A Simple "Try Again" Can Elicit Multi-Turn LLM Reasoning

• URL: http://arxiv.org/abs/2507.14295v2
• Date: Fri, 22 Aug 2025 16:49:10 GMT
• Title: A Simple "Try Again" Can Elicit Multi-Turn LLM Reasoning
• Authors: Licheng Liu, Zihan Wang, Linjie Li, Chenwei Xu, Yiping Lu, Han Liu, Avirup Sil, Manling Li,
• Abstract summary: Multi-turn problem solving is critical yet challenging for Large Reasoning Models (LRMs) to reflect on their reasoning and revise from feedback.<n>Existing Reinforcement Learning (RL) methods train large reasoning models on a single-turn paradigm with verifiable rewards.<n>We introduce Unary Feedback as Observation (UFO) for reinforcement learning, which uses minimal yet common unary user feedback during iterative problem solving.
• Score: 58.80217284841095
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-turn problem solving is critical yet challenging for Large Reasoning Models (LRMs) to reflect on their reasoning and revise from feedback. Existing Reinforcement Learning (RL) methods train large reasoning models on a single-turn paradigm with verifiable rewards. However, we observe that models trained with existing RL paradigms often lose their ability to solve problems across multiple turns and struggle to revise answers based on contextual feedback, leading to repetitive responses. We ask: can LRMs learn to reflect their answers in a multi-turn context? In this work, we find that training models with multi-turn RL using only unary feedback (e.g., "Let's try again") after wrong answers can improve both single-turn performance and multi-turn reasoning. We introduce Unary Feedback as Observation (UFO) for reinforcement learning, which uses minimal yet common unary user feedback during iterative problem solving. It can be easily applied to existing single-turn RL training setups. Experimental results show that RL training with UFO keeps single-turn performance and improves multi-turn reasoning accuracy by up to 14%, enabling language models to better react to feedback in multi-turn problem solving. To further minimize the number of turns needed for a correct answer while encouraging diverse reasoning when mistakes occur, we design reward structures that guide models to produce careful and deliberate answers in each turn. Code: https://github.com/lichengliu03/unary-feedback

