arXiv AI

arXiv:2610.23038v1 Announce Type: new Abstract: Automated research ideation has advanced rapidly, with multi-agent workflows that generate whole research ideas end to end. These frameworks leave largely unexamined the step that seeds a good idea: identifying an actionable limitation from literature. In this paper, we focus on this first step in the research ideation pipeline. Starting from a pilot study, we find that as large language models (LLMs) scale from 0.6B to 32B parameters, they become far better at recognizing which limitation later work addressed, but no better at generating one, suggesting that the bottleneck lies in the supervision signal rather than model capacity. We therefore construct ActLim-Bench from forward citations, yielding 18,279 evidence-linked supervision triples with human verification. On this signal, we propose a three-stage post-training pipeline: supervised fine-tuning, verifier-filtered rejection-sampling fine-tuning, and reinforcement learning with the verifier as an online dense reward. Experimental results show that our method achieves the highest recall score compared to existing methods among all frontier models. We further show that our generated limitations are preferred in 64.9% of non-tied human comparisons and improve downstream ideation systems. We will release our data and code upon publication.

arXiv:2610.23027v1 Announce Type: new Abstract: External text can supply predictive information absent from numerical histories, but its value depends on how it is represented, combined and deployed. We present Attribution-guided Semantic Evolution (ASE), a modular framework for constructing textual factors, evaluating their conditional contribution, and deploying validation-selected numerical--textual predictors. ASE supports task-specific implementations with lexical measurements, semantic primitives or evolved event/state factors, coupled to suitable numerical experts. Its feedback-based implementation uses conditional refitting diagnostics to guide factor revision and combination search. We evaluate ASE on the four text-associated TESS datasets and dynamic CSI 300 stock ranking. The four forecasting implementations obtain test MSEs of 0.001041, 0.022439, 0.333115 and 1.8150, each below the corresponding published TESS score. On CSI 300, the frozen text-fusion implementation improves mean RankIC by 0.000642 over its numerical expert and by 0.000701 over matched shuffled text, with positive differences in all five seeds. Controlled text perturbations support functional reliance on text correspondence, while incumbent retention prevents regressions in the measured development criterion. Together, the experiments characterize ASE at two levels: forecasting performance of task-specific implementations and the conditional contributions of individual modules.

arXiv:2610.23025v1 Announce Type: new Abstract: As AI-generated content becomes commoditized, economic value increasingly shifts from final artifacts to the upstream expertise used to specify inputs that steer LLM generation. Yet organizations lack methods for valuing this expertise and identifying which individual skills or configurations causally improve performance. This study examines generative marketing, where structured expert labels serve as skill primitives conditioning LLM-generated advertisements. Estimating their causal effects is difficult because outcomes reflect stochastic LLM mediation, high-dimensional label interactions, and multimodal confounding. This study proposes D-VAE (Deconfounder Variational Autoencoder), a counterfactual-inference framework integrating a multi-treatment deconfounder with causal representation learning. D-VAE recovers causally disentangled expert-labeling logic and derives PAC-based bounds on omitted-variable bias from single-treatment confounders. Applied to 29,177 foundation-makeup ad creatives, D-VAE outperforms state-of-the-art benchmarks. A field experiment shows that recommended configurations increase engagement by 32.7% and perform statistically indistinguishably from human experts, while a simulation study confirms causal attribution under complex confounding and treatment interactions. Overall, the study shifts value assessment from AI-generated products to skills, providing a foundation for pricing and optimizing AI-augmented skill portfolios.

