RL for Language Models

RL: Reinforcement Learning

Follow this topic Ask about this topic

Momentum

36 papers in the last four weeks, up 71% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 271

Sep 24, 2026cs.CL

EAGER: Enhancing Generative Event Extraction via Reinforcement Learning with Verifiable Rewards

End-to-end event extraction remains challenging for large language models as it requires simultaneous identification of event triggers, classification of event types, and extraction of schema-grounded argument spans. We present EAGER, a reinforcement learning framework for generative event extraction that combines fine-grained verifiable rewards with Schema-Contrastive Advantage Estimation to alleviate advantage collapse under sparse binary rewards. Our reward design explicitly targets structural validity, extraction accuracy, groundedness, coverage, over-generation, and span precision. Experiments across seven benchmark datasets show that EAGER consistently outperforms prompting, supervised fine-tuning, and prior reinforcement learning baselines, achieving a substantial improvement over the strongest prior method. Results demonstrate that task-aligned verifiable rewards and contrastive advantage estimation substantially improve structured extraction.

Omar Adjali, Siting Liang, Omair Shahzad Bhatti +1

German Research Center for Artificial Intelligence (DFKI), Germany · Carl von Ossietzky Universität Oldenburg, Germany

RL for Language Models Document Information Extraction LLM Information Extraction Reinforcement Learning with Verifiable Rewards

Sep 22, 2026cs.CL

Transcribe, Translate, and Optimize: Joint Reward Learning for Speech Translation

In LLM-based speech translation, transcription-based chain-of-thought (CoT) suffers from a mismatch between reference transcripts used in supervised fine-tuning (SFT) and model-generated transcripts at inference. To address this, we propose joint recognition and translation fine-tuning via group relative policy optimization (GRPO). We score both transcripts and translations, with translation conditioned on model-generated transcripts, and compare three token advantage strategies. Using Qwen2.5-Omni-3B across four languages, we evaluate CoT against direct speech translation (Direct ST) under SFT and GRPO, training on CoVoST 2 and testing on CoVoST 2 and FLEURS. CoT GRPO outperforms Direct ST GRPO by 1.77 and 0.83 average BLEU points on CoVoST 2 and FLEURS. Compared to CoT SFT, GRPO boosts BLEU by 0.82 and 0.67 points and reduces word error rate (WER) by 8.8% and 7.2% relatively. These results highlight reinforcement fine-tuning as an effective method to mitigate the training-inference mismatch, jointly improving recognition and translation.

Yanghe Dong, Wanting Huang, Weiran Wang

Independent Researcher · Department of Computer Science, University of Iowa, USA

RL for Language Models Speech Translation

Sep 21, 2026cs.DC

WeightBridge: An Efficient Weight Transfer Library for Reinforcement Learning

Weight transfer - the propagation of updated parameters from trainers to rollout generators - is becoming an important performance bottleneck in reinforcement learning (RL) systems for LLMs. The central challenge is supporting the diverse trainer and rollout layouts and synchronization requirements of modern RL workloads without sacrificing efficiency. Existing solutions are efficient under some configurations but perform poorly or lack support under others. We present WeightBridge, a flexible, efficient weight-transfer library designed to deliver high performance across diverse RL configurations. WeightBridge first automatically extracts the correspondence between trainer and rollout weight layouts, then plans and executes redundancy-free and load-balanced weight transfer. It exposes a small, general API while coordinating workers across diverse synchronization modes. Across configurations spanning different models, parallelization layouts, and synchronization modes, WeightBridge reduces average GPU stall time by up to 42

\times

over the state-of-the-art open-source RL framework and achieves high performance in all settings. A coding agent was able to integrate WeightBridge into two different RL frameworks without manual guidance, demonstrating the generality and ease of use of its APIs.

Xuanlin Jiang, Samuel Hsia, Michael Kuchnik +3

FAIR at Meta · Harvard University · Work carried out at Meta

RL for Language Models Distributed RL

Sep 17, 2026cs.LG

Score Centering Stabilizes Off-policy Reinforcement Learning

Reinforcement learning (RL) of large language models is notoriously sensitive to small differences between training and inference engines, often referred to as the training-inference mismatch (TIM). However, completely eliminating TIM is impractical, as it would come at a major cost to rollout efficiency. In this paper, we show that the instability of RL under TIM is primarily caused by drift: a persistent bias between training and inference engines that accumulates with every training step. We derive an additive "score centering" correction term that stabilizes RL under TIM by canceling drift. When training models from 0.6B to 30B parameters, score centering alone matches or outperforms methods based on importance sampling under quantization, with the gap growing as the mismatch becomes more severe. Because the correction is additive, score centering also composes with importance sampling -- their composition outperforms pure importance-sampling baselines in our staleness experiments.