Related papers

• Learn Hard Problems During RL with Reference Guided Fine-tuning [56.56461712665904]
  Reinforcement learning (RL) for mathematical reasoning can suffer from reward sparsity.<n>We introduce Reference-Guided Fine-Tuning (ReGFT) to synthesize positive trajectories on hard problems and train on them before RL.<n>Our results show that ReGFT effectively overcomes reward sparsity and unlocks stronger RL-based mathematical reasoning.
  arXiv  Detail & Related papers  (2026-03-01T18:41:28Z)
• Expanding the Capabilities of Reinforcement Learning via Text Feedback [49.561885700139676]
  We formalize a multi-turn RL setup, RL from Text Feedback (RLTF), where text feedback is available during training but not at inference.<n>To do this, we propose two methods: Self Distillation (RLTF-SD), which trains the single-turn policy to match its own feedback-conditioned second-turn generations; and Feedback Modeling (RLTF-FM), which predicts the feedback as an auxiliary objective.<n>Our results show that both methods consistently outperform strong baselines across benchmarks.
  arXiv  Detail & Related papers  (2026-02-02T18:56:56Z)
• MulFeRL: Enhancing Reinforcement Learning with Verbal Feedback in a Multi-turn Loop [28.558050861419957]
  We investigate how to leverage richer verbal feedback to guide RLVR training on failed samples.<n>Specifically, we propose a multi-turn feedback-guided reinforcement learning framework.<n>It builds on three mechanisms: (1) dynamic multi-turn regeneration guided by feedback, triggered only on failed samples, (2) two complementary learning signals for within-turn and cross-turn optimization, and (3) structured feedback injection into the model's reasoning process.
  arXiv  Detail & Related papers  (2026-01-30T12:19:54Z)
• Deep But Reliable: Advancing Multi-turn Reasoning for Thinking with Images [53.373427633330515]
  We propose DRIM, a model that enables deep but reliable multi-turn reasoning when thinking with images in its multimodal CoT.<n>Based on a high-resolution image dataset, we construct high-difficulty and verifiable visual question-answer pairs.<n>In the SFT stage, we collect tool trajectories as cold-start data, guiding a multi-turn reasoning pattern.<n>In the RL stage, we introduce redundancy-penalized policy optimization, which incentivizes the model to develop a self-reflective reasoning pattern.
  arXiv  Detail & Related papers  (2025-12-19T07:44:43Z)
• Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning [49.22815446849924]
  Large Language Models (LLMs) often struggle with problems that require multi-step reasoning.<n>For small-scale open-source models, Reinforcement Learning with Verifiable Rewards (RLVR) fails when correct solutions are rarely sampled.<n>We propose Supervised Reinforcement Learning (SRL), a framework that reformulates problem solving as generating a sequence of logical "actions"
  arXiv  Detail & Related papers  (2025-10-29T22:05:08Z)
• Answer-Consistent Chain-of-thought Reinforcement Learning For Multi-modal Large Langauge Models [33.398631680508814]
  We propose Answer-Consistent Reinforcement Learning that modifies the GRPO algorithm with an auxiliary consistency check.<n>We design a consistency-verification reward that grants a high reward only if both the original and the post-shuffle answers agree and are correct.<n>We evaluate ACRE on challenging Video Reasoning benchmarks and multimodal math reasoning benchmarks, achieving an average 2.2% and 1.5% improvement.
  arXiv  Detail & Related papers  (2025-10-11T08:32:52Z)
• Feedback Friction: LLMs Struggle to Fully Incorporate External Feedback [20.985320124495566]
  LLMs possess some ability to improve their responses when given external feedback.<n>It remains unclear how effectively and thoroughly these models can incorporate external feedback.
  arXiv  Detail & Related papers  (2025-06-13T16:31:51Z)
• Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning [28.92744927199283]
  ReVisual-R1 achieves a new state-of-the-art among open-source 7B MLLMs on challenging benchmarks including MathVerse, MathVision, WeMath, LogicVista, DynaMath, and challenging AIME2024 and AIME2025.
  arXiv  Detail & Related papers  (2025-06-04T17:51:08Z)
• Maximizing Confidence Alone Improves Reasoning [48.83927980325788]
  RENT: Reinforcement Learning via Entropy Minimization is a fully unsupervised RL method that requires no external reward or ground-truth answers.<n>We find that by reinforcing the chains of thought that yield high model confidence on its generated answers, the model improves its reasoning ability.
  arXiv  Detail & Related papers  (2025-05-28T17:59:37Z)
• Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models [67.87579664988199]
  TON is a two-stage training strategy for vision-language models (VLMs)<n>It introduces a think-or-not format that serves as a cold start for selective reasoning.<n>TON can reduce the completion length by up to 90% compared to vanilla GRPO.
  arXiv  Detail & Related papers  (2025-05-22T16:13:29Z)
• Thinkless: LLM Learns When to Think [57.857534644932194]
  Reasoning Language Models, capable of extended chain-of-thought reasoning, have demonstrated remarkable performance on tasks requiring complex logical inference.<n>We propose Thinkless, a learnable framework that empowers an LLM to adaptively select between short-form and long-form reasoning.<n>On several benchmarks such as Minerva Algebra, MATH-500, and GSM8K, Thinkless is able to reduce the usage of long-chain thinking by 50% - 90%.
  arXiv  Detail & Related papers  (2025-05-19T17:24:16Z)
• Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1 [53.894789613838654]
  We introduce SEED-Bench-R1, a benchmark designed to evaluate post-training methods for MLLMs in video understanding.<n>It includes intricate real-world videos and complex everyday planning tasks in the format of multiple-choice questions.<n>Using Qwen2-VL-Instruct-7B as a base model, we compare RL with supervised fine-tuning (SFT)<n>Our detailed analysis reveals that RL enhances visual perception but often produces less coherent reasoning chains.
  arXiv  Detail & Related papers  (2025-03-31T17:55:23Z)
• OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement [91.88062410741833]
  This study investigates whether similar reasoning capabilities can be successfully integrated into large vision-language models (LVLMs)<n>We consider an approach that iteratively leverages supervised fine-tuning (SFT) on lightweight training data and Reinforcement Learning (RL) to further improve model generalization.<n>OpenVLThinker, a LVLM exhibiting consistently improved reasoning performance on challenging benchmarks such as MathVista, MathVerse, and MathVision, demonstrates the potential of our strategy for robust vision-language reasoning.
  arXiv  Detail & Related papers  (2025-03-21T17:52:43Z)
• GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training [62.536191233049614]
  Reinforcement learning with verifiable outcome rewards (RLVR) has effectively scaled up chain-of-thought (CoT) reasoning in large language models (LLMs)<n>This work investigates this problem through extensive experiments on complex card games, such as 24 points, and embodied tasks from ALFWorld.<n>We find that when rewards are based solely on action outcomes, RL fails to incentivize CoT reasoning in VLMs, instead leading to a phenomenon we termed thought collapse.
  arXiv  Detail & Related papers  (2025-03-11T15:17:02Z)
• Recursive Introspection: Teaching Language Model Agents How to Self-Improve [30.086494067593268]
  We develop RISE: Recursive IntroSpEction, an approach for fine-tuning large language models. Our experiments show that RISE enables Llama2, Llama3, and Mistral models to improve themselves with more turns on math reasoning tasks.
  arXiv  Detail & Related papers  (2024-07-25T17:35:59Z)
• ARES: Alternating Reinforcement Learning and Supervised Fine-Tuning for Enhanced Multi-Modal Chain-of-Thought Reasoning Through Diverse AI Feedback [13.154512864498912]
  We propose a two-stage algorithm ARES that Alternates REinforcement Learning (RL) and Supervised Fine-Tuning (SFT) First, we request the Teacher to score how much each sentence contributes to solving the problem in a Chain-of-Thought (CoT) Second, we ask the Teacher to correct the wrong reasoning after the RL stage. With the correction feedback, we stabilize the RL fine-tuned model through SFT.
  arXiv  Detail & Related papers  (2024-06-25T07:20:11Z)
• Recursive Chain-of-Feedback Prevents Performance Degradation from Redundant Prompting [0.4662017507844857]
  This paper studies such repetitive behavior and its effect by defining a novel setting, Chain-of-Feedback (CoF) To alleviate these troubles, we propose a novel method, Recursive Chain-of-Feedback (R-CoF)
  arXiv  Detail & Related papers  (2024-02-05T00:44:28Z)
• Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint [104.53687944498155]
  Reinforcement learning (RL) has been widely used in training large language models (LLMs) We propose a new RL method named RLMEC that incorporates a generative model as the reward model. Based on the generative reward model, we design the token-level RL objective for training and an imitation-based regularization for stabilizing RL process.
  arXiv  Detail & Related papers  (2024-01-11T17:58:41Z)

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.