Related papers: R1-Fuzz: Specializing Language Models for Textual …
\textbf{RE}trieval-\textbf{A}ugmented \textbf{L}LM-based \textbf{M}achine \textbf{T}ranslation (REAL-MT) shows promise for knowledge-intensive tasks like idiomatic translation, but its reliability under noisy retrieval contexts remains…
Reinforcement Learning (RL) benefits Large Language Models (LLMs) for complex reasoning. Inspired by this, we explore integrating spatio-temporal specific rewards into Multimodal Large Language Models (MLLMs) to address the unique…
Fuzzing is a widely used technique for detecting vulnerabilities in smart contracts, which generates transaction sequences to explore the execution paths of smart contracts. However, existing fuzzers are falling short in detecting…
Reasoning-augmented search agents such as Search-R1, trained via reinforcement learning with verifiable rewards (RLVR), demonstrate remarkable capabilities in multi-step information retrieval from external knowledge sources. These agents…
Reinforcement learning (RL) offers a capable and intuitive structure for the fundamental sequential decision-making problem. Despite impressive breakthroughs, it can still be difficult to employ RL in practice in many simple applications.…
Reinforcement Learning (RL) has emerged as a dominant paradigm for end-to-end autonomous driving (AD). However, RL suffers from sample inefficiency and a lack of semantic interpretability in complex scenarios. Foundation Models,…
Reinforcement learning (RL) has become a standard paradigm for refining large language models (LLMs) beyond pre-training and instruction tuning. A prominent line of work is RL with verifiable rewards (RLVR), which leverages automatically…
Fuzzing has become a commonly used approach to identifying bugs in complex, real-world programs. However, interpreters are notoriously difficult to fuzz effectively, as they expect highly structured inputs, which are rarely produced by most…
Mathematical reasoning is a central challenge for large language models (LLMs), requiring not only correct answers but also faithful reasoning processes. Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising…
Reasoning has emerged as the next major frontier for language models (LMs), with rapid advances from both academic and industrial labs. However, this progress often outpaces methodological rigor, with many evaluations relying on…
Training reasoning language models (LMs) with reinforcement learning (RL) for one-hot correctness inherently relies on the LM being able to explore and solve its task with some chance at initialization. Furthermore, a key use case of…
Reinforcement learning (RL) finetuning has become a key technique for enhancing large language models (LLMs) on reasoning-intensive tasks, motivating its extension to vision-language models (VLMs). While RL-tuned VLMs improve on visual…
Fuzz testing is a fundamental technique employed to identify vulnerabilities within software systems. However, the process can be protracted and resource-intensive, especially when confronted with extensive codebases. In this work, I…
Inspired by the success of DeepSeek-R1, we explore the potential of rule-based reinforcement learning (RL) in large reasoning models. To analyze reasoning dynamics, we use synthetic logic puzzles as training data due to their controllable…
Recent studies have proposed leveraging Large Language Models (LLMs) as information retrievers through query rewriting. However, for challenging corpora, we argue that enhancing queries alone is insufficient for robust semantic matching;…
Among the many software vulnerability discovery techniques available today, fuzzing has remained highly popular due to its conceptual simplicity, its low barrier to deployment, and its vast amount of empirical evidence in discovering…
Recent advancements in Chain of Thought (COT) generation have significantly improved the reasoning capabilities of Large Language Models (LLMs), with reinforcement learning (RL) emerging as an effective post-training approach. Multimodal…
Large language models (LLMs)-empowered web agents enables automating complex, real-time web navigation tasks in enterprise environments. However, existing web agents relying on supervised fine-tuning (SFT) often struggle with generalization…
Text-to-SQL is a challenging task involving multiple reasoning-intensive subtasks, including natural language understanding, database schema comprehension, and precise SQL query formulation. Existing approaches often rely on handcrafted…
We propose TraceRL, a trajectory-aware reinforcement learning framework for diffusion language models (DLMs) that incorporates preferred inference trajectory into post-training, and is applicable across different architectures. Equipped…