Martin Marek, Max Ryabinin

Together AI

RL for Language Models Off-Policy RL

Sep 17, 2026cs.LG

EPIG-Tree: Compute-Optimal Branching for Gradient-Efficient Reinforcement Learning

Reward-based reinforcement learning for language models, exemplified by Group Relative Policy Optimization (GRPO), collapses an entire stochastic trajectory into a single scalar reward. This is clean and scalable, but it explores and allocates reward inefficiently: a trajectory may contain many causal decisions, recovery attempts, and environment-randomness events, yet every token or action inherits one trajectory-level advantage. We study tree-based rollout construction as a compute-allocation problem for policy-gradient estimation. Our central claim is that branches should be placed not where the policy is merely uncertain, but where an additional branch most reduces uncertainty about the policy gradient per unit of compute. From a law-of-total-variance decomposition of the local policy-gradient random variable, we derive two allocation laws: new branches reduce decision uncertainty, while repeated suffix rollouts reduce continuation uncertainty. The resulting EPIG-Tree score allocates branches using the already computed rollouts. It estimates occupancy- and score-weighted value uncertainty, along with a suffix law

n_e \propto w_e \|\nabla_θ\log π(a_e|h_e)\| σ_e / \sqrt{c_e}

. Empirically, EPIG reduces gradient MSE in cloned-state control, winning in all nine dense continuous-control environments of a 13-environment sweep and recovering the reference gradient direction near-perfectly, and it improves frozen-LLM gradient calibration relative to entropy branching. In online single-turn math, tree-local credit beats flat GRPO, while branch placement is secondary to token-level credit assignment. In online multi-turn Wordle, EPIG attains the highest final win rate (0.850), overtaking flat GRPO, which saturates early at 0.790, and entropy branching as training proceeds, confirming that the gradient-estimation advantage transfers to a stateful, large-action setting.

Nikita Khomich, Leopold Hermansson, Ido Hakimi

RL for Language Models Policy Gradient Credit Assignment in RL Policy Learning

Sep 16, 2026cs.LG

Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening

In reinforcement learning for large language models, Proximal Policy Optimization (PPO) commonly uses a critic to estimate state values and reduce the variance of policy updates. However, we uncover a systematic failure mode in PPO critics, which we call Value Flattening: state values, estimated from multiple Monte Carlo continuations, change sharply across intermediate states while critic predictions remain comparatively flat. We further observe this phenomenon in a controlled FrozenLake environment and find that it becomes more pronounced as the state space grows. Our theoretical and empirical analyses relate Value Flattening to an implicit variance penalty in the critic loss and redundant updates from temporally correlated states with similar gradients. Motivated by these findings, we introduce SParse Proximal Policy Optimization (SP

^3

O), which applies the value loss to only a few well-separated states in each response to mitigate both effects. Experiments on Qwen3-Base show that SP

^3

O with only three states supervised per response can mitigate Value Flattening and consistently improve the learned policy across model sizes and evaluation suites. Together, our results identify Value Flattening as an important yet overlooked failure mode of critic learning in standard PPO and show that a simple sparse supervision strategy can mitigate it.

Yizhuo Li, Jianhao Yan, Yun Luo +9

Shanghai Jiao Tong University · Shanghai AI Laboratory · Westlake University +4

RL for Language Models Value Function Estimation Proximal Policy Optimization

Sep 15, 2026cs.CL

TIAO: Token Importance-Aware Policy Optimization for Text Summarization

Text summarization requires models to condense content while preserving key qualities such as consistency and coherence. Large language models (LLMs) have shown strong performance on this task and can be further improved through reinforcement learning (RL). However, most existing methods apply reward signals directly to undifferentiated token sequences, overlooking the varying importance of individual tokens to word and sentence level quality in summarization. In this paper, we propose Token Importance-Aware Policy Optimization (TIAO), a novel reinforcement learning strategy that explicitly leverages token-importance awareness. Specifically, TIAO identifies core tokens based on token dependency and reweights a trajectory's advantage according to its overall dependencies. Experiments on the real world dataset show that our TIAO achieves highly competitive results, and that a 7B foundation model enhanced by TIAO performs comparably to GPT-4 and GPT-5-nano. Code is available at https://github.com/TechCloud-x/TIAO

Qixiu Li, Chenlong Bao, Xiang Zhu +4

National University of Defense Technology

RL for Language Models Token-Level Credit Assignment Text Summarization RL Fine-Tuning

Sep 14, 2026cs.CL

Learning to Coach for Experiential Learning

Language models can learn from experience, but raw solution trajectories are often too long and noisy to provide effective guidance. In this work, we propose Learning to Coach (L2C), a framework that trains a dedicated LLM-as-a-Coach to extract actionable experiential knowledge from an actor model's previous trajectory. The actor remains frozen, while the LLM-as-a-Coach is trained to maximize a reward given by the correctness of the actor's guided response. We study two such rewards: a same-instance reward, which improves subsequent responses on the original problem, and a cross-instance reward, which elicits knowledge that transfers to other instances. Across mathematical reasoning and interactive text-games, L2C consistently outperforms self-refinement and an untrained LLM-as-a-Coach. Running experiential learning for more iterations further improves accuracy and uses additional inference compute more effectively than enlarging the actor's decoding budget. The trained LLM-as-a-Coach also transfers to out-of-distribution tasks and adapts its guidance to the specific actor it coaches.

