RL for Language Model Reasoning

RL: Reinforcement Learning

Follow this topic Ask about this topic

Momentum

91 papers in the last four weeks, up 176% on the four weeks before. 0.9% of all new papers.

Jul 13Week of Sep 28

Latest papers 707

Jun 16, 2026cs.LG

Continual Self-Improvement with Lightweight Experiential Latent Memories

Large language models achieve strong reasoning performance by scaling inference-time compute, yet remain fundamentally stateless, discarding the rich, self-produced reasoning traces generated during this process. We investigate whether models can instead learn online from this experience, converting transient computation (reasoning traces) into persistent reusable knowledge, and without external supervision or access to future data. We show that In-Context Learning (ICL) over raw reasoning traces fails to generalize, reflecting a fundamental limitation of token-level reuse: individual traces lack the abstraction needed for transfer, even after refinement (e.g. self-reflection). In contrast, drawing inspiration from recent works on unsupervised reinforcement learning, we find that lightweight per-instance training with self-generated test-time signals (majority voting) as rewards yields substantial gains, often surpassing full-dataset offline training, motivating a shift from raw traces to learned latent representations. Building on this insight, we propose an online method that distills inference-time compute spent on encountered problems into compact modular latent memories capturing the underlying reasoning structure. These memories are stored and retrieved for future inputs, enabling continual improvement while avoiding catastrophic forgetting through modular design. Importantly, our method is highly efficient, parametrized as extremely lightweight soft prompt memories (~0.001% of model parameters) and trained with only a few gradient steps, yet achieving performance competitive with full parametric updates and offline training. Across challenging mathematical reasoning benchmarks, our approach significantly outperforms zero-shot and raw data ICL baselines, while transferring effectively across datasets.

Vaggelis Dorovatas, Nancy Kalaj, Rahaf Aljundi

Toyota Motor Europe · University of Trento

Continual Learning for LLMs Memory-Augmented Language Models RL for Language Model Reasoning Persistent Memory for Language Models Test-Time Training Online Continual Learning+2

Jun 16, 2026cs.AI

Shattering the Autoregressive Curse: Dynamic Epistemic Entropy Orchestrated Erasable Reinforcement Learning for LLMs

Although reinforcement learning (RL) has expanded the cognitive boundaries of large language models (LLMs), it often remains vulnerable to the autoregressive curse in long-horizon logical reasoning: small epistemic perturbations introduced early in generation can propagate irreversibly along the Markov decision process flow, triggering cascading failures that drive the reasoning trajectory toward collapse. To overcome this autoregressive cascade, in which a single early mistake can compromise all subsequent reasoning steps, we propose dynamic epistemic entropy orchestrated erasable reinforcement learning (

\text{E}^3\text{RL}

).

\text{E}^3\text{RL}

eliminates reliance on external signals by grounding the model's endogenous local autoregressive cross-entropy as an intrinsic coordinate of epistemic uncertainty. By introducing segment-level adaptive dynamic thresholds and advantage allocation,

\text{E}^3\text{RL}

enables the model to precisely excise localized logical defects while reusing historical key-value (KV) cache streams, thereby endowing the reasoning process with a self-healing capability. We train

\text{E}^3\text{RL}

on the DeepMath-103k dataset. Experimental results show that

\text{E}^3\text{RL}

reshapes the exploration efficiency of long-sequence reasoning and improves sample efficiency while maintaining linear memory overhead. On mathematical reasoning benchmarks such as AIME,

\text{E}^3\text{RL}

achieves substantial performance gains, with the 4B and 8B parameter models surpassing previous state-of-the-art (SOTA) results by 5.349% and 6.514%, respectively. These findings suggest that

\text{E}^3\text{RL}

shatters the autoregressive curse in long-sequence reasoning and establishes a theoretical and systems-level foundation for the next generation of self-healing artificial general intelligence (AGI).

Ziliang Wang, Kang An, Faqiang Qian +5

1SenseTime · 2Shanghai Jiao Tong University

LLM Self-Correction Reinforcement Learning RL for Language Model Reasoning LLM Reasoning

Jun 16, 2026cs.LG

Learning to Refine Hidden States for Reliable LLM Reasoning

Large language models show strong reasoning ability, but their internal reasoning process can remain unstable in complex multi-step settings, where early hidden-state errors may propagate to incorrect predictions. We propose ReLAR, a reinforcement-guided latent refinement framework that iteratively updates hidden representations before decoding. ReLAR maintains a compact latent reasoning state and uses learned depth and action controllers to adaptively determine both the number and direction of refinement steps. The controllers are trained with a policy gradient objective based on step-wise likelihood improvement, enabling efficient input-dependent reasoning without explicit chain-of-thought generation. Experiments on medical, mathematical, multi-hop reasoning, and open-ended generation benchmarks show that ReLAR improves accuracy, generation quality, and reasoning stability with substantially lower inference overhead than explicit reasoning baselines.

