Verification Mirage: Mapping the Reliability Boundary of Self-Verification in Medical VQA

Self-verification, re-invoking the same vision language model (VLM) in a fresh context to check its own generated answer, is increasingly used as a default safety layer for medical visual question answering (VQA). We argue that this practice is fundamentally unreliable. We introduce [METHOD NAME], a diagnostic framework for mapping the reliability boundary of medical VLM self-verification by decomposing verifier behavior into discrimination capability and agreement bias. Because the verifier and answer generator are capacity-coupled, the verifier can overly agree with the generator, creating a verification mirage: a regime with both high verifier error and high agreement bias, driven by false acceptance of incorrect answers. Evaluating six open-weight VLMs across five medical VQA datasets and seven medical tasks, we find that this boundary is strongly task-conditioned. Knowledge-intensive clinical tasks fall deepest into the mirage, simpler tasks are more resistant, and perceptual tasks lie in between. Verification also fails to provide an independent safety signal: logistic mixed-effects analysis shows that verifier error and agreement bias become more likely when the generator is wrong, while saliency analyses show that verifiers under-attend to image evidence relative to generators, a phenomenon we call the lazy verifier. Cross-verification reduces but does not eliminate the mirage. Moreover, when verification is reused in multi-turn actor-verifier loops, most initially wrong answers become locked in by false verification. Since our experiments use clean benchmarks, the observed reliability boundary likely underestimates failures in real clinical deployment.

Plug-and-Play Logit Fusion for Heterogeneous Pathology Foundation Models

Pathology foundation models (FMs) have become central to computational histopathology, offering strong transfer performance across a wide range of diagnostic and prognostic tasks. The rapid proliferation of pathology foundation models creates a model-selection bottleneck: no single model is uniformly best, yet exhaustively adapting and validating many candidates for each downstream endpoint is prohibitively expensive. We address this challenge with a lightweight and novel model fusion strategy, LogitProd, which treats independently trained FM-based predictors as fixed experts and learns sample-adaptive fusion weights over their slide-level outputs. The fusion operates purely on logits, requiring no encoder retraining and no feature-space alignment across heterogeneous backbones. We further provide a theoretical analysis showing that the optimal weighted product fusion is guaranteed to perform at least as well as the best individual expert under the training objective. We systematically evaluate LogitProd on \textbf{22} benchmarks spanning WSI-level classification, tile-level classification, gene mutation prediction, and discrete-time survival modeling. LogitProd ranks first on 20/22 tasks and improves the average performance across all tasks by ~3% over the strongest single expert. LogitProd enables practitioners to upgrade heterogeneous FM-based pipelines in a plug-and-play manner, achieving multi-expert gains with $\sim$12$\times$ lower training cost than feature-fusion alternatives.

EvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification

Anthropic proposes the concept of skills for LLM agents to tackle multi-step professional tasks that simple tool invocations cannot address. A tool is a single, self-contained function, whereas a skill is a structured bundle of interdependent multi-file artifacts. Currently, skill generation is not only label-intensive due to manual authoring, but also may suffer from human--machine cognitive misalignment, which can lead to degraded agent performance, as evidenced by evaluations on SkillsBench. Therefore, we aim to enable agents to autonomously generate skills. However, existing self-evolving methods designed for tools cannot be directly applied to skills due to their increased complexity. To address these issues, we propose EvoSkills, a self-evolving skills framework that enables agents to autonomously construct complex, multi-file skill packages. Specifically, EvoSkills couples a Skill Generator that iteratively refines skills with a Surrogate Verifier that co-evolves to provide informative and actionable feedback without access to ground-truth test content. On SkillsBench, EvoSkills achieves the highest pass rate among five baselines on both Claude Code and Codex, and also exhibits strong generalization capabilities to six additional LLMs.