Guanheng Chen, Tianzhu Ye, Li Dong +3

Microsoft Research

RL for Language Models RL for Language Model Reasoning

Sep 14, 2026cs.IR

Generate to Explore, Select to Exploit: Aligning LLM-based Headline Generation with Personalized Recommendation

In industrial recommendation feeds, presenting a static headline for an item often fails to satisfy the diverse, multimodal interests of the user population, particularly suppressing the needs of long-tail audiences. While Large Language Models (LLMs) have been integrated into recommendation for content understanding or ranking, directly optimizing them to output a single best headline typically leads to mode collapse---converging to generic patterns that satisfy average tastes but miss specific latent intents. To bridge this gap, we introduce GESE (Generate to Explore, Select to Exploit), a framework operating at the system's presentation layer that decouples personalization into generative exploration and selective exploitation. First, we treat the LLM as a probabilistic explorer, utilizing Group Sequence Policy Optimization (GSPO) with a hierarchical reward mechanism to generate a candidate set that maximizes the semantic coverage of potential user interests. Subsequently, a lightweight, real-time feedback-aware selector acts as the exploiter, identifying the optimal realization from the candidate pool based on instant contextual signals. Extensive deployment on a commercial platform with over 100 million daily active users demonstrates that GESE significantly outperforms state-of-the-art baselines, achieving a 2.57% lift in CTR and 0.87% in dwell time. These results validate that decoupling diversity-oriented generation from precision-oriented selection offers a robust blueprint for aligning generative AI with dynamic user utility.

Yi Chen, Rufeng Cheng, Qiang Xie +1

Baidu Inc., Beijing, China

RL for Language Models LLM Personalization Large Language Model-Based Recommendation Personalized Text Generation Generative Recommendation

Sep 14, 2026cs.LG

What Does an LLM Learn from Reinforcement Learning? A Mechanistic Interpretability Perspective with Fixed-SAE Track

Reinforcement learning (RL) is widely utilized in large language model training to improve targeted capabilities, yet how RL reshapes a model remains poorly understood. Prior attempts to explain how RL works largely offer behavioral perspectives, leaving open what RL gives a model at the representation level: can RL create genuinely novel features, and which existing features does it enhance or suppress? Recent developments in mechanistic interpretability suggest sparse autoencoders (SAEs) as a promising lens to decompose internal activations into human-interpretable features; however, they cannot be directly applied to tracking change across training. In this work, we introduce Fixed-SAE Track, a framework that trains one shared SAE per considered layer on activations pooled across the base model and all RL checkpoints, holding every feature direction fixed so that representation shifts are rigorously defined through the activations of interpretable SAE latents, including the detection of emerging novel features. Validated across multiple datasets and RL algorithms, we find that RL-induced drift is small, gradual, concept specific, and concentrated in late layers, mainly enhancing the sampling rates of a small set of ladder tokens, formatting scaffolding such as step breaks and answer delimiters, rather than reshaping problem content. Steering these features into the base model recovers around 80% of RL's performance gain, suggesting that RL primarily elicits capabilities the model already possesses, much as steering does. We further design a synthetic benchmark with features known by construction to test whether RL can instill genuinely novel features. We believe Fixed-SAE Track provides a principled approach to tracking representation shifts and offers representational evidence for understanding how reinforcement learning changes the inner representation of LLMs.

Lingheng Du, Yiming Tang, Xufeng Duan +1

Peking University · National University of Singapore · The Chinese University of Hong Kong

RL for Language Models Sparse Autoencoders Mechanistic Interpretability

Sep 14, 2026cs.AI

GLARE: Generative Learning via Adversarial Reward Estimation For Social Dynamics Forecasting

Meeting continuation requires tracking the agenda, speaker roles, participant intentions, and disagreement across long multi-party discussions. We introduce the Meeting Dynamic Forecasting Benchmark (MDFB), constructed from 2,207 real-world meetings and 24,794 future-facing queries. Given a transcript prefix and an active question, a model generates a plausible multi-turn continuation in one call. We evaluate utility---progress toward the question---and human-likeness---plausible conversational flow and role consistency---without requiring exact reproduction of the observed future. We further present GLARE, an adaptation of adversarial imitation learning to conditional language generation. A discriminator ranks the observed continuation above samples from the current actor, and its score supplies a KL-regularized policy reward; retraining on current-policy negatives allows the reward landscape to evolve with the actor. GLARE attains average human-evaluated win rates of 0.66 on utility and 0.70 on human-likeness, outperforming SFT and SPIN while remaining below the observed human continuation. We also demonstrate MDFB as a social reasoning arena for comparing general-purpose models, including closed-source systems, through reference-assisted judgments. Together, these studies illustrate the benchmark's use for both task-specific learning and output-based evaluation of meeting behavior.

Tenghao Huang, Zhaoxuan Tan, Muhao Chen +5

Microsoft · University of Notre Dame · University of California, Davis +1

RL for Language Models Adversarial Imitation Learning Multi-Turn Dialogue Evaluation Text Generation

Sep 14, 2026cs.SD

Direct Preference Density Alignment for Conversational Audio Equalization

Large Language Model alignment typically relies on learned proxy reward models, which significantly increase the memory footprint during training and are notoriously prone to instability and reward hacking. While offline methods like Direct Preference Optimization (DPO) bypass the reward model, they lose the ability to perform online exploration. If no optimization constraints are applied, this can lead to format collapse in bounded, continuous spaces. To resolve this, we propose Direct Preference Density Alignment: An alternative framework that removes the need for a learned proxy reward model while strictly preserving the benefits of online reinforcement learning. We leverage large-scale user data (approximately 90,000 samples) to construct non-parametric preference density maps, establishing an empirical reward surface. In addition to removing the reward model, Direct Preference Density Alignment enables the combination of the online structural grounding of Group Relative Policy Optimization (GRPO) with the targeted offline refinement of DPO. We show that this GRPO+DPO combination achieves the highest performance, and in a blind audio equalization listening test, enables a 1.5B-parameter model to achieve perceptual parity with a carefully prompt-engineered GPT-4o mini baseline, using only a fraction of the inference compute.