Chia-Hsuan Hsu, Jui-Ming Yao

RL for Language Model Reasoning Efficient Language Model Reasoning LLM Reliability Implicit Reasoning in Language Models Adaptive Computation Latent Reasoning

Jun 15, 2026cs.CV

Training LLMs with Reinforcement Learning over Digital Twin Representations for Reasoning-Intensive Surgical VideoQA

Surgical video question answering requires multi-step reasoning across semantic, spatial, and temporal dimensions. Existing methods architecturally compress videos into discrete token representations and couple visual perception with reasoning. This approach fragments continuous spatial-temporal relationships and has been shown to restrict multi-step reasoning capabilities. We introduce a reinforcement learning (RL) framework that trains large language models (LLMs) to decouple perception from reasoning by operating over digital twin representations constructed from surgical foundation models. Additionally, we introduce hierarchical representations across frame, temporal window, and procedure levels with probabilistic uncertainty estimates. Finally, we propose a novel reward that combines format validation with accuracy assessment through clinical plausibility evaluation and uncertainty-aware calibration for training. To demonstrate the capabilities of this approach, we introduce REAL-Colon-Reason, a colonoscopic benchmark with 2000 question-answer pairs across three complexity levels. We achieve state-of-the-art performance on REAL-Colon-Reason and two existing surgical VideoQA benchmarks REAL-Colon-VQA and EndoVis18-VQA.

Yiqing Shen, Han Zhang, Mathias Unberath

Johns Hopkins University, Baltimore, MD, USA

RL for Language Model Reasoning Medical VQA Video Reasoning Digital Twins

Jun 15, 2026cs.LG

Rethinking Groups in Critic-Free RLVR

Reinforcement learning (RL) has become a central paradigm for post-training large language models. Existing critic-free RL methods typically generate a group of rollouts for the same question to estimate value baselines for advantage computation. However, this design suffers from data inefficiency, group synchronization barriers, and inflexibility with structured rollouts. In this work, we revisit the role of the ``group'' and show that its underlying function is not merely to estimate baselines but to prevent false penalties on negative samples. Building on this insight, we propose negative token filtering, a simple and effective strategy that enables stable single-rollout training. We apply it to two batch-level advantage methods, achieving comparable performance on reasoning tasks and stronger performance on agentic tasks relative to group-based RL techniques.

Yihong Wu, Liheng Ma, Lingfeng Xiao +4

1Université de Montréal · 2McGill University · 3Mila - Quebec AI Institute +3

Reinforcement Learning RL for Language Model Reasoning Critic-Free RL Reinforcement Learning with Verifiable Rewards

Jun 15, 2026cs.CV

GeoDisaster: Benchmarking Orchestrated Agents for Operational Disaster Geo-Intelligence

Remote-sensing vision-language models (RS-VLMs) have advanced Earth-observation analysis toward visual interpretation and instruction-following, yet fall short of operational geo-intelligence, which demands tool-grounded spatial reasoning and structured, evidence-backed decisions. We introduce GeoDisaster, an operational geospatial disaster reasoning benchmark with 2,921 verified instances across 43 question types and five task families: deforestation monitoring, multi-hazard analysis, building-damage assessment, flood-safe routing, and Sentinel-1 SAR flood monitoring. Instances integrate heterogeneous EO/GIS evidence-optical and SAR imagery, raster masks, vector geometries, road networks, and exposure layers-spanning hazard detection, damage assessment, exposure estimation, and diagnostic report generation. Ground-truth answers are grounded in executable geospatial workflows and deterministic consistency checks, removing the need for language-model annotation. We further propose an orchestrated multi-agent framework with 18 disaster-oriented tools, where role-specialized agents coordinate through explicit execution contracts, aligned via Role-Contract Expectation Alignment (RCEA): failure-aware supervised fine-tuning combined with contract-grounded reinforcement learning over dense step-level signals. Experiments show that GeoDisaster challenges existing RS-VLMs and agentic systems, while RCEA improves tool use, evidence grounding, state consistency, and decision generation.

Maram Hasan, Aman Verma, Savitra Roy +5

Indian Institute of Technology Bombay · Mohamed bin Zayed University of Artificial Intelligence

Disaster Damage Assessment RL for Language Model Reasoning LLM Agent Orchestration Geospatial Reasoning Tool-Using Vision-Language Agents Remote Sensing Benchmarks+1

Jun 15, 2026cs.LG

ExpRL: Exploratory RL for LLM Mid-Training

Sparse reward reinforcement learning (RL) has become a standard tool for improving LLM reasoning, but its success depends critically on the coverage present in the base model. In practice, models are often primed for RL through \emph{mid-training} on curated reasoning traces that teach useful primitive skills such as decomposition, verification, or self-correction. Although effective, this strategy requires manually specifying what the model should learn, and it remains unclear whether such primitive coverage is enough for much harder problems, which require combining these skills into broader solution strategies. We study a more automated approach: \emph{RL-based mid-training} using large corpora of human-written question-answer data. Rather than treating reference solutions as targets to imitate, our method, ExpRL, uses them as \emph{reward scaffolds}: references are hidden from the policy and used only to construct problem-specific grading rubrics for judging on-policy reasoning traces. The policy samples from the original problem prompt, while an LLM judge compares the sampled reasoning trace against the reference solution and assigns outcome-level or process-level dense rewards. This lets ExpRL reinforce partial progress, useful intermediate reductions, and productive reasoning behaviors that sparse final-answer rewards often fail to upweight. On challenging math reasoning tasks, ExpRL yields stronger RL priming than SFT, sparse-reward GRPO, and self-distillation, and provides a better initialization for subsequent sparse-reward RL. Additional mixed-domain experiments further suggest that ExpRL can extend beyond the original math-only setting.

