The paper introduces Responsible Contrastive Soft Prompting (RCSP), a parameter-efficient method using soft prompts to improve LLM reliability by simultaneously suppressing hallucinations, encouraging…

The paper introduces Evidence-Carrying Agents (ECA) to prevent multimodal agents from executing privileged actions based on unsupported or hallucinated perceptual claims, achieving near-zero unsafe ex…

The paper proposes CSMR, a cognitive scheduling framework that allows a language model to dynamically decide when to acquire task-relevant visual evidence, significantly improving multimodal reasoning…

This paper analyzes failure modes in collaborative visual reasoning systems, demonstrating that naive shared workspaces can amplify hallucinations and proposing diagnostics for improving communication…

The paper proposes Reasoning-Conditioned Direct Preference Optimization (RC-DPO) to effectively mitigate hallucinations in multimodal large reasoning models by explicitly conditioning the preference o…

The paper proposes a memory-augmented, three-stage agentic pipeline that significantly reduces LLM hallucinations and improves operational efficiency by integrating semantic caching and advanced obser…

The paper introduces CHARM, a novel framework that detects and mitigates cascading hallucination—the amplification of errors across multi-step agentic RAG pipelines—achieving an 82.1% reduction in err…

This paper proposes a method to recover recoverability structure from failed traces of post-trained language models, enabling test-time routing and post-training analysis.

The paper explains the 'table-chart gap' in scientific claim verification by showing that multimodal LLMs successfully encode information from charts but fail to route it to the final prediction layer…

The paper introduces LL-Bench, a comprehensive benchmark for evaluating large-scale generative models on low-level vision tasks, and proposes LL-Score, an MLLM-based evaluator that better aligns quali…

The paper introduces the Image Reconstruction Game, a benchmark showing that the quality of the descriptive model is the primary determinant of image reconstruction success, while the generator's role…

The paper introduces a Hybrid Utility Minimum Bayes Risk (HUMBR) framework to significantly reduce hallucinations in high-stakes enterprise AI workflows, outperforming standard consistency methods.

VLA-Trace is a diagnostic framework that analyzes Vision-Language-Action (VLA) models by tracing their internal representations and external behaviors, revealing that while these models are good at vi…

The paper introduces EASE, a method that enhances multimodal Reinforcement Learning with Verifiable Rewards (RLVR) by providing spatial attention supervision anchored to visual evidence, significantly…

The paper proposes BRACS, a training-free steering framework that adaptively corrects visual grounding failures in large vision-language models, significantly reducing object hallucination without sac…

The paper introduces FraudBench, a multimodal benchmark designed to detect AI-generated fraudulent refund evidence, finding that current AI models struggle significantly with claim-conditioned fake-da…

The paper introduces HOPM, a hierarchical online prompt mutation framework that significantly improves the performance of language models in high-stakes evidence document generation by integrating dua…

The paper introduces extsc{Ptah}, a multi-agent harness designed to improve verifiable multimodal deep research by orchestrating the entire report generation process, ensuring factual grounding and v…

The paper proposes a unified framework that decouples long-video reasoning into semantic and visual evidence, significantly improving performance on the HD-EPIC VQA Challenge.