Ioannis Stylianou, Sven Ewan Shepstone, Jon Francombe +2

Department of Electronic Systems Aalborg University Aalborg, Denmark · Bang & Olufsen A/S Struer, Denmark

RL for Language Models LLM Alignment Direct Preference Optimization Preference Optimization

Sep 14, 2026cs.CL

Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement Learning

A notable byproduct of LLM alignment training is mode collapse: the progressive loss of output diversity that narrows a model's expressivity at inference time. This degradation is especially limiting for applications requiring open-ended exploration and pluralistic perspectives, such as scientific ideation and creative writing. We present MoDA (Mode-conditioned Diversity Alignment), an online post-training RL algorithm that jointly optimizes generation quality and diversity, inspired by the coordination perspective in multi-agent reinforcement learning (MARL). MoDA trains a single shared LLM policy conditioned on abstract numbered roles, where each role acts as an agent competing to produce outputs distinct from the others. This formulation encourages mode-conditioned agents to explore complementary regions of the high-quality output space without requiring hand-crafted personas or architectural modifications. MoDA employs a prompt-adaptive quality gating mechanism that calibrates a reference quality threshold and grants diversity rewards only to responses that meet the threshold, preventing reward-hacking behaviors that compromise response quality. To study quality-diversity tradeoffs, we evaluate MoDA on a comprehensive suite of benchmarks spanning seven general capability tasks and four domain-specific diversity tasks in scientific ideation and creative writing. MoDA improves SBERT diversity by 265% on the Infinite-Chat held-out prompts, while increasing average general capability pass@1 by 10.3% over the Qwen3-8B baseline. Compared with the strongest DivPO baseline, MoDA improves SBERT diversity from 0.274 to 0.482 (+75.9%) and E-Vendi from 2.86 to 4.4 (+53.8%), while improving average general capability pass@1 by 7.0%. Overall, MoDA provides a drop-in alternative to standard post-training methods that preserves and expands the model's expressive output space while improving quality.

Jiayi Yuan, Hangoo Kang, James Jihao Liu +4

University of Washington · 2Stanford University

RL for Language Models Multi-Objective Language Model Alignment Quality-Diversity Optimization LLM Post-Training Mode Collapse

Sep 12, 2026math.OC

Beyond Verified Answers: Solver-Informed Self-Distillation for Bootstrapping Operations Research Language Models

Modern large language models (LLMs) can translate natural-language descriptions into operations research (OR) formulations. Post-training techniques including reinforcement learning and on-policy self-distillation have further improved this capability. However, three limitations remain in training LLMs for OR formulations. First, training commonly relies on synthetic formulations validated by human experts or stronger models, constraining scalable supervision. Second, credit assignment is either coarse or costly: outcome rewards score an entire trajectory without locating the responsible modeling decision, whereas process-level supervision requires an additional evaluator. Third, privileged self-distillation can induce style mismatch by using solver context unavailable at deployment. We find that a model can improve from solver-artifact feedback generated by its own rollouts, making self-distillation a practical, evaluator-free source of dense supervision. Therefore, we propose SOLID: Solver-Informed On-Policy LearnIng through Self-Distillation, a novel framework for self-improving OR language models without verified answers or external evaluators. SOLID executes candidate programs from multiple rollouts, clusters their objectives, and selects a majority-group artifact as a pseudo-reference. The model then performs updates using group-relative advantages and dense self-supervision signals. Across multiple OR benchmarks, SOLID improves solution accuracy for both general-purpose and OR-tuned models over outcome-only group-relative training. These results show that solver artifacts can support scalable self-improvement without trusted answers.

Rui Zhu, Minglong Cao, Chenyu Zhou +2

Shanghai Jiao Tong University, Shanghai, China · Fudan University, Shanghai, China

RL for Language Models Large Language Model-Guided Optimization Self-Distillation Natural Language to Optimization Modeling

Sep 9, 2026cs.CL

SocialRL: Refining LLMs' Social Intelligence through Multi-turn Reinforcement Learning and Reward Design

Social intelligence enables agents to read social context, infer intent, and adapt over sustained dialogue. As language models become autonomous collaborators, it is central to building effective and trustworthy human-AI interaction. Existing reinforcement learning methods optimize single-turn utterances and sparse outcome rewards, producing short-sighted policies that struggle to manage goal-relationship tensions across multi-turn interactions. We propose SocialRL, a multi-turn reinforcement learning framework addressing both challenges. First, we apply multi-turn reinforcement learning using PPO that propagates delayed outcome rewards back to each turn, enabling long-horizon planning. Second, we design six process reward dimensions capturing the goal-relationship trade-off, including goal advancement, relational attunement, contextual coherence, etc. A reward model dynamically generates fine-grained scoring criteria for each dimension, while a stage-aware weight schedule prioritizes relationship-building in early turns, goal advancement mid-way, and balanced closure late. Across multiple social-dialogue benchmarks, SocialRL improves Goal Achievement by an average of 9.2 percentage points over the corresponding Base models. These results demonstrate the effectiveness of SocialRL across synthetic and real social scenes, as well as standard and challenging social scenarios.

