arXiv:2604.21006v1 Announce Type: new Abstract: We introduce Deep FinResearch Bench, a practical and comprehensive evaluation framework for deep research (DR) agents in financial investment research. The benchmark assesses three dimensions of report quality: qualitative rigor, quantitative forecasting and valuation accuracy,…
arXiv:2604.21018v1 Announce Type: new Abstract: While scaling test-time compute can substantially improve model performance, existing approaches either rely on static compute allocation or sample from fixed generation distributions. In this work, we introduce a test-time compute allocation framework that jointly…
arXiv:2604.21003v1 Announce Type: new Abstract: AI agents are increasingly deployed on complex, domain-specific workflows — navigating enterprise web applications that require dozens of clicks and form fills, orchestrating multi-step research pipelines that span search, extraction, and synthesis, automating code review…
arXiv:2604.20995v1 Announce Type: new Abstract: Alignment faking, where a model behaves aligned with developer policy when monitored but reverts to its own preferences when unobserved, is a concerning yet poorly understood phenomenon, in part because current diagnostic tools remain limited.…
arXiv:2604.20987v1 Announce Type: new Abstract: Long horizon interactive environments are a testbed for evaluating agents skill usage abilities. These environments demand multi step reasoning, the chaining of multiple skills over many timesteps, and robust decision making under delayed rewards and…
arXiv:2510.18731v2 Announce Type: replace-cross Abstract: Large Language Models demonstrate strong capabilities in single-turn instruction following but suffer from Lost-in-Conversation (LiC), a degradation in performance as information is revealed progressively in multi-turn settings. Motivated by the current progress on Reinforcement Learning…
arXiv:2604.21036v1 Announce Type: new Abstract: Text-to-image(T2I) models like Stable Diffusion and DALL-E have made generative AI widely accessible, yet recent studies reveal that these systems often replicate societal biases, particularly in how they depict demographic groups across professions. Prompts such…
arXiv:2601.09253v2 Announce Type: replace-cross Abstract: While Supervised Fine-Tuning (SFT) and Rejection Sampling Fine-Tuning (RFT) are standard for LLM alignment, they either rely on costly expert data or discard valuable negative samples, leading to data inefficiency. To address this, we propose…
arXiv:2604.21044v1 Announce Type: new Abstract: In some complex domains, certain problem-specific decompositions can provide advantages over monolithic designs by enabling comprehension and specification of the design. In this paper we present an intuitive and tractable approach to reasoning over large…
arXiv:2604.17656v2 Announce Type: replace-cross Abstract: Video-to-music (V2M) is the fundamental task of creating background music for an input video. Recent V2M models achieve audiovisual alignment by typically relying on visual conditioning alone and provide limited semantic and stylistic controllability to…