LoFi: Location-Aware Fine-Grained Representation Learning for Chest X-ray

Fine-grained representation learning is crucial for retrieval and phrase grounding in chest X-rays, where clinically relevant findings are often spatially confined. However, the lack of region-level supervision in contrastive models and the limited ability of large vision language models to capture fine-grained representations in external validation lead to suboptimal performance on these tasks. To address these limitations, we propose Location-aware Fine-grained representation learning (LoFi), which jointly optimizes sigmoid, captioning, and location-aware captioning losses using a lightweight large language model. The location-aware captioning loss enables region-level supervision through grounding and dense captioning objectives, thereby facilitating fine-grained representation learning. Building upon these representations, we integrate a fine-grained encoder into retrieval-based in-context learning to enhance chest X-ray grounding across diverse settings. Extensive experiments demonstrate that our method achieves superior retrieval and phrase grounding performance on MIMIC-CXR and PadChest-GR.

Instruction-Free Tuning of Large Vision Language Models for Medical Instruction Following

Large vision language models (LVLMs) have demonstrated impressive performance across a wide range of tasks. These capabilities largely stem from visual instruction tuning, which fine-tunes models on datasets consisting of curated image-instruction-output triplets. However, in the medical domain, constructing large-scale, high-quality instruction datasets is particularly challenging due to the need for specialized expert knowledge. To address this issue, we propose an instruction-free tuning approach that reduces reliance on handcrafted instructions, leveraging only image-description pairs for fine-tuning. Specifically, we introduce a momentum proxy instruction as a replacement for curated text instructions, which preserves the instruction-following capability of the pre-trained LVLM while promoting updates to parameters that remain valid during inference. Consequently, the fine-tuned LVLM can flexibly respond to domain-specific instructions, even though explicit instructions are absent during fine-tuning. Additionally, we incorporate a response shuffling strategy to mitigate the model's over-reliance on previous words, facilitating more effective fine-tuning. Our approach achieves state-of-the-art accuracy on multiple-choice visual question answering tasks across SKINCON, WBCAtt, CBIS, and MIMIC-CXR datasets, significantly enhancing the fine-tuning efficiency of LVLMs in medical domains.

Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents

Test-time scaling has become a dominant paradigm for improving LLM agent reliability, yet current approaches treat compute as an abundant resource, allowing agents to exhaust token and tool budgets on redundant steps or dead-end trajectories. Existing budget-aware methods either require expensive fine-tuning or rely on coarse, trajectory-level heuristics that cannot intervene mid-execution. We propose the Budget-Aware Value Tree (BAVT), a training-free inference-time framework that models multi-hop reasoning as a dynamic search tree guided by step-level value estimation within a single LLM backbone. Another key innovation is a budget-conditioned node selection mechanism that uses the remaining resource ratio as a natural scaling exponent over node values, providing a principled, parameter-free transition from broad exploration to greedy exploitation as the budget depletes. To combat the well-known overconfidence of LLM self-evaluation, BAVT employs a residual value predictor that scores relative progress rather than absolute state quality, enabling reliable pruning of uninformative or redundant tool calls. We further provide a theoretical convergence guarantee, proving that BAVT reaches a terminal answer with probability at least $1-ε$ under an explicit finite budget bound. Extensive evaluations on four multi-hop QA benchmarks across two model families demonstrate that BAVT consistently outperforms parallel sampling baselines. Most notably, BAVT under strict low-budget constraints surpasses baseline performance at $4\times$ the resource allocation, establishing that intelligent budget management fundamentally outperforms brute-force compute scaling.