Violet Xiang, Amrith Setlur, Chase Blagden +2

1Stanford University · 2Carnegie Mellon University · 3OpenAI +1

Reinforcement Learning RL for Language Model Reasoning Mathematical Reasoning Rubric-Based RL Reward Design for RL

Jun 15, 2026cs.AI

Latent Thought Flow: Efficient Latent Reasoning in Large Language Models

Large Language Models (LLMs) increasingly rely on intermediate reasoning, yet explicit Chain-of-Thought (CoT) suffers from a linguistic space bottleneck: each thought must be decoded into tokens, causing high inference overhead. Latent reasoning moves deliberation into continuous space, but existing methods mostly learn deterministic or reward-maximizing paths, lacking a principled way to allocate probability across trajectories with different correctness and costs. We propose Latent Thought Flow (LTF), which models reasoning as variable-length continuous trajectories and trains a sampler to match a reward-induced posterior over answer quality and computation cost. We instantiate this with a continuous GFlowNet using stochastic latent transitions. To handle sparse answer supervision, we introduce an Entropy-Weighted Subtrajectory Balance objective for intermediate rewards and a reference-prior regularizer to anchor exploration. Experiments under finetuning and transfer learning settings show that LTF outperforms explicit CoT and latent reasoning baselines, improving accuracy by 9.5% while reducing reasoning length by 27.2% on average compared with strong latent reasoning baselines.

Xiandong Zou, Jing Huang, Jianshu Li +1

Singapore Management University · Ant Group

RL for Language Model Reasoning Efficient Language Model Reasoning Generative Flow Networks LLM Inference Acceleration Continuous Latent Reasoning Latent Reasoning

Jun 15, 2026cs.LG

A Gradient Perspective on RLVR Stability and Winner Advantage Policy Optimization

Reinforcement learning with verifiable rewards (RLVR) improves language-model reasoning, but GRPO-style optimization remains prone to collapse. We analyse this instability through token-level gradient dynamics, deriving a taxonomy that predicts how updates affect next-token probabilities and entropy. The taxonomy shows that stability depends jointly on the advantage sign and token distribution under the current policy. Motivated by this finding, we propose Winner Advantage Policy Optimization (WAPO), a simple online clipped policy-gradient objective that updates only on positive-advantage completions. Across mathematical reasoning and multi-hop QA benchmarks, WAPO improves training stability and matches or outperforms baselines across multiple model families. Full code can be found at https://github.com/layer6ai-labs/wapo.

Prasanth YSS, Zhichen Ren, Rasa Hosseinzadeh +6

Layer 6 AI

RL for Language Model Reasoning Policy Optimization Reinforcement Learning with Verifiable Rewards Policy Gradient Methods

Jun 14, 2026cs.AI

STRIDE: Strategic Trajectory Reasoning via Discriminative Estimation for Verifiable Reinforcement Learning

Reinforcement Learning with Verifiable Rewards (RLVR) has become an effective post-training paradigm for improving the reasoning abilities of large language models. However, existing RLVR methods typically rely on final-answer correctness to assign trajectory-level rewards, providing sparse supervision and treating all tokens uniformly regardless of their actual contribution to reasoning. Although recent studies introduce intermediate signals such as process rewards, high-entropy tokens, and semantic uncertainty, these signals are often not inherently verifiable and may fail to distinguish beneficial strategic patterns from harmful ones. To address this limitation, we propose STRIDE (Strategic Trajectory Reasoning with Discriminative Estimation), a fine-grained RLVR framework that derives strategic reasoning supervision from verifiable outcomes. STRIDE contrasts successful and failed trajectories within each response group to estimate the outcome-discriminative preference of each

n

-gram strategic pattern, and further combines this signal with reasoning saliency entropy to identify decision-relevant strategic patterns. These patterns are assigned differentiated advantage values during RL optimization, enabling more precise credit assignment while preserving the verifiability of RLVR. Extensive experiments demonstrate that STRIDE consistently improves reasoning performance across diverse models, tasks, and extended settings, including VLMs and agent-based systems.

Qinjian Zhao, Zhihao Dou, Dinggen Zhang +10

Kean University · Case Western Reserve University · University of Texas at Austin +4

RL for Language Model Reasoning Credit Assignment in RL Step-Level Credit Assignment in RL Reinforcement Learning with Verifiable Rewards

Jun 14, 2026cs.LG

Localizing Credit at the Divergence: Path-Conditioned Self-Distillation for LLM Reasoning

Reinforcement learning from verifiable rewards assigns a single scalar to each rollout, leaving token-level credit assignment underspecified in long reasoning traces. On-policy self-distillation addresses this by letting the same model act as a teacher conditioned on privileged information, producing a dense per-token signal. But the common choice of a ground-truth answer is only an endpoint cue: on terse-answer tasks, the teacher falls silent at the intermediate positions where path-level guidance matters most. We propose Hindsight Self-Distillation (HSD), which conditions the teacher on a successful peer rollout drawn from the current training group. Such a peer is an exact sample from the success-conditioned policy, requiring no additional sampled rollouts. By providing a full successful continuation rather than only the final answer, the resulting credit signal concentrates at the divergence position between a failed rollout and a successful peer. Across Qwen3-8B and Qwen3-32B on math and code benchmarks, HSD obtains the best result against GRPO variants and on-policy distillation baselines, with the largest gains on terse-answer tasks such as AIME.

