Related papers: ExecVerify: White-Box RL with Verifiable Stepwise …

Language models trained with reinforcement learning (RL) can engage in reward hacking--the exploitation of unintended strategies for high reward--without revealing this behavior in their chain-of-thought reasoning. This makes the detection…

As large language models become smaller and more efficient, small reasoning models (SRMs) are crucial for enabling chain-of-thought (CoT) reasoning in resource-constrained settings. However, they are prone to faithfulness hallucinations,…

Large language models have achieved significant reasoning improvements through reinforcement learning with verifiable rewards (RLVR). Yet as model capabilities grow, constructing high-quality reward signals becomes increasingly difficult,…

Large Language Models (LLMs) show great promise in complex reasoning, with Reinforcement Learning with Verifiable Rewards (RLVR) being a key enhancement strategy. However, a prevalent issue is ``superficial self-reflection'', where models…

Reinforcement learning with verifiable rewards (RLVR) has demonstrated superior performance in enhancing the reasoning capability of large language models (LLMs). However, this accuracy-oriented learning paradigm often suffers from entropy…

Most progress in recent coder models has been driven by supervised fine-tuning (SFT), while the potential of reinforcement learning (RL) remains largely unexplored, primarily due to the lack of reliable reward data/model in the code domain.…

As language models accelerate scientific research by automating hypothesis generation and implementation, a new bottleneck emerges: evaluating and filtering hundreds of AI-generated ideas without exhaustive experimentation. We ask whether…

Accurate chart comprehension represents a critical challenge in advancing multimodal learning systems, as extensive information is compressed into structured visual representations. However, existing vision-language models (VLMs) frequently…

Large language models (LLMs) increasingly rely on reinforcement learning (RL) to enhance their reasoning capabilities through feedback. A critical challenge is verifying the consistency of model-generated responses and reference answers,…

Reinforcement Learning with Verifiable Rewards ( RLVR ) has emerged as a transformative paradigm for enhancing the reasoning capabilities of Large Language Models ( LLMs), yet its potential in 3D scene understanding remains under-explored.…

Applying reinforcement learning to improve factual accuracy in knowledge-intensive question answering faces a reward design dilemma. Response-level rewards provide only coarse supervision and cannot distinguish correct from incorrect…

Code generation and understanding are critical capabilities for large language models (LLMs). Thus, most LLMs are pretrained and fine-tuned on code data. However, these datasets typically treat code as static strings and rarely exploit the…

While Reinforcement Learning with Verifiable Rewards (RLVR) is effective for deterministically checkable tasks, many vision-language tasks are partially verifiable, demanding multi-criteria supervision (e.g., perceptual details, reasoning…

Large Language Models (LLMs) can generate plausible code, but in settings that require exact stdin/stdout behavior they frequently produce programs that compile yet fail tests, and in some cases they introduce security-sensitive patterns.…

We aim to improve the reasoning capabilities of language models via reinforcement learning (RL). Recent RL post-trained models like DeepSeek-R1 have demonstrated reasoning abilities on mathematical and coding tasks. However, prior studies…

Large Language Models (LLMs) have demonstrated remarkable progress in complex reasoning tasks through both post-training and test-time scaling laws. While prevalent test-time scaling approaches are often realized by using external reward…

Reinforcement Learning with Verifiable Rewards (RLVR) improves multimodal reasoning by rewarding verifiable final answers. Yet answer-correct trajectories may still rely on incomplete derivations, weak evidence, or statements that…

Test-time scaling methods have seen a rapid increase in popularity for its computational efficiency and parameter-independent training to improve reasoning performance on Large Language Models. One such method is called budget forcing, a…

Test-time scaling has been shown to substantially improve large language models' (LLMs) mathematical reasoning. However, for a large portion of mathematical corpora, especially theorem proving, RLVR's scalability is limited: intermediate…

Large Language Models excel at code generation yet struggle with complex programming tasks that demand sophisticated reasoning. To bridge this gap, traditional process supervision relies on learned reward models requiring costly training…