…Shijue Huang , , , , , , , , , Abstract A visual-native agent harness with image bank reference protocol enables reusable intermediate visual evidence and closed-loop data generation that improves multimodal deep search performance across multiple benchmarks…
…In SFT, the drafter learns from fixed target-generated trajectories, whereas during speculative decoding it is evaluated on blocks proposed under its own policy. This motivates on-policy distillation (OPD), where the…
…We further observe that performance degrades as more constraints accumulate, with user constraints posing a particularly large challenge and failures often stemming from weaker physical grounding and reduced effectiveness. These results establish…
…Wangcheng Tao , , Abstract Self-Evolving Prompt Optimization (SePO) enhances agent performance by jointly optimizing both task and prompt agent system prompts through evolutionary search, demonstrating superior accuracy across diverse benchmarks. Generated by…
…Utilizing the expert-verified verbatim transcriptions and grading reports of student solutions, we simultaneously evaluate various MLLMs' upstream recognition fidelity and downstream auto-grading performance. Our evaluation uncovers an astonishing scale of…
…The following papers were recommended by the Semantic Scholar API When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel (2026) The Detection-Extraction Gap…
…However, existing methods often rely on fixed steering directions or task-specific intervention modules, making them difficult to adapt to fine-grained concepts and compositional constraints. We propose UniSteer, a text-guided…
…Sanitization confines the on-device LLM to proposing which spans to mask, while a deterministic registry performs all substitution and reversal, keeping actions directly executable on device. On three agentic benchmarks under…
…Venkata Pushpak Teja Menta Abstract A self-contained text-to-speech to speech-to-text flywheel approach significantly improves niche-domain Indic automatic speech recognition performance through synthetic data generation and low…
…AI-generated summary Large language models have achieved remarkable success under the autoregressive paradigm , yet high-quality text generation need not be tied to a fixed left-to-right order. Existing alternatives…