Yu Li, Shu Hong, Tian Lan

Department of Electrical and Computer Engineering, George Washington University

RL for Language Model Reasoning Credit Assignment in RL Step-Level Credit Assignment in RL Reinforcement Learning with Verifiable Rewards On-Policy Distillation Teacher-Student Learning+1

Jun 13, 2026cs.LG

Understanding Diversity Collapse in RLVR via the Lens of Overtraining

Reinforcement learning with verifiable rewards (RLVR) has become a key approach for enhancing the reasoning abilities of large language models. However, RLVR often suffers from \emph{diversity collapse}: Pass@

1

improves while high-

k

Pass@

k

degrades, which is viewed as a narrowing of the model's reasoning boundary. We formalize this diversity collapse through the lens of \emph{overtraining}: once a problem's contribution to the reference metric has effectively saturated, further updates no longer expand what the model can solve but still concentrate probability mass on the trajectories favored by on-policy sampling. Under a standard setup with few rollouts per problem, even a single observed success places a problem in a nearly saturated regime for high-

k

Pass@

k

, so most updates in standard RLVR are overtraining from the boundary perspective. This perspective also suggests a reading of whether RLVR can expand the model's reasoning abilities beyond the base model: since RLVR is structurally biased against high-

k

Pass@

k

, its aggregate decline does not by itself mean that no new reasoning gains occurred. Interventionally, restricting updates to problems with zero observed success lifts Pass@

256

above the base model on difficult benchmarks; observationally, a non-trivial fraction of initially unsolvable problems become solvable during standard RLVR training. Building on these findings, we propose \emph{Bayesian Boundary Gating} (BBG), which redirects optimization away from overtraining by estimating each problem's marginal contribution to the reasoning boundary. Across multiple reasoning benchmarks, BBG improves average Pass@

k

across a wide range of

k

.

Suqin Yuan, Jinkun Chen, Jiyang Zheng +6

Sydney AI Centre, The University of Sydney · Southeast University · Microsoft +3

Reinforcement Learning Reasoning Diversity RL for Language Model Reasoning Reinforcement Learning with Verifiable Rewards

Jun 13, 2026cs.CL

AdaMame: A Training Recipe for Adaptive Multilingual Reasoning

While Large Reasoning Models (LRMs) show strong performance in English, they often fail to reason in the language of the query, a phenomenon known as language collapse. Existing RL-based fixes typically add a binary language fidelity reward to the accuracy objective, yet still incur trade-off in accuracy, mid-trace code-switching, and excessive token usage. In this work, we propose AdaMame, a two-stage training recipe for multilingual mathematical reasoning that addresses these limitations by adaptively aligning the reasoning language to the query language without compromising accuracy. The first SFT stage fine-tunes on non-MT reasoning traces across five languages to establish multilingual reasoning capability. In the subsequent RL stage, we introduce AdaMame-GRPO, an adaptation of Group Relative Policy Optimization (GRPO) in which a query-conditioned alignment factor grows progressively during training, guiding the model to first explore diverse reasoning languages before exploiting reasoning in the query language. Evaluated across two benchmarks, two LRMs, and 12 languages, AdaMame-GRPO achieves Pareto-optimal performance across reasoning accuracy, language fidelity, and token efficiency over all baselines, with the strongest gains on out-of-domain, lower-resource languages.

Dayeon Ki, Kevin Duh, Marine Carpuat

Multilingual Language Models Cross-Lingual Reasoning in Language Models RL for Language Model Reasoning Multi-Objective Language Model Alignment LLM Reasoning

Jun 12, 2026cs.CL

CoRA: Confidence-Rationale Alignment for Reliable Chain-of-Thought Reasoning

Chain-of-thought (CoT) reasoning can improve LLM performance, but high answer confidence may be misleading when the accompanying CoT rationale is plausible yet incomplete or poorly supported. We study confidence--rationale alignment: whether a model's confidence in its committed answer is justified by its generated rationale. We introduce a GRPO-based reinforcement learning framework that jointly rewards answer correctness, committed-answer probability, and rubric-based rationale support, where the rubric assesses grounding, coherence, task match, and connection to the selected answer without revealing the gold answer to the judge. Across MedQA, MathQA, and OpenBookQA using three open-weight LLMs, our method reduces the confidence--rationale alignment error by up to 26.51% compared with untuned checkpoints, SFT, and correctness-only GRPO, while maintaining competitive accuracy and often improving calibration. These results show that reliable CoT reasoning requires not only confident answers, but rationales that substantively support them.

Juming Xiong, Weixin Liu, Kevin Guo +9

Vanderbilt University · Vanderbilt University Medical Center · Intuit AI Research

CoT Reasoning RL for Language Model Reasoning LLM Reliability LLM Uncertainty Estimation

Jun 12, 2026cs.CL

AdaSR: Adaptive Streaming Reasoning with Hierarchical Relative Policy Optimization

Large reasoning models typically follow a read-then-think paradigm: they observe the complete input, reason over a static context, and then produce the answer. Yet many real-world scenarios are inherently dynamic, such as audio and video stream, where information arrives as a continuous stream and models must reason, update, and respond under partial observations. Recent streaming reasoning methods allow models to think while reading, but they largely rely on supervised imitation of pre-constructed trajectories, which limits their flexibility. In this paper, we propose AdaSR, an adaptive streaming reasoning framework that enables models to reason during input streaming and perform final deliberation once the stream is complete, learning when to think, and how much computation to allocate across different stages. To optimize this hierarchical reasoning process, we introduce Hierarchical Relative Policy Optimization (HRPO), which decomposes policy optimization into streaming reasoning and deep reasoning phases, providing more fine-grained advantage assignment instead of uniformly distributing a single sequence-level advantage over all tokens. HRPO integrates format, accuracy, and adaptive thinking rewards to enforce valid reasoning protocols, preserve final task performance, and encourage latency-aware computation allocation. Experiments show that AdaSR achieves a better balance among reasoning accuracy, computational efficiency, and streaming latency compared with supervised fine-tuning baseline. We release our code at https://github.com/EIT-NLP/StreamingLLM/tree/main/AdaSR.

