolution, feature development, and terminal operations. Our evaluation of 14 representative models reveals substantial limitations: the highest recall and exact-match rate are only 48.97% and 10.00%, respectively. To address these limitations, we develop ObligationGuard using 40,000 synthetic training examples. ObligationGuard achieves 57.52% recall and an exact-match rate of 21.67%, surpassing all evaluated models on both metrics. We call on the community to incorporate obligation identification into the design and evaluation of future guard models to improve agent safety.

arXiv:2610.11723v3 Announce Type: replace Abstract: Multiplayer world models must ensure that independently controlled views remain consistent with a single shared and persistent world. We introduce MultiWorldBench, a diagnostic Minecraft benchmark comprising 495 case configurations across seven task suites and ten capabilities, including independent control, cross-view motion, shared-state synchronization, persistence, structural reasoning, concurrent interaction, and delayed revisit. Using Engine GT as a reference, we evaluate two multiplayer world models, Solaris (MP) and Gamma-World, together with a single-player generation variant, Solaris (SP). Among the generated systems, Gamma-World achieves the highest ten-capability average at 21.39, followed by Solaris (MP) at 20.88 and Solaris (SP) at 10.06, while Engine GT reaches 91.69. Gamma-World performs better on several control, shared-state, and revisit capabilities, whereas Solaris (MP) leads in cross-view motion and race-condition consistency. Nevertheless, all generated systems score at most 8.00 on state persistence and 1.33 on structural consistency, and none succeeds in spatial reasoning or building-identity preservation. Human pairwise evaluation yields the same overall system ranking and shows strong alignment with the automatic evaluation, with a mean dimension-level Spearman correlation of 0.95. These results show that current multiplayer world models still exhibit a substantial gap relative to Engine GT in maintaining a coherent shared world.

arXiv:2610.11570v2 Announce Type: replace Abstract: In this paper, we argue that Looped Transformers need their own residual connections to prevent performance degradation as the number of iterations grows. We first introduce an interesting phenomenon we observed in Looped Transformers, called latent overthinking: noisy state updates overwrite correct intermediate deductions and even undo completed solutions. This leaves subsequent iterations to recover lost information from an already degraded representation: once an error arises in an earlier loop, often as a result of long-range propagation through the recurrence, later loops find it difficult to correct. In this paper, we introduce InfiLoop, a loop-native residual connection that learns which past computations to retain and how much to accept from each new update. InfiLoop combines content-based weighting with learned temporal decay to maintain a running summary of recurrent states. An exact streaming recurrence keeps its persistent aggregation memory constant as the loop count grows. The resulting adaptive update suppresses unreliable proposals and preserves useful intermediate states. Across extensive reasoning tasks, a 7M-parameter InfiLoop model outperforms existing recursive architectures, reaching 97.9% exact accuracy on Sudoku-Extreme, and 13.6% pass@2 on ARC-AGI-2. Notably, on Sudoku-Extreme, InfiLoop continues to improve with test-time looping beyond 20,000 effective steps, showing that added depth translates directly into stronger reasoning. Our code is available at https://github.com/pixeli99/InfiLoop.

arXiv:2610.11370v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) grounds language models in external corpora. Agentic RAG enables iterative search, yet exposes the model to isolated chunks without document structure, making it difficult to distinguish relevant evidence from chunks that merely resemble the query. Structure-aware methods such as PageIndex navigate using the structure but cannot scale to structures of large corpora that cannot fit in the LLM context. Hence, they first commit to a single document using a document retriever and cannot recover from a wrong choice. We propose RIT-RAG (Retrieval-Induced Tree RAG), which combines content retrieval with structural navigation. Offline, RIT-RAG builds a tree for each document from its table of contents or sitemap. At query time, it retrieves a broad set of chunks and uses their positions to induce manageable sub-trees, potentially across multiple documents. An LLM agent navigate these sub-trees, selectively reads promising nodes, and reformulates queries when needed. Thus, retrieval proposes where to look, while the agent decides what to read. Across financial, scientific, and customer-support benchmarks, RIT-RAG achieves the highest answer accuracy among vanilla, graph-based, and agentic baselines. On EntQABench, our new benchmark of 2.84 million technical-documentation webpages, it improves accuracy by 6.6--11.4 points over the strongest baseline across three LLMs.