Jianing Wang, Xintao Wang, Aili Chen +7

Fudan University · Hello Group

RL for Language Models Reinforcement Learning Process Reward Models

Sep 3, 2026cs.AI

FiMI Banking: A Sovereign Model for Indian Retail Banking

Banks need conversational systems that can answer product questions, assist customers with account-related requests, and operate safely within strict operational and regulatory constraints. General-purpose language models do not reliably meet these requirements. They fall short when a task requires grounded information, correct tool use, or cautious handling of bank-specific sensitive situations. We introduce FiMI Banking, a controlled Indian retail-banking setting. We build it from vetted banking documents, structured ground truth, synthetic customer backgrounds, and banking tools. We evaluate two post-training approaches: preference optimization for response-level behavior, and reinforcement learning with verifiable rewards for multi-turn tool-use tasks. Preference optimization improves safe behavior substantially: out-of-scope refusal rises from 52% to 80%. Reinforcement learning improves edge-case performance from 0.509 to 0.718 and order-sensitive task performance from 0.590 to 0.679, while using 29% fewer generated tokens. These results show that preference optimization and verifiable-reward reinforcement learning address complementary requirements for reliable banking agents.

NPCI AI Research Team, Aman Kumar, Asit Desai +15

NPCI AI Research Team

Financial Services RL for Language Models Preference Optimization Reinforcement Learning with Verifiable Rewards AI Agent Safety Benchmarks LLM Agent Reliability

Sep 2, 2026cs.AI

PGPO: Potential-Guided Policy Optimization for Multi-Turn Agentic Tasks

Group-based reinforcement learning (RL) has become an effective paradigm for LLM post-training, but in multi-turn agentic tasks with sparse terminal rewards, it often provides coarse credit for intermediate actions. To obtain more fine-grained credit assignment, recent work such as GiGPO introduces step-level advantages for intermediate actions. However, these step-level signals still rely on the final outcome of each individual trajectory. As a result, actions within failed trajectories can remain poorly differentiated, so effective actions can receive the same unfavorable credit as erroneous ones. In this work, we propose Potential-Guided Policy Optimization (PGPO) for multi-turn agentic tasks. PGPO estimates empirical state potentials from anchor-state-group return statistics within each rollout group. It then derives action advantages from potential differences between adjacent states, enabling cross-trajectory credit propagation. This provides finer-grained step-level credit assignment, especially within failed trajectories. Experiments on ALFWorld and WebShop show strong overall performance relative to recent group-based RL methods. Further analysis provides evidence that PGPO yields more informative failure-side credit signals with negligible training overhead.

Yuyao Zheng, Haipeng Sun, Junwei Bao +4

1Fudan University · 2Zuoyebang Education Technology · 3BEDI Cloud

RL for Language Models Credit Assignment

Sep 2, 2026cs.LG

DMRL: Document-Mediated Reinforcement Learning for Skill Optimization in Advertising Recommendation

Advertising recommendation requires continuously tuning complex system parameters while balancing commercial returns and user experience. Recent work has introduced large language models (LLMs) with skill documents to assist this labor-intensive process, but skill optimization remains largely prompt-driven, lacking a principled mechanism to attribute rewards to specific document edits. To address this limitation, we propose Document-Mediated Reinforcement Learning (DMRL), a skill self-evolution framework that models skill document optimization as a sequence of structured editing actions. In DMRL, an upper-level agent performs controlled document edits, while a frozen lower-level task agent evaluates their effects through A/B testing. To address credit assignment and long-term outcomes, we introduce two key components: (1) Dual-Relative Policy Optimization (DRPO), a post-training policy optimization method for robust and risk-aware advantage estimation; and (2) Long-term Reward Predictor (LRP), which estimates long-term outcomes by modeling population heterogeneity with disentangled representation learning and cross-attention transfer. DMRL was deployed on a large-scale short-video ads platform and extensive empirical evaluation shows that DMRL outperforms state-of-the-art baselines across key advertising metrics

Wei Zhang, Hongji Li, Song Sun +4

Shanghai Jiao Tong University · Kuaishou Technology

Recommender Systems RL for Language Models

Sep 1, 2026cs.CL

The Rise of Verbal Reinforcement Learning

Natural language is emerging as a primary feedback channel for improving language agents, capable of conveying intent, preferences, and causal structure in forms interpretable by both humans and modern language models. We call this paradigm Verbal Reinforcement Learning (VRL) and offer the first unified account of it. We organize the field around a single axis, \textit{when} verbal feedback takes effect in an agent's lifecycle and \textit{what} it modifies, yielding three pillars: (1) \textbf{Language as Grounding Signal}, where language defines the task itself by specifying goals, states, and reward structures; (2) \textbf{Language as Deliberative Feedback}, where natural language guides reasoning at test time without the need to update model parameters; (3) \textbf{Language as Learning Signal}, where language-based feedback shapes model parameters through training. Within each pillar, we synthesize representative work, distinguish key subcategories of approaches, and outline the distinct role language plays in shaping agent behavior. Together, this taxonomy shows how verbal reinforcement is reshaping agent development, while also defining the challenges and opportunities for building more capable and aligned agents.