arXiv:2610.23012v1 Announce Type: new Abstract: Recent advances in multimodal foundation models have significantly improved the ability to operate real-world software through graphical user interfaces (GUIs) using visual observations and natural language instructions. However, maintaining strong performance on unseen applications remains challenging, as practical tasks often require long-horizon procedural knowledge and application-specific operation patterns. In addition, constructing executable tasks and collecting corresponding trajectories for training still heavily rely on human-annotated data, incurring substantial cost. In this paper, we propose MAGE (Manual-augmented computer use AGent Execution and learning), a framework that leverages user manuals as a scalable source of procedural knowledge to improve both inference and training. During execution, MAGE retrieves task-relevant manual content and uses a planner to generate explicit procedural guidance for CUAs. To further account for the discrepancies between manuals and actual GUI environments, such as version differences or user settings, MAGE also adapts the agent policy through environment interaction. During training, MAGE converts manuals into executable task-plan pairs and uses the plans to guide environment rollouts toward task-relevant states; the resulting trajectories are then used to optimize the policy without human-authored demonstrations. This unified design enables effective utilization of manuals for both task execution and training, reducing reliance on human-authored training data. Experimental results across six applications demonstrate improvements in task success rates over strong baselines, highlighting the effectiveness of manual-guided planning and policy adaptation in new software environments. We provide the code and reproduction scripts at https://github.com/ku-autoai/MAGE.

arXiv:2610.23006v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models reduce inference computation through sparse expert activation, but their large expert memory footprint often exceeds GPU capacity, making expert offloading necessary for memory-constrained inference. However, existing systems typically handle GPU-missed experts by either transferring them to the GPU, incurring substantial PCIe transfer latency, or executing them on the CPU, making the slower CPU computation the bottleneck. To address these limitations, we present \method, a CPU-GPU collaborative MoE inference system that adaptively assigns these missed experts to the CPU or GPU for efficient execution. By exploiting differences in expert token-loads, \method selectively transfers high-load experts to the GPU while executing low-load experts on the CPU. To minimize inference latency, \method adaptively adjusts expert assignments to balance the CPU computation path against the GPU transfer-and-computation path, allowing both execution paths to complete as early as possible. Extensive experiments on three representative MoE LLMs show that \method improves prefill speed by up to 51.9\% and decode throughput by up to 39.5\% over the strongest baseline across the evaluated batch sizes, with consistent gains under different GPU-memory budgets.

arXiv:2610.22992v1 Announce Type: new Abstract: Designing RNA sequences that fold into specific 3D structures is a fundamental challenge in therapeutics. Current RNA inverse folding methods typically condition on 3D backbone coordinates but the generation is limited to 1D discrete sequences. This ignores the continuous side-chain orientations, which are essential for overall structural stability. To address this issue, we explicitly introduce side-chain geometry into the RNA generative process. Unlike co-design frameworks that diffuse across separate raw spaces, we propose Geometric Optimized Latent Diffusion (\textbf{GOLD}), which project sequence and structure into a unified latent manifold. GOLD employs a novel GeoVAE to elegantly integrate discrete RNA sequences with continuous side-chain angles. By mapping these modalities into a single, smooth latent manifold, GOLD naturally facilitates a synergistic co-diffusion process. To enhance structural validity, we further introduce a training-free, gradient-guided sampling mechanism. By decoding the generated sequence probabilities and side-chain geometries into structures during the sampling process, we compute analytical gradients from physical constraints. This dynamic feedback actively guides the generated sequence to a physically stable state. Extensive experiments validate the superiority of GOLD, achieving state-of-the-art performance across sequence recovery, secondary structure validity, and 3D foldability metrics. Our code and data are publicly available at https://github.com/darkflash03/GOLD.

arXiv:2610.22987v1 Announce Type: new Abstract: Coding agents use execution harnesses to constrain the consequences of prompt injection by enforcing permission boundaries. These systems deterministically intercept any out-of-sandbox action and prompt the user for approval. To reduce approval fatigue, users can approve allow-rules proposed by the agent, after which any future action matching the rule is allowed without a prompt. In this work, we show that this mechanism introduces a new risk: untrusted context can influence the permissions presented for approval, with consequences extending beyond the immediate task. We investigate privilege escalation targeting this permission-update process. Specifically, adversarial context planted in a repository can reliably steer an agent performing a routine task into requesting a plausibly justified, yet dangerously broad allow-rule. If the user approves the request, the saved rule can effectively blind the harness, enabling adversaries to execute malicious actions that would otherwise require approval, without triggering human oversight. Across production platforms, including Claude Code and Codex CLI, we demonstrate that agents successfully elicit the target allow-rules in 58% of experimental instances. Once acquired, these rules exhibit a massive semantic blast radius, covering 56.9% of category-specific capability test cases. To further quantify the downstream risk, we show that conditional on rule approval, our exploit achieves verified, silent goal completion in 47 of the 58 eligible instances (81.0%), undermining the safety promise of human-in-the-loop oversight.