arXiv:2610.09146v2 Announce Type: replace Abstract: Large language models (LLMs) and vision-language models (VLMs) are usually frozen after deployment, so they do not learn from the cases they solve. This is especially concerning in medicine, where new clinical evidence, updated guidelines, and new therapies can change established practice. Fine-tuning can update the model, but it requires access to model weights and additional training. Parameter-free methods avoid training, but they may overfit a fixed validation set, lack reliable domain knowledge, or lose visual details by saving experience only as text. To address these limitations, we present a model-agnostic framework that allows frozen LLMs and VLMs to learn from deployment experience through three forms of external expertise: a Skill that guides reasoning and tool use, a Knowledge Memory that stores reliable facts supported by earlier cases or trusted external evidence, and a Multimodal Knowledge Base that keeps visual examples and guides the model to relate each retrieved case to the current image. Instead of relying on a fixed validation set, a validation strategy keeps an update only if it helps on new cases without degrading performance on earlier ones. Across six benchmarks covering clinical diagnosis, clinical workflows, medical reasoning, and medical and non-medical visual reasoning, and with four open-weight and closed-source base models, our framework improves performance during online deployment by up to 34.2% over the base model on medical tasks, generalizes to unseen cases, transfers to other models without further optimization, and works in non-medical domains.

arXiv:2610.08621v2 Announce Type: replace Abstract: Recent game design agents have made substantial progress in generating playable games. However, program correctness does not ensure an enjoyable experience for players. We present Recursive Game Creator, an experience-oriented harness to advance agentic game development from rough game prototypes into entertaining games. Recursive Game Creator organizes recursive development around four components: Designer, Builder, Player, and Reviewer. The Designer translates user instructions and Reviewer's feedback into detailed plans. The Builder turns these plans into candidate games. The coding-native Player creates and executes reusable policies through programmatic interfaces to efficiently collect diverse gameplay trajectories, mitigating evaluation bias caused by slow GUI-based collection. The Reviewer uses carefully designed trajectory-based metrics to induce player preferences, integrating with visual evidence and explicit textual preferences to evaluate games against game-specific criteria. Finally, the Reviewer accepts the better version and provides improvement reviews for the next round, closing the recursive loop. Our method achieves state-of-the-art overall performance of 77.89 on GameCraft-Bench. On GameASG-Bench, it achieves a strict task success rate of 53.2%, a 34.1% improvement over the same-model baseline, and the highest mean runtime-check pass rate at 93.4% among compared methods. A user study shows longer playtime and higher ratings. Project page is at: https://imbaldy.github.io/recursive-game-creator/.

arXiv:2610.04184v2 Announce Type: replace Abstract: Recursive self-improvement (RSI) relies on evaluation feedback to assess progress and guide further research, yet repeatedly running complex benchmarks is costly and slows iteration. Human experts reduce this cost by selecting benchmark subsets or designing compact suites. We ask whether AI agents can automate this design process and introduce EvalResearchBench (ERB), a benchmark for autonomous evaluation research. Given target materials, development references, candidate APIs, and fixed time and API budgets, an agent called the researcher selects or synthesizes tasks, implements graders, and revises them in pilot tests before freezing an executable evaluator for coding, co-work, and reasoning. We study 9 researchers and 13 candidate models and compare each frozen evaluator with 14 target benchmarks on score concordance and pairwise agreement. The best evaluators order about 75\% of candidate pairs as the targets do, below the 91\% ceiling set by disagreements among the targets. No researcher leads on every metric, and the best evaluator on development targets is not the best on sealed targets hidden from the researcher. A human-designed sample of public tasks remains a strong baseline, and the evaluator with the lowest recorded execution cost attains the highest pairwise agreement. Agents repair tasks and graders through pilot feedback, yet their evaluators can still truncate answers, exhaust the evaluation budget, or let a few questions dominate a domain score.