5 results for "Tu, Songjun"
Showing 1–5 · 1.15 seconds · RSS
-
Preprint Full text
Dynamic Dual-Granularity Skill Bank for Agentic RL
Agentic reinforcement learning (RL) can benefit substantially from reusable experience, yet existing skill-based methods mainly extract trajectory-level guidance and often lack principled mechanisms for maintaining an evolving skill memory. We propose D2Skill, a dynamic dual-granularity skill bank…
-
Preprint Full text
Saliency-Guided Representation with Consistency Policy Learning for Visual Unsupervised Reinforcement Learning
Zero-shot unsupervised reinforcement learning (URL) offers a promising direction for building generalist agents capable of generalizing to unseen tasks without additional supervision. Among existing approaches, successor representations (SR) have emerged as a prominent paradigm due to their…
-
Preprint Full text
PaperAudit-Bench: Benchmarking Error Detection in Research Papers for Critical Automated Peer Review
Large language models can generate fluent peer reviews, yet their assessments often lack sufficient critical rigor when substantive issues are subtle and distributed across a paper. In this paper, we introduce PaperAudit-Bench, which consists of two components: (1) PaperAudit-Dataset, an error…
-
Preprint Full text
AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning
Agentic retrieval-augmented generation (RAG) systems enable large language models (LLMs) to solve complex tasks through multi-step interaction with external retrieval tools. However, such multi-step interaction often involves redundant search steps, incurring substantial computational cost and…
-
Preprint Full text
$π$-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data
Deep search agents have emerged as a promising paradigm for addressing complex information-seeking tasks, but their training remains challenging due to sparse rewards, weak credit assignment, and limited labeled data. Self-play offers a scalable route to reduce data dependence, but conventional…