Kshitij Tayal, Arun Sharma, Genta Indra Winata +2

1AI Foundations, Capital One · University of Minnesota, USA

RL for Language Models Reinforcement Learning RL for LLM Agents

Sep 1, 2026cs.CL

PersuaRL: Reinforcement Learning-Driven Multi-Expert Selection for Persuasive Dialogue Generation in Insurance

Large Language Models (LLMs) are revolutionizing digital communication by powering conversational agents deployed across domains such as customer service, digital sales, and insurance. These agents, built on LLMs, can understand user input, retrieve relevant information, and generate coherent responses. However, while they excel at factual communication, they often lack the ability to engage in truly persuasive, context-sensitive dialogue, especially in domains like insurance, where trust and clarity are critical. Building on this need within the insurance domain, our work focuses on improving the persuasiveness of digital agents, aka LLMs. To support this, we introduce InsureDial, a Persuasive Insurance Dialogue dataset, designed to capture the nuances of persuasive communication specific to motor insurance interactions. We introduce PersuaRL, a reinforcement learning-based framework that equips LLM-driven dialogue agents with the ability to adaptively explore, select, and coordinate strategies across multiple expert modules, guided by the evolving dialogue context, to achieve more effective persuasion. We conduct extensive automatic human and qualitative evaluations on two benchmark persuasion dialogue datasets, including our InsureDial. Our evaluations consistently demonstrate that PersuaRL outperforms baseline, generating contextually appropriate and highly persuasive responses.

Rohan Kirti, Akash Ghosh, Aryan Vats +5

Indian Institute of Technology Patna, India · Ramakrishna Mission Vivekananda Educational and Research Institute, India · Accenture Labs, Bangalore, India

RL for Language Models LLM Agent Training Text Generation

Sep 1, 2026cs.CL

Context-Grounding Gains Are Mediated by Pre-existing Machinery: Auditing GRPO, SFT, and DPO

Language models can ignore prompt evidence when it conflicts with memorized knowledge. Post-training can make models follow such evidence more reliably, but it is unclear whether these gains require new machinery or strengthen machinery already present. We compare nine post-training arms spanning GRPO, SFT, and DPO from one starting checkpoint, with key comparisons extended across scales and families. We estimate a grounding direction from that checkpoint before training. Across five tested GRPO variants, grounding gains are small. For the two variants replicated across seeds, equivalence tests bound their effects below the conflict-SFT gain even as the rewarded metric improves. Conflict-SFT improves grounding moderately, while DPO drives grounding near ceiling on its matched distribution. Conflict-SFT and DPO largely use the same causal attention-head set as the starting model. Subtracting the starting-model direction suppresses both gains, while adding it to the starting model recovers 35% of DPO's gain at a dose passing all stated side-effect checks. After a supervised warm start makes the context answer appear in more rollouts, the same GRPO recipe adds essentially no further grounding gain. In our setting, grounding gains largely depend on machinery already present in the starting model.

Prakhar Gupta, Vaibhav Gupta

University of Michigan · University of Waterloo

RL for Language Models LLM Grounding Knowledge Conflicts in Language Models LLM Auditing Language Model Post-Training Causal Interventions in Language Models

Aug 31, 2026cs.LG

Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement

On-policy distillation (OPD) offers dense token-level supervision as an alternative to the sparse outcome-level advantages of reinforcement learning with verifiable rewards (RLVR). However, the teacher scores student-generated trajectories that are inherently off-policy for it, so the reliability of its supervision, and hence the source of the student's improvement, remains unclear. We quantitatively analyze teacher supervision during OPD training and find substantial noise whose prevalence increases with teacher scale. Surprisingly, the student policy is insensitive to such noise, converging to comparable performance regardless of whether noisy supervision is retained or removed. Does OPD distill at all? By analyzing what drives its gains, we find that learning concentrates on low log-probability tokens, and using a single fixed negative advantage matches the performance of teacher-provided ones. This suggests that OPD works largely by suppressing low log-probability tokens, which requires no teacher. These findings motivate On-Policy Self-Adaptation (OPSA), a supervision-free method using entropy-adaptive negative advantages. It assigns stronger learning signals to high-entropy positions, suppressing tail tokens, and evenly redistributing probability mass among head tokens. Compared with the base \texttt{Qwen3-1.7B}, OPSA improves Avg@32 by 35.41 points on AIME24, corresponding to a 263% relative gain, and more than doubles Pass@32 across all three benchmarks. It also outperforms OPD by 16.77 points in Avg@32 on AIME24. Extensive experiments and analyses across model families and tasks further demonstrate its effectiveness and generalizability.

Yi Ding, Ruqi Zhang

Department of Computer Science, Purdue University, USA

RL for Language Models Language Model Distillation On-Policy Distillation Language Model Self-Improvement Policy Learning

Aug 31, 2026cs.CL

When Does Predictor-Based RL Align with Human Perception? A Study of Subjective Rewards in Codec-Based Speech Language Models

Codec-based text-to-speech (TTS) models make language-model post-training applicable to speech generation, but it remains unclear when learned perceptual predictors can serve as reinforcement learning rewards without losing alignment with human listeners. We study this question with Group Relative Policy Optimization (GRPO) using learned rewards for anime-like speaking style, naturalness, likability, and arousal. To prevent perceptual rewards from being optimized through transcript drift, we introduce a character error rate (CER) zone constraint and compare policy optimization with Best-of-

N

reranking under the same reward gate. Across single-reward runs, each reward primarily improves its own target metric, showing that subjective predictors are not interchangeable quality surrogates. Multi-rater A/B tests further show uneven human transfer, while a reward-gap analysis separates average transfer from within-axis calibration: signed reward gaps significantly predict listener choices in the pooled analysis, whereas residual CER gaps do not, but per-axis calibration remains heterogeneous. Best-of-8 is a strong human-level baseline and is not clearly worse than GRPO perceptually, suggesting that GRPO should be viewed as amortizing reward-selected behavior into the policy rather than uniformly outperforming reranking. These results support analyzing subjective speech rewards as predictor-axis-base tuples and provide practical diagnostics for selecting rewards before multi-reward speech post-training.

