Reward Is Enough: LLMs Are In-Context Reinforcement Learners

• URL: http://arxiv.org/abs/2506.06303v1
• Date: Wed, 21 May 2025 16:15:01 GMT
• Title: Reward Is Enough: LLMs Are In-Context Reinforcement Learners
• Authors: Kefan Song, Amir Moeini, Peng Wang, Lei Gong, Rohan Chandra, Yanjun Qi, Shangtong Zhang,
• Abstract summary: Reinforcement learning (RL) is a human-designed framework for solving sequential decision making problems.<n>In this work, we demonstrate that, surprisingly, RL emerges in LLM's (Large Language Model) inference time.<n>We propose a novel multi-round prompting framework called ICRL prompting.
• Score: 27.916966728955348
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning (RL) is a human-designed framework for solving sequential decision making problems. In this work, we demonstrate that, surprisingly, RL emerges in LLM's (Large Language Model) inference time -- a phenomenon known as in-context RL (ICRL). Specifically, we propose a novel multi-round prompting framework called ICRL prompting. The goal is to prompt the LLM to complete a task. After the LLM generates a response at the current round, we give numerical scalar feedbacks for the response, called the rewards. At the next round, we prompt the LLM again with the same task and a context consisting of all previous responses and rewards. We observe that the quality of the LLM's response increases as the context grows. In other words, the LLM is able to maximize the scalar reward signal in the inference time, just like an RL algorithm. We evaluate ICRL prompting in three benchmarks (Game of 24, creative writing, and ScienceWorld) and demonstrate significant performance improvements over baseline methods such as Self-Refine and Reflexion. Surprisingly, in some experiments the reward signals are generated by the LLM itself, yet performance improvements are still observed from ICRL prompting, offering a promising paradigm for scaling test-time compute.

Related papers

• Large Language Model-enhanced Reinforcement Learning for Low-Altitude Economy Networking [71.83640290222928]
  Low-Altitude Economic Networking (LAENet) aims to support diverse flying applications below 1,000 meters.<n>Complex decision-making, resource constraints, and environmental uncertainty pose significant challenges to the development of the LAENet.
  arXiv  Detail & Related papers  (2025-05-27T11:25:42Z)
• On the Emergence of Thinking in LLMs I: Searching for the Right Intuition [34.32871896067864]
  We propose a post-training framework called Reinforcement Learning via Self-Play (RLSP)<n> RLSP involves three steps: supervised fine-tuning with human or synthetic demonstrations of the reasoning process, using an exploration reward signal to encourage diverse and efficient reasoning behaviors, and RL training with an outcome verifier to ensure correctness while preventing reward hacking.<n> Empirical studies in the math domain show that RLSP improves reasoning.
  arXiv  Detail & Related papers  (2025-02-10T18:52:04Z)
• VinePPO: Refining Credit Assignment in RL Training of LLMs [66.80143024475635]
  We propose VinePPO, a straightforward approach that leverages the flexibility of language environments to compute unbiased Monte Carlo-based estimates.<n>Our method consistently outperforms PPO and other baselines across MATH and GSM8K datasets in less wall-clock time.
  arXiv  Detail & Related papers  (2024-10-02T15:49:30Z)
• Investigating Context-Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style [13.968658352075334]
  We investigate the impact of memory strength and evidence presentation on Large Language Models' receptiveness to external evidence.<n>Our results show that for questions with high memory strength, LLMs are more likely to rely on internal memory.<n>These findings provide key insights for improving retrieval-augmented generation and context-aware LLMs.
  arXiv  Detail & Related papers  (2024-09-17T07:44:06Z)
• RLSF: Reinforcement Learning via Symbolic Feedback [11.407319705797242]
  We propose a new fine-tuning paradigm we refer to as Reinforcement Learning via proofs Feedback (RLSF) In RLSF, the LLM being fine-tuned is considered an RL agent, while the environment is allowed access to reasoning or domain knowledge tools. We show that our RLSF-based fine-tuning of LLMs outperforms traditional approaches on five different applications.
  arXiv  Detail & Related papers  (2024-05-26T18:49:59Z)
• ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL [80.10358123795946]
  We develop a framework for building multi-turn RL algorithms for fine-tuning large language models. Our framework adopts a hierarchical RL approach and runs two RL algorithms in parallel. Empirically, we find that ArCHer significantly improves efficiency and performance on agent tasks.
  arXiv  Detail & Related papers  (2024-02-29T18:45:56Z)
• How Can LLM Guide RL? A Value-Based Approach [68.55316627400683]
  Reinforcement learning (RL) has become the de facto standard practice for sequential decision-making problems by improving future acting policies with feedback. Recent developments in large language models (LLMs) have showcased impressive capabilities in language understanding and generation, yet they fall short in exploration and self-improvement capabilities. We develop an algorithm named LINVIT that incorporates LLM guidance as a regularization factor in value-based RL, leading to significant reductions in the amount of data needed for learning.
  arXiv  Detail & Related papers  (2024-02-25T20:07:13Z)
• Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves [57.974103113675795]
  We present a method named Rephrase and Respond' (RaR) which allows Large Language Models to rephrase and expand questions posed by humans. RaR serves as a simple yet effective prompting method for improving performance. We show that RaR is complementary to the popular Chain-of-Thought (CoT) methods, both theoretically and empirically.
  arXiv  Detail & Related papers  (2023-11-07T18:43:34Z)
• LaGR-SEQ: Language-Guided Reinforcement Learning with Sample-Efficient Querying [71.86163159193327]
  Large language models (LLMs) have recently demonstrated their impressive ability to provide context-aware responses via text. This ability could potentially be used to predict plausible solutions in sequential decision making tasks pertaining to pattern completion. We introduce LaGR, which uses this predictive ability of LLMs to propose solutions to tasks that have been partially completed by a primary reinforcement learning (RL) agent.
  arXiv  Detail & Related papers  (2023-08-21T02:07:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.