DUCX: Decomposing Unfairness in Tool-Using Chest X-ray Agents

Tool-using medical agents can improve chest X-ray question answering by orchestrating specialized vision and language modules, but this added pipeline complexity also creates new pathways for demographic bias beyond standalone models. We present ours (Decomposing Unfairness in Chest X-ray agents), a systematic audit of chest X-ray agents instantiated with MedRAX. To localize where disparities arise, we introduce a stage-wise fairness decomposition that separates end-to-end bias from three agent-specific sources: tool exposure bias (utility gaps conditioned on tool presence), tool transition bias (subgroup differences in tool-routing patterns), and model reasoning bias (subgroup differences in synthesis behaviors). Extensive experiments on tool-used based agentic frameworks across five driver backbones reveal that (i) demographic gaps persist in end-to-end performance, with equalized odds up to 20.79%, and the lowest fairness-utility tradeoff down to 28.65%, and (ii) intermediate behaviors, tool usage, transition patterns, and reasoning traces exhibit distinct subgroup disparities that are not predictable from end-to-end evaluation alone (e.g., conditioned on segmentation-tool availability, the subgroup utility gap reaches as high as 50%). Our findings underscore the need for process-level fairness auditing and debiasing to ensure the equitable deployment of clinical agentic systems. Code is available here: https://anonymous.4open.science/r/DUCK-E5FE/README.md

GSS: Gated Subspace Steering for Selective Memorization Mitigation in LLMs

Large language models (LLMs) can memorize and reproduce training sequences verbatim -- a tendency that undermines both generalization and privacy. Existing mitigation methods apply interventions uniformly, degrading performance on the majority of tokens that generalize normally. We show empirically that memorization is sparse, intermittent, and token-conditioned, suggesting that effective mitigation requires context-aware intervention rather than static parameter modification. To this end, we propose a novel and effective selective memorization mitigation method -- Gated Subspace Steering (GSS), which decomposes intervention into a probe (detecting memorization-relevant activations) and a steer (applying targeted correction only when the probe exceeds a threshold). The optimal probe-steer pair emerges from a principled optimization framework based on optimal subspace steering. Experiments on four benchmarks show GSS matches or exceeds state-of-the-art memorization reduction while requiring $100-1000 \times$ less compute than optimization-based alternatives. Furthermore, we provide new theoretical insights into the geometry of memorization in neural representations.

TextResNet: Decoupling and Routing Optimization Signals in Compound AI Systems via Deep Residual Tuning

Textual Gradient-style optimizers (TextGrad) enable gradient-like feedback propagation through compound AI systems. However, they do not work well for deep chains. The root cause of this limitation stems from the Semantic Entanglement problem in these extended workflows. In standard textual backpropagation, feedback signals mix local critiques with upstream contexts, leading to Attribution Ambiguity. To address this challenge, we propose TextResNet, a framework that reformulates the optimization process to achieve precise signal routing via four key innovations. Firstly, in the forward pass, it enforces Additive Semantic Deltas to preserve an Identity Highway for gradient flow. Secondly, in the backward pass, it introduces Semantic Gradient Decomposition via a Semantic Projector to disentangle feedback into causally independent subspaces. Thirdly, it implements Causal Routing, which routes projected signals to their specific components. Finally, it performs Density-Aware Optimization Scheduling to leverage the disentangled signals to dynamically allocate resources to key system bottlenecks. Our results show that TextResNet not only achieves superior performance compared to TextGrad, but also exhibits remarkable stability for agentic tasks in compound AI systems where baselines collapse. Code is available at https://github.com/JeanDiable/TextResNet.

AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent

While large language model (LLM) multi-agent systems achieve superior reasoning performance through iterative debate, practical deployment is limited by their high computational cost and error propagation. This paper proposes AgentArk, a novel framework to distill multi-agent dynamics into the weights of a single model, effectively transforming explicit test-time interactions into implicit model capabilities. This equips a single agent with the intelligence of multi-agent systems while remaining computationally efficient. Specifically, we investigate three hierarchical distillation strategies across various models, tasks, scaling, and scenarios: reasoning-enhanced fine-tuning; trajectory-based augmentation; and process-aware distillation. By shifting the burden of computation from inference to training, the distilled models preserve the efficiency of one agent while exhibiting strong reasoning and self-correction performance of multiple agents. They further demonstrate enhanced robustness and generalization across diverse reasoning tasks. We hope this work can shed light on future research on efficient and robust multi-agent development. Our code is at https://github.com/AIFrontierLab/AgentArk.