Joonyong Park, Jerry Li

Spellbrush

Reward Modeling RL for Language Models Speech Generation Evaluation TTS Evaluation Speech Language Models

Aug 31, 2026cs.CL

Co-Evolving Actor-Conditioned Critics for Non-Verifiable Generation

Natural-language critiques provide supervision beyond scalar rewards for non-verifiable generation, which lacks deterministic verifiers. In critique-guided refinement, a critic gives feedback on an initial response and an actor revises it. However, final revision quality does not reveal whether the critique was actually useful: a capable actor may improve without following the feedback, while valid feedback may fail if the actor cannot execute it. We frame critique as actor-conditioned revision guidance, where usefulness depends on whether the feedback helps the target actor address the intended weakness. We introduce TAIScore (Targeted Actionable Improvement Score), a reward that evaluates the instruction, initial response, critique, and revision together, assessing whether the critique targets a real weakness, whether the actor follows it, and whether the intended aspect improves. We use this reward to train an actor-tailored critic with GRPO, and use critique-guided refinements to construct DPO preference pairs for the actor, forming a co-evolving critic-actor loop where the critic adapts to the actor's changing capability. Experiments show that an 8B critic trained with TAIScore outperforms both a zero-shot 120B critic and critics trained with outcome-only or critique-only reward signals. Co-evolving the critic and actor further improves performance, suggesting that effective critique supervision should adapt as the actor changes.

Jinyoung Kim, Muhammad Khalifa, Lajanugen Logeswaran +4

University of Michigan · LG AI Research · University of Illinois at Chicago

RL for Language Models LLM Evaluation LLM Self-Refinement

Aug 27, 2026cs.CL

A Survey on Rubric-Guided Reinforcement Learning for Language Models

Reinforcement learning from human feedback (RLHF) has become the dominant paradigm for aligning large language models (LLMs) with human preferences. However, traditional RLHF relies on scalar reward signals that lack interpretability and fail to capture the multifaceted nature of response quality. Rubric-guided reinforcement learning addresses these limitations by introducing structured, interpretable evaluation criteria, or rubrics, as the backbone of reward design, feedback generation, and policy optimization. In this survey, we introduce a Bayesian framework that defines constitutions as prior distributions

P(R)

over evaluation criteria and rubrics as conditional instantiations

R_x \sim P(R|x)

. Under this unified view, we present a taxonomy of rubric-guided RL along the prior-posterior axis, covering constitutional AI, instance-specific rubrics, process-level supervision, self-evolving rubrics, and their agentic and multimodal extensions. Furthermore, as rubrics are natural-language artifacts, we present a linguistic analysis of how granularity trade-offs, semantic drift, and linguistic reward hacking impact alignment reliability, identifying key open problems for future research.

Zifei Shan, Fangning Shao

WeChat, Tencent · Independent Researcher

RL for Language Models LLM Alignment Rubric-Based RL

Aug 22, 2026cs.CL

ToSCA: Leveraging Hierarchical Reinforcement Learning on Temporal and Strategic Abstractions of Conversational Agents

Humans naturally exhibit multiple forms of abstraction in reasoning and interaction, including temporal abstraction across decision timescales and strategic abstraction over communicative intents. Inspired by these complementary abstractions, we propose a two-level hierarchical reinforcement learning (HRL) framework for conversational agents that bridges the gap between existing token-level and utterance-level RL methods. Built upon a two-level Markov decision process (MDP), our framework conditions token-level response generation on utterance-level actions represented by explicit textual strategies. Based on theoretical analysis and efficiency considerations, we employ DQN to optimize the high-level Q-network and PPO to train the low-level actor-critic. To further alleviate reward sparsity and facilitate convergence, we introduce a dual-granularity reward mechanism that combines the utterance-level satisfaction score with token-level intrinsic self-consistency and a KL-divergence penalty. Experiments on both daily-life and emotional support conversations demonstrate that our method consistently outperforms a wide range of baselines in both strategy determination and response quality. Our implementation is available at https://github.com/AaronJi/ToSCA.

Xiaoyu Wang, Qingqing Gu, Yue Zhao +5

1Geely AI Lab · 2Beijing Institute of Technology · 3Peking University

RL for Language Models Hierarchical RL Conversational Agents

Aug 20, 2026cs.AI

SAPO: Single-Rollout Autoregressive Policy Optimization for Agentic Reinforcement Learning

Agentic reinforcement learning (RL) has emerged as an important post-training approach for enhancing the capabilities of Large Language Models (LLMs). However, existing methods face a trade-off between policy performance and resource efficiency. Conventional Proximal Policy Optimization (PPO) implementations incur substantial memory overhead from a separate critic, whereas critic-free group-relative methods require multiple rollouts and face potential learning bottlenecks on long-horizon tasks. In this work, we propose Single-rollout Autoregressive Policy Optimization (SAPO), an efficient PPO-style framework that unifies policy optimization and value learning within a single causal language model. SAPO exploits the autoregressive structure of LLMs to sequentially generate action and value estimation at distinct causal boundaries with shared parameters, and then jointly optimizes the PPO objectives and an auxiliary on-policy SARSA objective with turn-level generalized advantage estimation, where the latter is designed to facilitate value learning. Extensive experiments on ALFWorld and WebShop with Qwen2.5-1.5B/7B and Qwen3-14B demonstrate that SAPO reduces peak GPU memory usage by 23.1% and per-iteration runtime by 24.8% over strong PPO baseline, while matching or slightly improving task success rate. Our experiments also show that SAPO outperforms Group Relative Policy Optimization (GRPO) and recent cutting-edge variants in both task success and training stability.

