We have 15 of 188 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
QREF, a plug-and-play Query Refiner and Evidence Filter that rewrites search queries according to the current reasoning intent while ensuring complementary coverage across each search batch, improves the performance of DeepSearch agents across four challenging benchmarks.
This paper proposes ToolCUA, an end-to-end agent designed to learn optimal GUI-Tool path selection through a staged training paradigm, and introduces an Interleaved GUI-Tool Trajectory Scaling Pipeline that repurposes abundant static GUI trajectories and synthesizes a grounded tool library, enabling diverse GUI-Tool tr...
CCTU, a benchmark for evaluating LLM tool use under complex constraints, is introduced and nine state-of-the-art LLMs are evaluated in both thinking and non-thinking modes, showing that models violate constraints in over 50% of cases.
A gradient-level characterization of reverse-KL OPD trained with the K2 estimator, with Surprise-aware Reweighting (SuRe), a detached, bounded weighting rule that further amplifies this existing allocation.
MuseCritic is introduced, a semi-scalar reward model that generates a natural-language critique covering five aesthetic dimensions and uses it as an intermediate representation to predict continuous reward scores, showing that critique-conditioned reward modeling reduces scoring error and provides an effective optimiza...
SPIEval is introduced, a human-curated benchmark grounded in five cognitive capabilities that exposes fundamental limitations of current LLM-based mobile assistants and motivates future research in this direction.
A critique-in-the-loop self-improvement method that incorporates critique-based supervision into the actor’s self-training process and improves the actor’s exploration efficiency and solution diversity, especially on challenging queries, leading to a stronger actor model.
This tutorial provides a comprehensive, end-to-end view of LLM interpretability, transitioning from microscopic neural analysis to macroscopic application and deployment, and explores how these interpretability paradigms scale and inspire the design of frontier architectures, agentic systems, and thinking models.
EntangleCodec is proposed, a unified discrete audio tokenizer that learns caption-aligned semantic-acoustic representations before quantization that achieves reconstruction quality competitive with specialized codecs, outperforms all codec-based baselines on audio understanding, and supports both TTS and TTA generation...
A novel textual representation of fault trees is proposed, and a benchmark for multi-turn dialogue systems that emphasizes robust interaction in complex environments is constructed, evaluating a model's ability to assist in malfunction localization.
CAFE (Coupled Agent--Feedback Evolution), a framework in which a shared-parameter model alternates between search-agent and critic roles, is introduced, suggesting that a self-improving search agent needs feedback that co-evolves with the policy it guides.
Pera describes a persistent agent organized around perception and control components that continually perceive service-relevant signals from episodic task executions, internal context, and changes in the surrounding environment, and use these signals to construct lifecycle tasks.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
