Sitong Wang

Author directory

2026

Large language models (LLMs) have recently demonstrated remarkable capabilities in machine translation (MT). However, most advanced MT-specific LLMs rely heavily on external supervision during training, such as human-annotated reference data or trained reward models (RMs), which are expensive to obtain and difficult to scale. To address this limitation, we propose Simple Self-Rewarding (SSR), a reinforcement learning (RL) framework for MT that is reference-free and relies solely on self-judging rewards. Using only 13K monolingual examples and Qwen-2.5-7B as the backbone, SSR-Zero-7B outperforms existing MT-specific LLMs as well as larger general LLMs such as Qwen2.5-32B-Instruct on English ↔ Chinese translation benchmarks including WMT23, WMT24, and FLORES200. It further demonstrates strong generalization to low-resource language pairs. In addition, when augmented with external supervision from COMET, our strongest model, SSR-X-Zero-7B, surpasses all existing open-source models under 72B parameters and performs competitively with leading closed-source systems in English ↔ Chinese translation. Our analysis highlights the effectiveness and generalizability of the self-rewarding mechanism relative to external LLM-as-a-judge approaches and demonstrates its complementary benefits when combined with trained RMs. We will publicly release our code, data, and models.
Human-AI collaboration on complex planning goals is bottlenecked by how LLM interfaces handle context: users must manually curate and re-surface relevant information across long and unstructured chat histories. Despite advances in long-context prompting and memory-augmented retrieval, this burden remains unresolved: users still have to identify and supply the right context at each decision point, regardless of how much the model can store or surface. We propose JumpStarter, a system that enables LLMs to collaborate with humans on complex goals by dynamically decomposing tasks to help users manage context. We specifically introduce task-structured context curation, a framework that breaks down a user’s goal into a hierarchy of actionable subtasks and scopes context to localized decision points, enabling finer-grained personalization and reuse. The framework is realized through three core mechanisms: context elicitation, selection, and reuse. In a within-subjects user study, plans produced with JumpStarter were rated substantially higher in quality than those produced with ChatGPT. A complementary automatic simulation study shows that JumpStarter consistently outperforms ChatGPT baselines, planning and memory agents, and workflow ablations. These findings show that effective human-AI planning depends not on the volume of context provided, but on attaching the right context to the right subtask at the right time.