Dayang Liang, Lang Feng, Bo An +1

Xiamen University, China

RL for Language Models Agentic RL Proximal Policy Optimization RL for LLM Agents

Aug 13, 2026cs.CV

Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs

Hybrid-thinking multimodal large language models (MLLMs) allow a single model to alternate between deliberative thinking and latency-efficient non-thinking inference. Although these modes differ in reasoning budget, their delivered responses should satisfy the same user-facing standard. Correctness alone may not characterize this response quality; we therefore evaluate task accuracy and response-pattern failures as complementary outcomes. We study this gap through \textbf{response-pattern alignment}: whether thinking and non-thinking interfaces preserve acceptable final-response behavior. We introduce \textbf{PatternEval}, a failure-enriched diagnostic benchmark comprising 2,415 multimodal prompts spanning visual perception and grounding, structured image understanding, and multimodal knowledge reasoning. PatternEval tests four recurrent failures: chain-of-thought leakage, response repetition, logical contradiction, and performative reasoning. Response-pattern failures are widespread across models from different providers, with non-thinking inference exhibiting substantially higher failure rates and thereby creating systematic misalignment between thinking and non-thinking interfaces. Motivated by this diagnosis, we develop \textbf{PatternRM}, a response-level reward model, and \textbf{PatternRL}, which introduces pattern-specific penalties during reinforcement learning. Experiments on Qwen3-VL-4B and Qwen3-VL-8B show that incorporating pattern-specific penalties into reinforcement learning can mitigate cross-mode misalignment while incurring a marginal task performance trade-off. Together, PatternEval and PatternRL provide an evaluation-and-training framework for aligning user-visible response patterns across hybrid-thinking interfaces.

Xinming Wang, Weinong Wang, Hongming Yang +13

Institute of Automation, Chinese Academy of Sciences · Tencent · Zhongguancun Academy +3

RL for Language Models LLM Alignment Multimodal Large Language Models Multimodal Model Evaluation

Aug 12, 2026cs.DC

RoutePack: Expert Placement and Attention-Aware Data Packing for MoE Reinforcement Learning

Training Mixture-of-Experts (MoE) models for reinforcement learning (RL) couples two load-balancing problems: sequence composition determines dense attention work in each data-parallel microbatch, while token routing determines sparse expert work on expert-parallel ranks. Optimizing either alone can shift the bottleneck to the other. In MoE RL, rollout-time routing replay exposes every sample's sequence length and layer-wise expert demand before its training step. We present RoutePack, a hierarchical planner that coordinates state-consistent, layer-wise expert rerouting with joint attention- and expert-aware data packing over an optimizer-step window. RoutePack first places experts independently at each MoE layer using aggregate routing demand. It then packs samples into the smallest certified, or best-known feasible, number of token-capped execution rows and optimizes their DP layout with a projected EDP-shard-aware objective. The objective combines a window-normalized linear-quadratic attention proxy with per-layer physical EP-rank peaks and minimizes the accumulated cost of the slowest EDP shard. Parallel population annealing searches fixed-row feasible layouts while preserving sample coverage, capacity, nonempty cells, equal microbatch counts, and communicator topology. State-consistent materialization preserves logical top-k routing and existing MoE kernels without microbatch-level expert replication. Across Ling-3.0-Tiny and Ling-3.0-Flash, expert rerouting improves mean trainer-measured token throughput by 3.80% and 10.50%, while routing-aware packing adds another 4.86% and 3.98%, respectively. Overall, RoutePack improves throughput by 8.85% and 14.89% over the baseline.

Yibo Shen, Xudong Han, Xiaowei Zhu +2

Ant Group

RL for Language Models Expert Load Balancing Mixture-of-Experts Language Models Mixture-of-Experts Models

Aug 12, 2026cs.CL

When the API Speaks the Wrong Language: Revisiting Post-Training for Multilingual Tool Use

The reliability of Large Language Models (LLMs) for API calling degrades in multilingual settings. A common failure occurs when a model selects the correct tool but generates argument values in an inconsistent language, which we term Argument Language Mismatch (ALM). Although semantically correct, such outputs are operationally invalid and not captured by standard API-calling metrics. We revisit post-training strategies for mitigating ALM and find that, in our benchmark, supervised fine-tuning (SFT) provides a strong baseline, substantially improving argument language consistency and end-to-end function call accuracy. Under consistent model selection, SFT achieves performance comparable to, and sometimes exceeding more complex reinforcement learning (RL) approaches. We further examine whether RL with structured, argument-aware rewards offers additional benefits. While methods such as Group Relative Policy Optimization (GRPO) can improve language consistency and better preserve general reasoning ability, these gains are incremental and most pronounced in generalization and multi-objective trade-offs. Overall, our results suggest that much of the performance in multilingual API grounding can be achieved through careful supervised training, with RL providing targeted rather than fundamental improvements.

Siddharth Chauhan, Thomas Butler, Abhishek Singhania +2

Amazon.

Supervised Fine-Tuning Multilingual Language Model Evaluation RL for Language Models Cross-Lingual Consistency in Language Models