11 papers
Probe to Act: Elevating Browser-Use Agent via Active Visual Probing
Keliang Li, Heng Wang, Chen Hu +3
Browser-use agents require seamless alignment between structured web metadata and visual information, while preserving relevant context across long interactions. Existing interface…
onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction
Lei Yang, Mengyin Liu, Jia Wang +9
We present onPanda, an interactive tool for efficiently annotating LLM alignment data and agent trajectories. onPanda adopts token-level correction as its core interaction: while r…
StepAudio 3 Realtime Technical Report
Bin Lin, Bo Zhao, Boyang Zhang +87
Realtime spoken interaction demands deep reasoning, prompt responses, and fluid turn-taking. We present StepAudio 3 Realtime, an audio-language foundation model organized around a…
SpotAgent: Grounding Visual Geo-localization in Large Vision-Language Models through Agentic Reasoning
Furong Jia, Ling Dai, Wenjin Deng +4
Large Vision-Language Models (LVLMs) have demonstrated strong reasoning capabilities in geo-localization, yet they often struggle in real-world scenarios where visual cues are spar…
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters
Ailin Huang, Ang Li, Aobo Kong +213
We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency. We focus on what matters most wh…
Learning to Compress: Unlocking the Potential of Large Language Models for Text Representation
Yeqin Zhang, Yizheng Zhao, Chen Hu +4
Text representation plays a critical role in tasks like clustering, retrieval, and other downstream applications. With the emergence of large language models (LLMs), there is incre…
Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards
Haoran He, Yuxiao Ye, Qingpeng Cai +4
RL with Verifiable Rewards (RLVR) has emerged as a promising paradigm for improving the reasoning abilities of large language models (LLMs). Current methods rely primarily on polic…
GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging
Ziyi Ni, Huacan Wang, Shuo Zhang +15
Beyond scratch coding, exploiting large-scale code repositories (e.g., GitHub) for practical tasks is vital in real-world software development, yet current benchmarks rarely evalua…
SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents
Jiaye Lin, Yifu Guo, Yuzhen Han +11
Large Language Model (LLM)-based agents have recently shown impressive capabilities in complex reasoning and tool use via multi-step interactions with their environments. While the…
DialogueReason: Rule-Based RL Sparks Dialogue Reasoning in LLMs
Yubo Shu, Zhewei Huang, Xin Wu +3
We propose DialogueReason, a reasoning paradigm that uncovers the lost roles in monologue-style reasoning models, aiming to boost diversity and coherency of the reasoning process.…
Unearthing Gems from Stones: Policy Optimization with Negative Sample Augmentation for LLM Reasoning
Zhaohui Yang, Yuxiao Ye, Shilei Jiang +4
Recent advances in reasoning language models have witnessed a paradigm shift from short to long CoT pattern. Given the substantial computational cost of rollouts in long CoT models…