Related papers: GLOVE: Global Verifier for LLM Memory-Environment …

The reasoning capabilities of large language models (LLMs) have been significantly improved through reinforcement learning (RL). Nevertheless, LLMs still struggle to consistently verify their own reasoning traces. This raises the research…

We introduce Reinforcement Learning (RL) with Adaptive Verifiable Environments (RLVE), an approach using verifiable environments that procedurally generate problems and provide algorithmically verifiable rewards, to scale up RL for language…

Large Language Model (LLM) reasoning for complex tasks inherently involves a trade-off between solution accuracy and computational efficiency. The subsequent step of verification, while intended to improve performance, further complicates…

Despite the syntactic fluency of Large Language Models (LLMs), ensuring their logical correctness in high-stakes domains remains a fundamental challenge. We present a neurosymbolic framework that combines LLMs with SMT solvers to produce…

Large language models (LLMs) have shown significant general language understanding abilities. However, there has been a scarcity of attempts to assess the logical reasoning capacities of these LLMs, an essential facet of natural language…

Verifiers--functions assigning rewards to agent behavior--have been key to AI progress in math, code, and games. However, extending gains to domains without clear-cut success criteria remains a challenge: while humans can recognize desired…

Large Language Models (LLMs) possess general world knowledge but often struggle to generate precise predictions in structured, domain-specific contexts such as simulations. These limitations arise from their inability to ground their broad,…

Self-improvement is a significant techniques within the realm of large language model (LLM), aiming to enhance the LLM performance without relying on external data. Despite its significance, generally how LLM performances evolve during the…

Large language models (LLMs) have been increasingly applied to tasks in language understanding and interactive decision-making, with their impressive performance largely attributed to the extensive domain knowledge embedded within them.…

Learning open-vocabulary physical skills for simulated agents presents a significant challenge in artificial intelligence. Current reinforcement learning approaches face critical limitations: manually designed rewards lack scalability…

Combining Large Language Models (LLMs) with Reinforcement Learning (RL) enables agents to interpret language instructions more effectively for task execution. However, LLMs typically lack direct perception of the physical environment, which…

Vision-Language Models (VLMs) excel at visual understanding but often suffer from visual hallucinations, where they generate descriptions of nonexistent objects, actions, or concepts, posing significant risks in safety-critical…

Large language models (LLMs) have emerged as effective action policies for sequential decision-making (SDM) tasks due to their extensive prior knowledge. However, this broad yet general knowledge is often insufficient for specific…

Large vision-language models (LVLMs) have shown remarkable abilities in understanding visual information with human languages. However, LVLMs still suffer from object hallucination, which is the problem of generating descriptions that…

Using LLMs to evaluate text, that is, LLM-as-a-judge, is increasingly being used at scale to augment or even replace human annotations. As such, it is imperative that we understand the potential biases and risks of doing so. In this work,…

Reinforcement Learning (RL) has emerged as a pivotal mechanism for enhancing the complex reasoning capabilities of Multimodal Large Language Models (MLLMs). However, prevailing paradigms typically rely on solitary rollout strategies where…

There is considerable confusion about the role of Large Language Models (LLMs) in planning and reasoning tasks. On one side are over-optimistic claims that LLMs can indeed do these tasks with just the right prompting or self-verification…

Large Language Models (LLMs) internalize vast world knowledge as parametric memory, yet inevitably inherit the staleness and errors of their source corpora. Consequently, ensuring the reliability and malleability of these internal…

Machine unlearning has the potential to improve the safety of large language models (LLMs) by removing sensitive or harmful information post hoc. A key challenge in unlearning involves balancing between forget quality (effectively…

Verifying the complex and multi-step reasoning of Large Language Models (LLMs) is a critical challenge, as holistic methods often overlook localized flaws. Step-by-step validation is a promising alternative, yet existing methods are often…