Junlong Tong, Wenqi Xu, Yingqi Fan +4

1Eastern Institute of Technology, Ningbo · 2Shanghai Jiao Tong University · 5Xi’an Jiaotong-Liverpool University +2

Adaptive Inference RL for Language Model Reasoning Large Reasoning Models

Jun 11, 2026cs.CL

Learning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning

Retrieval-augmented generation (RAG) has become a standard mechanism for grounding language models in external knowledge, yet conventional retrieval based on lexical or semantic similarity is poorly suited for complex reasoning tasks: a semantically similar problem may demand an entirely different solution strategy, while a superficially different problem may share the same underlying reasoning pattern. We propose Retrieval-Augmented Reinforcement Fine-Tuning (RA-RFT), a post-training framework that teaches language models to reason by analogy. RA-RFT uses gold-relevance distillation to train a retriever that ranks contexts by expected reasoning benefit rather than semantic overlap, and then fine-tunes the policy model via reinforcement fine-tuning methods with retrieved analogous demonstrations, so the model learns to leverage reasoning traces under verifiable outcome rewards. We further analyze the diversity of retrieved contexts and find that reasoning-aware retrieval surfaces complementary solution strategies that provide distinct reasoning scaffolds for individual problems. Across challenging mathematical reasoning benchmarks, RA-RFT consistently outperforms standard reinforcement fine-tuning methods. For example, it improves AIME 2025 average@32 accuracy by 7.1 and 2.8 points over GRPO for Qwen3-1.7B and Qwen3-4B respectively -- suggesting that reasoning-aware retrieval is a complementary axis of improvement and orthogonal to advances in reward design or training curricula.

Zilin Xiao, Qi Ma, Chun-cheng Jason Chen +4

Meta Superintelligence Labs · Rice University · Work partially done during internship at Meta

Analogical Reasoning RL for Language Model Reasoning Mathematical Reasoning

Jun 11, 2026cs.CL

ArogyaSutra: A Multi-Agent Framework for Multimodal Medical Reasoning in Indic Languages

Multimodal Large Language Models (MLLMs) have shown promising reasoning capabilities in general domains, yet their performance remains limited in specialized settings such as healthcare, especially in multilingual and low-resource scenarios. This gap is critical in regions like rural India, where patients often express complex medical queries in native Indic languages and rely on multimodal inputs such as medical images. Existing English-centric MLLMs struggle to support such use cases, limiting equitable access to AI-driven healthcare assistance. To address this challenge, we introduce ArogyaBodha, a large-scale multilingual multimodal medical question-answer dataset constructed from eight heterogeneous sources, covering 31 body systems, six imaging modalities, and 21 clinical domains across English and seven major Indian languages. We further propose ArogyaSutra, an actor-critic-based multi-agent framework that integrates tool grounding with dual-memory mechanisms for step-wise, reasoning-aware decision making, and uses stored actor-critic simulation trajectories for distillation. Experiments show that our dataset and framework improve multilingual medical reasoning accuracy across all Indic languages, with ablations validating the contribution of each component. The source code and dataset are available at: https://iitp-cse.github.io/ArogyaSutra/

Tanmoy Kanti Halder, Akash Ghosh, Subhadip Baidya +2

1Indian Institute of Technology Patna · 3Prasannadeb Women’s College · 2Indian Institute of Technology Kanpur

Multilingual Language Models RL for Language Model Reasoning Multimodal QA Medical QA Multi-Agent LLMs Medical LLMs

Jun 11, 2026cs.AI

ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learning

Reinforcement Learning with Verifiable Rewards (RLVR) is a central technique for improving long-horizon reasoning in Large Language Models (LLMs). However, existing RLVR methods often encourage unnecessarily long reasoning rollouts, which can degrade reasoning coherence and exhaust the available context budget. Existing approaches to long-context organization often depend on external mechanisms to organize rollouts, rather than enabling the model to manage its own reasoning trajectory. To address this limitation, we propose ReSum, a novel RLVR framework that enables LLMs to compress and organize their reasoning trajectories through self-summarization. Our pilot studies show that self-summarization stabilizes generation by lowering token-level entropy, and that introducing a ``summarization'' phrase can substantially mitigate errors propagated from an incorrect rollout prefix. Motivated by these findings, ReSum adopts a summarization-aware adaptive rollout mechanism that contrastively evaluates whether self-summarization benefits the ongoing reasoning process. Specifically, when the model spontaneously triggers self-summarization, ReSum masks the summarization phrase to create a contrastive branch; for non-summarization positions, it instead randomly injects the phrase to create a matched branch. We further design a summarization-aware advantage to enable finer-grained comparison between contrastive rollout trajectories. Extensive experiments show that ReSum improves performance at an average of 4% while reducing rollout length by 18.6%.

Xucong Wang, Ziyu Ma, Yong Wang +5

University of Science and Technology of China · 2AMAP, Alibaba Group

RL for Language Model Reasoning Reinforcement Learning with Verifiable Rewards CoT Compression

Jun 11, 2026cs.AI

Mental-R1: Aligning LLM Reasoning for Mental Health Assessment

Mental health problems such as anxiety, depression, and suicide remain urgent global challenges, where timely and accurate assessment is critical for effective intervention. Recently, large language models have been explored for mental health assessment. However, existing general-purpose post-training methods do not align with the cognitive processes of human assessment, which may lead to unreliable reasoning outcomes. To bridge this gap, we propose Cognitive Relative Policy Optimization (CRPO), a reinforcement learning framework tailored for the mental health domain. CRPO extends group relative policy optimization by integrating stage-dependent uncertainty modeling into the policy optimization process. Specifically, we introduce a stage-wise entropy regularization mechanism that encourages broad exploration in early reasoning phases and progressively enforces confident decision-making in later stages, mimicking the human cognitive shift from uncertainty to certainty. In addition, inspired by cognitive appraisal theory, we formalize cognitive reasoning stages, thereby guiding theory-grounded interpretable inference. Experiments on 8 mental health datasets show that CRPO achieves an average improvement of 10.4 percentage points in weighted F1-score over the best reinforcement learning baseline. Furthermore, the CRPO-trained model Mental-R1 demonstrates clear advantages compared with existing large language models on reasoning-intensive cases, suggesting that CRPO enhances reasoning capabilities for mental health assessment.

