13 papers
AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards
Xin Gao, Yifan Yang, Xin Li +13
Generating information-rich visual artifacts such as slides, posters, and dashboards as code is appealing because the outputs are structured, editable, and verifiable. Yet code mod…
ReDeck: Step-Level Render-Grounded Refinement for Document-to-Slide Generation
Muzhao Tian, Zezi Zeng, Yifan Yang +14
Document-to-slide generation is challenging because slides are dense editable artifacts that require both faithful content selection and precise spatial layout. Recent slide agents…
From Static Context to Calibrated Interactive RL: Mitigating Distribution Shift in Multi-turn Dialogue with Aligned Simulator
Xiaohua Wang, Jiakang Yuan, Zisu Huang +5
A long-standing goal of the research community is to develop highly interactive LLM-based dialogue agents. Recent research focuses on optimizing policies based on fixed offline log…
From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
Zisu Huang, Jingwen Xu, Yifan Yang +13
Language agents increasingly improve by reusing \emph{skills} -- structured procedural artifacts distilled from past experience. In particular, \emph{domain-level} and \emph{model-…
Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges
Xiaohua Wang, Muzhao Tian, Yuqi Zeng +20
Reinforcement Learning from Human Feedback (RLHF) and related alignment paradigms have become central to steering large language models (LLMs) and multimodal large language models…
Beyond identifiability: Learning causal representations with few environments and finite samples
Inbeom Lee, Tongtong Jin, Bryon Aragam
We provide explicit, finite-sample guarantees for learning causal representations from data with a sublinear number of environments. Causal representation learning seeks to provide…
TRIP-Bench: A Benchmark for Long-Horizon Interactive Agents in Real-World Scenarios
Yuanzhe Shen, Zisu Huang, Zhengyuan Wang +14
As LLM-based agents are deployed in increasingly complex real-world settings, existing benchmarks underrepresent key challenges such as enforcing global constraints, coordinating m…
Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generation
Changze Lv, Jie Zhou, Wentao Zhao +13
Nowadays, developing reliable DeepResearch-style long-form report generation remains challenging, as training and evaluation lack verifiable reward signals. Accordingly, rubric-bas…
BatCoder: Self-Supervised Bidirectional Code-Documentation Learning via Back-Translation
Jingwen Xu, Yiyang Lu, Zisu Huang +9
Training LLMs for code-related tasks typically depends on high-quality code-documentation pairs, which are costly to curate and often scarce for niche programming languages. We int…
CSSG: Measuring Code Similarity with Semantic Graphs
Yiyang Lu, Jingwen Xu, Changze Lv +6
Existing code similarity metrics, such as BLEU, CodeBLEU, and TSED, largely rely on surface-level string overlap or abstract syntax tree structures, and often fail to capture deepe…
Benchmark^2: Systematic Evaluation of LLM Benchmarks
Qi Qian, Chengsong Huang, Jingwen Xu +13
The rapid proliferation of benchmarks for evaluating large language models (LLMs) has created an urgent need for systematic methods to assess benchmark quality itself. We propose B…
Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human-Agent Interaction
Muzhao Tian, Zisu Huang, Xiaohua Wang +8
As LLM-based agents are increasingly used in long-term interactions, cumulative memory is critical for enabling personalization and maintaining stylistic consistency. However, most…
RECAST: Expanding the Boundaries of LLMs' Complex Instruction Following with Multi-Constraint Data
Zhengkang Guo, Wenhao Liu, Mingchen Xie +13
Large language models (LLMs) are increasingly expected to tackle complex tasks, driven by their expanding applications and users' growing proficiency in crafting sophisticated prom…