arXiv:2610.22973v1 Announce Type: new Abstract: Reinforcement learning improves diffusion models using rewards on generated images, but repeated denoising and gradient estimation make training expensive. We introduce \method, an efficient method that constructs useful update directions by regressing centered rewards on centered final denoised images. It requires neither reward derivatives nor adjoint backpropagation through the sampling trajectory. A unified first-variation formulation identifies the value-gradient target with or without a trajectory-KL penalty. A population analysis under Gaussian noising explains the regression geometry, while a subspace analysis motivates clean-image coordinates. The implementation adapts rollout bandwidth and query weights to reward continuity: local rollouts suit smooth rewards, whereas broader groups provide informative contrasts for discrete rewards. Trained jointly on five rewards, one SD3.5-Medium model matches or exceeds DiffusionNFT's joint model on seven of eight metrics, reaching GenEval $0.94$, OCR $0.92$, and PickScore $23.82$ at about one fifth of its estimated training compute. In single-reward training, \method reaches matched reward thresholds $2.1$--$6.7\times$ faster than reproduced DiffusionNFT on identical hardware. Ablations support the clean-image estimator, direct direction transfer, and reward-dependent rollout choices. Code is available at https://github.com/jy-wang-tsinghua/DIFFUSIONRVGE.

arXiv:2610.22928v1 Announce Type: new Abstract: Multi-turn jailbreaks use feedback from a victim large language model to adapt their queries over several turns. However, once an effective trajectory has been found, it is unclear how much of the earlier query history is still needed. In this work, we study this by removing early attacker queries and running the remaining queries again in a new conversation while regenerating the victim's responses. We define the effective horizon as the shortest remaining query sequence that recovers the same attack progress. Empirically, we find that roughly half of the original query sequence is sufficient on average to recover the same attack progress. We call this phenomenon effective-horizon compression. We show that this shorter history can recover the best point reached during an unsuccessful attack and provide a better starting point for continuing the attack. It also helps identify which earlier queries should receive less learning signal during attacker training, and downweighting those queries improves performance. We further find that short reward-propagation windows preserve calibrated defense performance close to full-trajectory returns. These results show that multi-turn attacks can contain more queries than are needed to recover the progress reached later in the interaction.

arXiv:2610.22924v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable success in complex reasoning through explicit Chain-of-Thought (CoT), but the associated computational overhead and token verbosity remain significant barriers to efficiency. While implicit reasoning in continuous latent spaces offers a promising alternative, existing methods like Coconut and CODI often rely on fixed-length latent sequences and suffer from representational collapse. In this paper, we propose Sep-Latent, an adaptive implicit reasoning framework that utilizes separator tokens as structural semantic anchors. By introducing an Attention-Decay mechanism, we force the model to aggregate and compress reasoning logic into these anchors during training. We then align explicit and implicit pathways through multi-level distillation across all layers to ensure logical consistency. Crucially, Sep-Latent enables dynamic reasoning depth by adaptively terminating the latent thinking phase based on query complexity. Experimental results on the GSM8k-Aug benchmark show that Sep-Latent achieves an accuracy of 56.8\% with an average of only 5.4 tokens, significantly outperforming prior fixed-length implicit models in efficiency while narrowing the performance gap with explicit CoT. Further analysis via PCA and symbolic variant testing confirms that our method ensures semantic grounding and exhibits superior robustness to perturbations.