Xin Wang, Boyan Gao, Yibo Yang +1

Department of Engineering Science, University of Oxford, Oxford, U.K · Department of Engineering Science, University of Oxford, U.K. · Oxford Suzhou Centre for Advanced Research, Suzhou, China

Cognitive Modeling Medical Diagnosis Mental Health RL for Language Model Reasoning Medical LLMs

Jun 11, 2026cs.LG

Select and Improve: Understanding the Mechanics of Post-Training for Reasoning

Reinforcement learning has rapidly emerged as a key component in the training of reasoning and coding models, yet it remains poorly understood from a mechanistic perspective. We study how and through what underlying processes capabilities are acquired or enhanced via reinforcement learning post-training. Our analysis, based on controlled math reasoning experiments with Qwen-2.5-1.5B, reveals two core mechanisms: strategy selection and strategy improvement. Our results highlight the role of SFT data and reinforcement learning data in activating these mechanisms, in particular showing how supervising the model on diverse reasoning strategies can enable strategy selection and how increasing difficulty in reinforcement learning data can enable strategy improvement. Taken together, our results provide mechanistic insight into RL training and suggest practical interventions to continue scaling reasoning capabilities.

Akshay Krishnamurthy, Audrey Huang, Nived Rajaraman

Microsoft Research NYC · UIUC

RL for Language Model Reasoning RL Post-Training LLM Reasoning

Jun 11, 2026cs.LG

Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning

Latent chain-of-thought compresses reasoning by replacing visible reasoning traces with continuous hidden-state recurrence, but existing formulations are difficult to optimize with standard on-policy reinforcement learning (RL) and hard to interpret causally. Our key insight is that a single pair of explicit boundary tokens can address both issues at once: discrete entry and exit anchors make the latent block compatible with standard on-policy RL, and the same anchors offer a natural foothold for mechanistic analysis. Motivated by this, we propose SWITCH, a switchable latent reasoning framework. The model emits <swi> to enter latent mode and </swi> to exit. Because the boundaries are ordinary discrete tokens, the GRPO policy ratio is well-defined at every decision point. The same anchors also expose the latent steps to direct probing and causal intervention. We train the model with a visible-to-latent curriculum and a Switch-GRPO objective that propagates gradients through recurrent latent computation. SWITCH consistently outperforms prior hidden-state-recurrence latent reasoning approaches at similar scale. Mechanistic analysis through the boundary tokens further reveals three findings: (i) <swi> is a sharply localised, learned switching policy rather than a stylistic artefact; (ii) the latent step it opens performs problem-specific, causally important computation rather than acting as an inert placeholder; and (iii) that computation is concentrated at a single hidden-state transition on entry. Together, these results show that hidden-state-recurrence latent reasoning is both RL-trainable and open to direct mechanistic analysis, including of how on-policy RL itself improves the model from the inside.

Jiayu Yang, Chao Chen, Shengen Wu +6

HKUST(GZ) · University of Cambridge · NTU +2

RL for Language Model Reasoning Mechanistic Interpretability Recurrent Transformers RL Post-Training Latent CoT Reasoning

Jun 11, 2026cs.CL

Multi-Turn Reasoning When Context Arrives in Pieces: Scalable Sharding and Memory-Augmented RL

When a user reveals task-critical information across several conversation turns, LLM accuracy drops by up to 65% despite full context availability. We show that this Lost in Conversation degradation can be substantially mitigated by training models to maintain a compact rolling memory instead of attending to a growing history. To make such training scalable, we introduce a low-cost sharding pipeline that converts single-turn QA datasets into multi-turn fragmented-information episodes, eliminating the need for hours of manual annotation. Training only on sharded GSM8K, our memory-augmented policy significantly improves multi-turn accuracy and generalises zero-shot to harder math and out-of-domain long-context QA. Moreover, memory-trained models outperform full-history baselines even when given the full history at test time, suggesting that learning to compress induces more robust incremental reasoning than full-context exposure alone.

Shu Tong Luo, Wenqin Liu, Rui Liu +2

The University of Melbourne · The University of Tokyo

Memory-Augmented Language Models RL for Language Model Reasoning Persistent Memory for Language Models LLM Context Management

Jun 10, 2026cs.CL

Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization

Reinforcement Learning (RL) with verifiable environments has emerged as a powerful approach for enhancing the reasoning capabilities of Large Language Models (LLMs). While prior research demonstrates that scaling environment quantity improves RL performance, existing manual or individual construction methods suffer from linear scaling limits, thereby hindering scalable reasoning generalization. This paper introduces RACES (\textbf{R}ecursive \textbf{A}utomated \textbf{C}omposition for \textbf{E}nvironment \textbf{S}caling), a framework that conceptualizes verifiable environments as composable building blocks that can be recursively assembled. The key insight is that when the codomain (output type) of one environment matches the domain (input type) of another, they can be automatically fused into a new verifiable environment, enabling recursive composition. RACES is implemented with 300 individual environments and defines a set of composition operators (\textsc{SEQUENTIAL}, \textsc{PARALLEL}, \textsc{SORT}, and \textsc{SELECT}) that induce diverse reasoning patterns. Extensive experiments show that RL training on these composite environments consistently enhances reasoning generalization. Specifically, RACES improves DeepSeek-R1-Distill-Qwen-14B by an average of 3.1 points (from 48.2 to 51.3) and boosts Qwen3-14B performance from 58.8 to 61.1 on six benchmarks, which are unseen during the construction of training environments. Moreover, RACES achieves performance comparable to training on 300 individual environments using only 50 base environments, demonstrating significant efficiency in environment utilization.

