Related papers: A Rubric-Supervised Critic from Sparse Real-World …

Despite recent progress in Large Language Model (LLM) Agents for Software Engineering (SWE) tasks, end-to-end fine-tuning typically relies on verifiable terminal rewards such as whether all unit tests pass. While these binary signals…

Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for complex reasoning tasks with clear correctness signals such as math and coding. However, extending it to real-world reasoning tasks is challenging, as evaluation…

Large language models (LLMs) achieve strong downstream performance largely due to abundant supervised fine-tuning (SFT) data. However, high-quality SFT data in knowledge-intensive domains such as humanities, social sciences, medicine, law,…

LLM-based automated scoring approaches near-human performance, but scaling to new tasks remains bottlenecked by the per-item human configuration of upstream stages such as rubric construction. Human experts bypass this bottleneck through…

Agentic systems are evaluated on benchmarks where agents interact with environments to solve tasks. Most papers report a pass@1 score computed from a single run per task, assuming this gives a reliable performance estimate. We test this…

Rubrics and oral feedback are approaches to help students improve performance and meet learning outcomes. However, their effect on the actual improvement achieved is inconclusive. This paper evaluates the effect of rubrics and oral feedback…

Interactive reinforcement learning has shown promise in learning complex robotic tasks. However, the process can be human-intensive due to the requirement of a large amount of interactive feedback. This paper presents a new method that uses…

Nowadays, training and evaluating DeepResearch-generated reports remain challenging due to the lack of verifiable reward signals. Accordingly, rubric-based evaluation has become a common practice. However, existing approaches either rely on…

As agents based on large language models are increasingly deployed to long-horizon tasks, maintaining their alignment with stakeholder preferences becomes critical. Effective alignment in such settings requires reward models that are…

Formative feedback is widely recognized as one of the most effective drivers of student learning, yet it remains difficult to implement equitably at scale. In large or low-resource courses, instructors often lack the time, staffing, and…

A reliable critic is central to on-policy actor-critic learning. But it becomes challenging to learn a reliable critic in a multi-agent sparse reward scenario due to two factors: 1) The joint action space grows exponentially with the number…

Reinforcement fine-tuning (RFT) often suffers from reward over-optimization, where a policy model hacks the reward signals to achieve high scores while producing low-quality outputs. Our theoretical analysis shows that the key lies in…

Iterative self-refinement is a popular inference-time reliability technique, but its effectiveness in code-mode tool use depends heavily on the structure of the feedback signal: unstructured critique helps inconsistently across models, and…

Training reliable tool-augmented agents remains a significant challenge, largely due to the difficulty of credit assignment in multi-step reasoning. While process-level reward models offer a promising direction, existing LLM-based judges…

Reinforcement learning with verifiable rewards has made post-training highly effective when correctness can be checked automatically. However, many important model behaviors require satisfying several qualitative criteria at once.…

Large language models can fail in critic interaction not only by answering incorrectly, but also by abandoning an initially correct scientific solution after user criticism. This is especially risky in scientific reasoning, where user…

Training critiquing language models to assess and provide feedback on model outputs is a promising way to improve LLMs for complex reasoning tasks. However, existing approaches typically rely on stronger supervisors for annotating critique…

Positive feedback via likes and awards is central to online governance, yet which attributes of users' posts elicit rewards -- and how these vary across authors and communities -- remains unclear. To examine this, we combine…

We fine-tune large language models to write natural language critiques (natural language critical comments) using behavioral cloning. On a topic-based summarization task, critiques written by our models help humans find flaws in summaries…

Large language models (LLMs) are increasingly used for writing and review support, but their usefulness depends on context-dependent criteria, such as expert preferences or organization-specific conventions, that are often tacit,…