11 papers
Repairing LLM-Generated Specifications with Deterministic Diagnosis
Giovanni Vaccarino, Emanuele La Malfa, Dehai Min +6
Large language models (LLMs) are increasingly used as formalizers: given a reasoning problem expressed in natural language, they produce a formal specification that a symbolic solv…
TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces
Dehai Min, Daoan Zhang, Yiming Zeng +13
An agent can complete a task while exhibiting undesirable behavior during execution. Developers need tests for the specific behaviors encountered in deployment, beyond fixed benchm…
Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning
Fangxu Yu, Tao Feng, Dehai Min +6
Audio reasoning is essential for machine understanding of the acoustic world. Reinforcement learning with verifiable rewards can elicit such reasoning, yet existing reward designs…
TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning
Fangxu Yu, Tao Feng, Dehai Min +3
Time series reasoning is essential for real-world problem-solving. While both Large Language Models (LLMs) and Vision-Language Models (VLMs) can reason about time-series data, thei…
One Skill, Two Masters: Serving Users and Attackers through Skill Injection
Haochang Hao, Dehai Min, Zhifang Zhang +5
Large language model agents use skills that package reusable instructions, code, and resources. Existing skill-injection attacks exploit trust in these packages by adding malicious…
Beyond Math and Code: Lightweight Corpus-Grounded Process Rewards for Factual Question Answering
Shicheng Fan, Haochang Hao, Dehai Min +10
Process supervision during reinforcement learning (RL) post-training matters in factual question answering (QA) because responses receiving positive response-level rewards can stil…
Stop When Reasoning Converges: Semantic-Preserving Early Exit for Reasoning Models
Dehai Min, Giovanni Vaccarino, Huiyi Chen +3
Large Reasoning Models (LRMs) achieve strong performance by generating long chains of thought (CoT), but often overthink, continuing to reason after a solution has already stabiliz…
Latent Thoughts Tuning: Bridging Context and Reasoning with Fused Information in Latent Tokens
Weihao Liu, Dehai Min, Lu Cheng
While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it constrains the model's thoughts to a discrete vocabulary space. Rec…
EpiQAL: Benchmarking Large Language Models in Epidemiological Question Answering and Reasoning
Mingyang Wei, Dehai Min, Zewen Liu +8
Reliable epidemiological reasoning requires synthesizing study evidence to infer disease burden, transmission dynamics, and intervention effects at the population level. Existing m…
QuCo-RAG: Quantifying Uncertainty from the Pre-training Corpus for Dynamic Retrieval-Augmented Generation
Dehai Min, Kailin Zhang, Tongtong Wu +1
Dynamic Retrieval-Augmented Generation adaptively determines when to retrieve during generation to mitigate hallucinations in large language models (LLMs). However, existing method…
MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs
Huiyi Chen, Jiawei Peng, Dehai Min +5
Evaluating the robustness of Large Vision-Language Models (LVLMs) is essential for their continued development and responsible deployment in real-world applications. However, exist…