Hao Xiang, Qiaoyu Tang, Le Yu +8

University of Chinese Academy of Sciences · Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences · Qwen Team, Alibaba Group

RL for Language Model Reasoning Reinforcement Learning with Verifiable Rewards Procedural Content Generation

Jun 10, 2026cs.AI

The Art of Interrogation: Consistency Amplifies Factuality in Spatial Reasoning

Current Large Reasoning Models (LRMs) exhibit remarkable general capabilities but significantly underperform in spatial reasoning tasks. Existing approaches treat this gap as a knowledge deficit, relying on supervised fine-tuning (SFT) to ingest labeled spatial data from external vision sources or synthetic engines. In contrast, we argue that for many tasks, spatial reasoning capabilities are already present in pre-trained LRMs but require alignment through logical coherence under geometric 2D and 3D constraints. In this work, we propose a self-supervised reinforcement learning (RL) framework that targets the internal reasoning process without requiring ground-truth annotations. By formalizing the notion of consistency verifiers -- reward functions that check for geometric and semantic consistency under transformations -- we demonstrate that models can improve their spatial reasoning abilities. We use both image transformations, like flipping, and textual transformations, like swapping the order of objects in the question, and propose a new optimal transport-based RL strategy, OT-GRPO, which is a minimal-matching variant of group relative policy optimization tailored to pairwise verifiers. We show that this label-free consistency training approaches the accuracy of models trained with ground-truth supervision and achieves similar generalization across diverse tasks and data domains.

Theo Uscidda, Marta Tintore Gazulla, Maks Ovsjanikov +2

CREST, ENSAE, Institut Polytechnique de Paris · Google Zurich · Google DeepMind

Reinforcement Learning 3D Spatial Reasoning RL for Language Model Reasoning Spatial Reasoning Large Reasoning Models

Jun 10, 2026cs.LG

RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation

On-policy self-distillation (OPSD) provides dense, token-level supervision for reasoning models by aligning a model's own distribution with that under privileged context, typically a verified solution. However, we show that the resulting distributional gap concentrates on style tokens rather than task-bearing ones, as the hinted model tends to produce shorter, more direct outputs. We term this pathology \emph{privilege-induced style drift}, which can destabilize training and shorten responses. To address this, we propose \textbf{RLCSD} (Reinforcement Learning with Contrastive on-policy Self-Distillation), which mitigates this drift by contrasting the teacher-student gap under a correct hint against that under a wrong hint, suppressing style shifts induced by hints regardless of correctness and yielding a signal more concentrated on task-bearing tokens. Experiments on Qwen3 (1.7B/4B/8B) and Olmo-3-7B-Think across mathematical and logical reasoning show that RLCSD consistently outperforms GRPO and prior OPSD methods, with additional results on agentic tasks supporting broader applicability. We further show that the contrastive principle is general: it plugs into existing OPSD methods to improve them, and its underlying insight extends to broader cross-model on-policy distillation.

Leyi Pan, Shuchang Tao, Yunpeng Zhai +5

1Tsinghua University · 2Tongyi Lab , Alibaba Group · 3Peking University

RL for Language Model Reasoning Language Model Distillation On-Policy Distillation Teacher-Student Learning Knowledge Distillation

Jun 10, 2026cs.AI

Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning

The rapid progress of reasoning and agentic large language models (LLMs) has increased the demand for long-context inference, but self-attention (SA) scales quadratically with context length. To address this, we study SWARR (Sliding-Window Attention with Reinforced Adaptation for Math Reasoning), a practical recipe for adapting SWA models to mathematical reasoning. SWARR has two stages: (1) efficient conversion from a pretrained SA model to SWA with supervised fine-tuning (SFT), which avoids pretraining a new base model, and (2) policy adaptation with reinforcement learning (RL). We find that SWA still underperforms SA after SFT, and we hypothesize that this gap is caused in part by a data-architecture mismatch: most SFT data are prepared for SA models and may contain long-range dependencies that are difficult for SWA to model. Because on-policy RL optimizes self-generated trajectories under the SWA constraint, it can adapt trajectories to better match SWA. Experiments on mathematical reasoning benchmarks show that this recipe substantially narrows the gap between SWA and SA, recovering much of the accuracy lost during SWA conversion while preserving the efficiency benefits of linear-complexity attention. Our central contribution is the empirical finding that RL changes the conclusion one would draw from conversion and SFT alone about SWA's viability for math reasoning.