arXiv:2610.22915v1 Announce Type: new Abstract: Open-ended tool agents can complete the same objective through different tool paths, and their quality depends jointly on the interaction trace, environment state, and final artifacts, so such tasks rarely admit an executable ground-truth reward. The central challenge is therefore to construct a reward from existing experience that exposes the current policy's failures while remaining stationary during optimization. We introduce Reward Engine, which, like a self-motivated student, first works out what success requires and then optimizes toward it. From the task and initial trajectories, it builds a RewardPack of testcases for required correctness and rubrics for graded quality, each executed as a check that returns a judgment with evidence. The frozen RewardPack then guides the agent to revise and select its outputs, and can also serve as a reward for reinforcement learning. On WorkBuddy Bench Office and Claw-Eval, the constructed reward largely agrees with the benchmark graders, not reversing their ordering on 82.3\% and 80.5\% of candidate pairs. Used to revise executions, it raises three-run consistency ($\mathrm{Pass}^{3}$) over Baseline from 45.0\% to 54.0\% and from 78.4\% to 83.7\%.

arXiv:2610.22897v1 Announce Type: new Abstract: Long-horizon agents learn from failure, but the value of a failure record can change as execution progresses. We study when retaining, compressing, or removing the same history block improves subsequent execution relative to full-history KEEP. We introduce RECAP, a framework that combines matched context interventions, execution-relational prediction, and independent policy certification. Matched environment states and rollout seeds measure success and continuation prompt-cost differences; prefix-only relations between a failure block and the current execution propose promising edits. Independent task bundles then select a policy subject to harmful-intervention and non-positive-benefit risk constraints under a fixed measurement protocol. A five-seed longitudinal case holds both the failure block and its summary fixed: compression fails at an early state and becomes a cost-saving intervention at a later state. Across five backbones, RECAP produces positive paired-success saving estimates with backbone-specific reliability-efficiency tradeoffs. On Hunyuan-A13B, it edits 43.24% of retained checkpoints while matching KEEP's observed 91.89% continuation success and reducing unconditional mean continuation prompt cost by 4,619.8 tokens (2.13%). The framework provides an execution-level reference for deciding when to forget: retain history by its value to what comes next.

arXiv:2610.22883v1 Announce Type: new Abstract: Parameter-Efficient Fine-Tuning (PEFT) has emerged as a prevalent strategy for adapting large pre-trained models. Among PEFT techniques, reparameterization-based methods, particularly those that employ low-rank or sparsity structures, have attracted significant attention. However, these approaches often underperform full fine-tuning. Specifically, low-rank methods constrain the update rank, which is misaligned with the inherently high-rank nature of full fine-tuning. In contrast, sparsity-based techniques limit the flexibility of the parameter space and compromise connectivity across weights. To overcome these limitations, we explore the use of Toeplitz matrices, whose entries are constant along each diagonal, therefore providing a compact parameterization without imposing explicit rank or sparsity constraints. A straightforward approach is to update weights via a product of Toeplitz matrices. However, similar to RNNs, long multiplicative chains often lead to gradient instability. To address this issue, we propose \textbf{ToPA}, a more refined version of this idea that replaces standard Toeplitz matrices with block-wise Toeplitz, greatly increasing each factor's capacity and shortening the chain, thereby stabilizing training and improving expressiveness. We theoretically show that products of block-wise Toeplitz matrices can approximate arbitrary matrices under shorter chain length, justifying the structural design of ToPA. Furthermore, we demonstrate that ToPA offers greater expressivity than existing low-rank and sparse parameterizations. Empirical evaluations across 21 NLP and CV datasets, spanning 5 model architectures, consistently validate the effectiveness of ToPA.

arXiv:2610.22872v1 Announce Type: new Abstract: Time series forecasting models are increasingly deployed in continuously evolving environments. After a forecast is issued, future observations gradually arrive and reveal how the model has failed. Existing methods mainly treat such observations as supervision for parameter updates. However, it remains unclear whether verified forecasting errors can themselves provide causal feedback for correcting future predictions. To address this, we introduce Error Feedback Calibration (EFC), a fully test-time framework for deterministic post-hoc correction of time series forecasting. EFC constructs a Causal Error Diagonal (CED) from revealed errors of overlapping historical forecasts, providing a fresh view of the frozen forecaster's recent failure behavior. Then Cumulative Error Transport (CET) maps this error state to future residuals using cumulative estimation, while temporal out-of-sample validation controls the correction strength. Temporal Residual Learning (TRL) further predicts only the residual structure left after CET from recent CED trajectories, rather than relearning the entire forecasting error. Extensive experiments across forecasting backbones and datasets show that EFC broadly improves forecasting performance while substantially controlling harmful over correction.

