Related papers: RAGEN-2: Reasoning Collapse in Agentic RL

Looped Language Models (LoopLMs) enable efficient latent reasoning through depth recurrence, yet exhibit unreliable test-time scaling behavior: performance often peaks at a certain iteration depth and then collapses with further recurrence.…

Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) for Large Language Model (LLM) reasoning have been hindered by a persistent challenge: exploration collapse. The semantic homogeneity of random rollouts often traps…

Recent advancements in Large Language Models (LLMs) have generated growing interest in their structured reasoning capabilities, particularly in tasks involving abstraction and pattern recognition. The Abstraction and Reasoning Corpus (ARC)…

Large reasoning models (LRMs) aim to solve diverse and complex problems through structured reasoning. Recent advances in group-based policy optimization methods have shown promise in enabling stable advantage estimation without reliance on…

Large language models (LLMs) are increasingly deployed in settings where reasoning, such as multi-step problem solving and chain-of-thought, is essential. Yet, current evaluation practices overwhelmingly report single-run accuracy while…

Recent generations of language models have introduced Large Reasoning Models (LRMs) that generate detailed thinking processes before providing answers. While these models demonstrate improved performance on reasoning benchmarks, their…

Reinforcement learning with verifiable rewards (RLVR) has proven effective in eliciting complex reasoning in large language models (LLMs). However, standard RLVR training often leads to excessively verbose processes (in reasoning tasks) and…

Recent advances in large language models (LLMs) have demonstrated significant potential in hardware design automation, particularly in using natural language to synthesize Register-Transfer Level (RTL) code. Despite this progress, a gap…

Generative Reward Models (GenRMs) and LLM-as-a-Judge exhibit deceptive alignment by producing correct judgments for incorrect reasons, as they are trained and evaluated to prioritize Outcome Accuracy, which undermines their ability to…

With the advent of foundation models, prompt tuning has positioned itself as an important technique for directing model behaviors and eliciting desired responses. Prompt tuning regards selecting appropriate keywords included into the input,…

Hybrid reasoning systems that combine learned components with model-based inference are increasingly deployed in tool-augmented decision loops, yet their runtime behavior under partial observability and sustained evidence mismatch remains…

Vision-Language Models (VLMs) have achieved impressive performance across a wide range of multimodal tasks, yet they often exhibit inconsistent behavior when faced with semantically equivalent inputs, undermining their reliability and…

This paper explores the challenges of test-time scaling of large language models (LLMs), regarding both the data and inference efficiency. We highlight the diversity of multi-lingual reasoning based on our pilot studies, and then introduce…

Reinforcement learning (RL) training is inherently unstable due to factors such as moving targets and high gradient variance. Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning from AI Feedback (RLAIF) can…

Reinforcement learning (RL) has become a key approach for enhancing reasoning in large language models (LLMs), yet scalable training is often hindered by the rapid collapse of policy entropy, which leads to premature convergence and…

Multi-agent debate (MAD) systems improve LLM reasoning through iterative deliberation, but remain vulnerable to debate collapse, a failure type where final agent decisions are compromised on erroneous reasoning. Existing methods lack…

The success of Deepseek-R1 has drawn the LLM community's attention to reinforcement learning (RL) methods like GRPO. However, such rule-based 0/1 outcome reward methods lack the capability to regulate the intermediate reasoning processes…

Reasoning benchmarks such as the Abstraction and Reasoning Corpus (ARC) and ARC-AGI are widely used to assess progress in artificial intelligence and are often interpreted as probes of core, so-called ``fluid'' reasoning abilities. Despite…

We argue that translation quality alone is not a sufficient metric for measuring knowledge transfer in multilingual neural machine translation. To support this claim, we introduce Representational Transfer Potential (RTP), which measures…

Automated \enquote{LLM-as-a-Judge} frameworks have become the de facto standard for scalable evaluation across natural language processing. For instance, in safety evaluation, these judges are relied upon to evaluate harmfulness in order to…