Kai Liu, Peijie Dong, Xinchen Xie +5

Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University · Hong Kong University of Science and Technology (Guangzhou) · Shanghai AI Laboratory

RL for Language Model Reasoning LLM Inference Acceleration Sliding-Window Attention RL Fine-Tuning LLM Mathematical Reasoning

Jun 9, 2026cs.CL

The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes

Large Language Models (LLMs) have achieved strong performance across natural language processing tasks, yet reliable reasoning remains an open challenge. Although modern LLMs show progress in structured inference, multi-step problem solving, and contextual understanding, their reasoning behavior is often inconsistent and sensitive to prompting strategies, task design, and model scale. This survey provides a systematic analysis of more than 300 recent papers from arXiv, Semantic Scholar, Google Scholar, Papers with Code, and the ACL Anthology to examine how reasoning capabilities emerge in LLMs and where they fail. We make three main contributions. First, we introduce a structured taxonomy of LLM reasoning research, covering Chain-of-Thought reasoning, multi-hop reasoning, mathematical reasoning, common sense reasoning, visual and temporal reasoning, code and algorithmic reasoning, retrieval-augmented reasoning, tool-augmented and agentic reasoning, and reinforcement learning-based reasoning. Second, we analyze methodological trends across these paradigms, including prompting methods, model architectures, training objectives, reward modeling, and evaluation benchmarks. Third, we synthesize recurring limitations and failure modes, such as reasoning hallucinations, brittle multi-step inference, weak causal abstraction, and poor cross-domain generalization. By organizing a rapidly expanding literature, this survey offers a unified view of the current capabilities and limitations of reasoning in LLMs. We also identify emerging research directions, including meta-reasoning, self-evolving reasoning frameworks, multimodal reasoning, and socially grounded reasoning. Overall, this work aims to serve as a reference for developing more robust, interpretable, and generalizable reasoning systems in future language models.

Avinash Anand, Mahisha Ramesh, Avni Mittal +7

SIT × Nvidia AI Center (SNAIC) · MIDAS Lab, IIIT Delhi · MIDAS Lab, IIT Mandi +4

CoT Reasoning RL for Language Model Reasoning Mathematical Reasoning LLM Reasoning

Jun 9, 2026cs.AI

The Role of Feedback Alignment in Self-Distillation

Conditioning a language model on additional context, such as feedback on a previous attempt, typically improves its response. Self-distillation trains the model to retain this improvement when the context is not present. The method works by matching the model's output distribution under two settings: a student that sees only the question, and a self-teacher that also sees the context. What the model learns therefore depends on what context the self-teacher receives, yet the design of this context remains largely unexplored. We study context design for self-distillation by training a solver on feedback from a frozen critic. We compare three conditions: (i) a binary reward (GRPO), (ii) the reference solution, and (iii) a step-by-step critique aligned to the solver's reasoning trace. Step-aligned critique yields the largest gains, outperforming GRPO by 16.11 points and reference-solution-conditioned self-distillation by 5.27 points (Avg@12). Per-token advantage analysis reveals why: step-aligned feedback targets only the tokens where reasoning fails, leaving correct behavior intact. Conditioning on the reference solution, by contrast, pressures the model to change its behavior at every token (even correct steps) because an alternative derivation inevitably differs in phrasing and approach. This suggests that structural alignment between feedback and the solver's reasoning is a key driver of self-distillation effectiveness.

Semih Kara, Oğuzhan Ersoy

Gensyn

RL for Language Model Reasoning Language Model Distillation LLM Reasoning

Jun 9, 2026cs.LG

Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning

Reinforcement learning with verifiable rewards (RLVR) has become standard for improving LLM reasoning. However, existing PPO-style trust-region mechanisms remain position-agnostic by enforcing uniform thresholds across all tokens independently. This pointwise treatment conflicts with autoregressive generation in two critical ways. First, uniform thresholds ignore autoregressive asymmetry. Early-stage deviations produce compounding sequence-level drift, causing static thresholds to under-regulate early divergence and excessively constrain late-stage exploration. Second, evaluating token-level divergence in isolation overlooks cumulative prefix drift, granting the same divergence allowance regardless of how far the conditioning history has already deviated from the rollout policy. To address this limitation, we propose CPPO (Cumulative Prefix-divergence Policy Optimization), a token-level masking rule that aligns updates with a finite-horizon policy-improvement bound via two coupled mechanisms. First, a position-weighted threshold imposes stricter limits at early positions whose effects persist longer, relaxing constraints for late-stage tokens. Second, a cumulative prefix budget tracks historical deviations, dynamically restricting further token-level deviation to prevent compounding errors along the prefix. Empirically, CPPO enhances training stability and significantly improves reasoning accuracy across various model scales.

Renjie Mao, Xiangxin Zhou, Lvfang Tao +7

Tencent Hunyuan

RL for Language Model Reasoning Reinforcement Learning with Verifiable Rewards RL Post-Training

Jun 9, 2026cs.LG

N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization

The success of Large Language Models in mathematical reasoning relies heavily on the generation of diverse and valid solution paths during the rollout phase. However, current rollout techniques face a fundamental trade-off: token-level sampling often yields redundant trajectories that differ only in rephrasing, while embedding-level methods utilizing random noise frequently disrupt semantic consistency. To resolve this, we introduce N-GRPO, a novel exploration strategy integrated into the Group Relative Policy Optimization (GRPO) framework. Rather than relying on token-level sampling or native embedding-level noise, our approach leverages Semantic Neighbor Mixing. This mechanism dynamically constructs input representations by mixing the embeddings of an anchor token and its nearest semantic neighbors, thereby injecting diversity while strictly adhering to the local semantic manifold. Experimental evaluations on the DeepSeek-R1-Distill-Qwen models across different sizes show that N-GRPO not only achieves consistent improvements over strong baselines on math reasoning benchmarks but also exhibits robust generalization capabilities on out-of-distribution tasks.

Xukun Zhu, Hang Yu, Peng Di +1

Zhejiang University · Ant Group

RL for Language Model Reasoning Group Relative Policy Optimization LLM Mathematical Reasoning