arXiv:2610.22871v1 Announce Type: new Abstract: Federated Prompt Tuning (FPT) adapts large vision--language models by freezing the pretrained backbone and optimizing only lightweight prompt parameters across clients. Although this design improves communication and parameter efficiency, it creates an overlooked security risk. Since the backbone is shared and frozen, a malicious client can induce backdoor behavior through the representation space while keeping its uploaded prompt updates close to benign ones. We propose \textbf{ShadowFPT}, a targeted backdoor attack that exploits this frozen-backbone attack surface. ShadowFPT first pretrains a learnable \emph{Shadow Trigger} against the frozen CLIP visual encoder, using either auxiliary public data or the malicious client's local data, so that triggered inputs are steered toward the target class in representation space. During federated prompt tuning, the malicious client adapts the trigger under the current global prompt and then optimizes its local prompt on both clean and triggered samples. Only prompt parameters are uploaded to the server, while the trigger and frozen encoders remain local. By shifting most of the attack burden from prompt updates to trigger-induced representation steering, ShadowFPT achieves targeted misclassification while preserving prompt-space stealthiness. Across multiple datasets, aggregation rules, and non-IID federated partitions, ShadowFPT increases the attack success rate from 19.81\% to 90.36\% in our main setting, while maintaining clean accuracy. It remains effective across textual, visual, and joint vision--language prompt tuning. These results identify frozen backbones as stealthy and underexplored backdoor surfaces in federated prompt tuning, suggesting that defenses based only on prompt-update anomaly detection are insufficient.

arXiv:2610.22869v1 Announce Type: new Abstract: LLM agents are increasingly integrated into real-world works, yet they must handle diverse domain-specific tools and complex multi-sub-task problems that sequential tool invocation resolves inefficiently and with severe context bloat. The Main-Agent Delegation and Sub-Agent Execution (MAD-SAE) paradigm addresses these issues by delegating sub-tasks to specialized sub-agents for parallel execution in isolated contexts, but its delegation and orchestration quality remains unquantified. We introduce MS-Eval, a unified evaluation kit comprising an MCP-intensive benchmark, a controlled execution harness, tailored delegation and orchestration metrics, and the MSQ index for comprehensive assessment. Evaluating four MAD-SAE variants and eight frontier models reveals that (1) sub-agent specialization (Spec) is the best practical practice; (2) open-source models are largely competitive with few exceptions; and (3) MAD-SAE generally raises cost with contingent payoff, benefiting most open-source models in both performance and efficiency while leaving closed-source models with higher cost and degraded performance. Our case study further traces these gains to better single-agent solutions, effective context offloading, and genuine sub-task parallelism, whereas unnecessary or redundant delegation turns the same cost into pure overhead. Codes: https://github.com/LINs-lab/MS-Eval

arXiv:2610.22861v1 Announce Type: new Abstract: In branch-and-bound for Mixed-Integer Linear Programming (MILP), branching and node selection are two critical and tightly coupled decisions, yet most existing learning-based approaches focus on optimizing them separately. We propose Evo-B&B, an LLM-guided evolutionary framework that jointly evolves executable branching and node selection policies using end-to-end SCIP solving feedback. To improve search efficiency and reduce redundant evaluations of behaviorally similar policies, Evo-B&B introduces a behavior-aware multi-island evolutionary mechanism. It measures policy similarity from branching and node-selection behaviors on a fixed set of B&B decision states and uses this similarity to preserve population diversity. We evaluate Evo-B&B on four standard MILP benchmarks across multiple instance scales. Experimental results show that Evo-B&B achieves competitive solving performance and generalizes well to larger-scale instances, while ablation studies further demonstrate the effectiveness of joint evolution and behavior-aware diversity management.

arXiv:2610.22825v1 Announce Type: new Abstract: World models have shown considerable promise in sequential decision-making by anticipating the consequences of actions and providing predictive foresight for policy learning. However, learning to reason about counterfactual actions remains challenging, since predictive objectives may underemphasize information critical for action evaluation, while unexecuted actions lack observed futures for direct supervision. To address these challenges, we propose the World Action Critic (WAC) Model, which proposes multimodal action candidates and jointly learns candidate-conditioned future prediction and consequence evaluation. In our proposed framework, critic supervision directly shapes intermediate predictive representations during rollout, encouraging them to retain information needed to distinguish action quality. Observed futures supervise prediction for executed actions, while external task-quality targets provide evaluation signals for counterfactual candidates. Through joint optimization, critic signals from these candidates propagate into predictive representations without requiring their observed futures. Our theoretical analysis characterizes critic-guided feature retention and bounds candidate-selection regret. Applied to autonomous driving, WAC achieves 93.4 PDMS on NAVSIM-v1, demonstrating the effectiveness of jointly learning predictive foresight and consequence evaluation.

arXiv:2610.22805v1 Announce Type: new Abstract: Emergent Misalignment - the out of domain generalization of narrow harmful fine-tuning first shown by Betley et al. [2025] has been widely studied in language models but not in reward models that supervise them. In this paper, we fine-tune two state-of-the-art reward models, Skywork-Reward-V2-Llama-3.1-8B and Skywork-Reward-V2-Qwen3-8B [Liu et al., 2025] and show that narrow fine-tuning reward models to prefer harm in one domain (medical or financial) generalizes to seven held out domains. This is not degeneracy, as the fine-tuned reward models lose only 4.8 and 5.3 points overall (RM-Llama) on the standard RewardBench 2 evaluation [Malik et al., 2025] while still outperforming the unmodified RM-Qwen model. We then fine-tune the underlying language models, Llama-3.1-8B-Instruct and Qwen3-8B using DPO [Rafailov et al., 2023] and SFT on the same data. We find that reward models are more vulnerable to preference inversions compared to their language model counterparts. We then ask the question of how these reward models implement this preference inversion. Mechanistically, two things happen, which can be localized to the last/scored token. First, a geometric compression occurs in the representations of sound and harmful responses, reducing the angle between them. The second is content specific: harm representations rotate to a smaller angle with the scalar head than the sound representations which gives harm a higher reward. This happens only in harmful preference fine-tunes and not in control.

arXiv:2610.22779v1 Announce Type: new Abstract: Automated agent design increasingly trusts a single score to decide whether a change is an improvement -- but a score optimized aggressively enough ceases to measure what it was meant to. When an agent also explains its design, that explanation is a second signal we can check without human labels: negate each stated claim, re-run, and observe whether performance drops. We ask whether such a verifier stays reliable once an agent optimizes against it. Our contribution is not a new verifier but a way to stress-test one: a pressure ratio $\rho$ measuring how much the verifier steers the agent's search, and four falsifiable probes covering four failure modes -- giving no signal, being too weak to matter, being gamed by stating fewer claims, and being queried before the agent commits. We apply the test to our own verifier, the Rationale Consistency Score (RCS), inside an LLM agent that designs machine-learning pipelines, with one generator model, six tasks, and three seeds. First, in our prior configuration the verifier barely affects the search objective ($\rho \ll 1$), partly because of an accuracy gate, so its robustness had not been tested; it still shapes the reported artifact through a final-selection tie-break that $\rho$ does not register. Second, a capability control shows the agent shortens its claim lists when instructed, yet search does not, even at $\rho$ over 100 times the prior level; since feedback omits claim volume and horizons are short, this null result is largely structural rather than evidence of robustness. Third, when the agent can probe the verifier before committing, it keeps claims that pass while held-out faithfulness falls -- a decline invisible to in-loop metrics, though partly confounded by how RCS scores small pipelines. We offer these as preliminary evidence and propose a reporting standard: audit a verifier with $\rho$ and these probes before trusting it.