Live intelligence

Latest AI updates

47 updates

Research Editor selected

RLVR-Optimized Icon Generation for Alexa+

This paper describes a production pipeline for generating animated icons for Alexa+ devices from text descriptions, replacing a slow hand-drawn process. The authors focus on improving the critical image generation stage using reinforcement learning from verifiable rewards (RLVR) with objective verifiers that enforce design guidelines. The fine-tuned model increased the pass rate from 15.7% to 58.7% under an independent VLM judge, and both the model and verifier are deployed in production.

Why it matters: This is a concrete, recent deployment of RLVR in a production system, showing significant quality improvements and practical value for AI-driven content generation.

arxiv13h agoScore 82

reinforcement learningimage generationproduction deployment

Research Editor selected

Rubric Curriculum RL Improves RLVR in Non-Verifiable Domains

The paper introduces Rubric Curriculum RL (RcRL), a method that exploits the generation-verification gap in domains without ground-truth rewards by combining pairwise preferences over rollouts with a curriculum over rubric criteria. This creates a more discriminative and non-stationary training signal, avoiding the plateau seen in baselines. RcRL achieves a 70.5% human win rate on creative writing and improves HealthBench performance by 14.6% (full set) and 25.4% (consensus subset), outperforming all training baselines.

Why it matters: This presents a concrete, novel training method with measurable gains in open-ended domains, addressing a key limitation of RLVR.

arxiv13h agoScore 82

Reinforcement LearningReward ModelingLLM Alignment

Research Editor selected

Traffic-VL: Reinforced Vision-Language Model for End-to-End Traffic Signal Control

Traffic-VL is an 8-billion-parameter vision-language model that directly maps multi-view surveillance images and natural-language phase descriptions to traffic signal decisions, bypassing intermediate structured states. It is trained with offline reinforcement learning on photorealistic synthetic data (SynTra-V) and online stepwise trajectory optimization, matching structured-state baselines while outperforming image-based controllers and general-purpose VLMs. Evaluations include unseen topologies, degraded sensing, real footage, and a three-week deployment across ten intersections.

Why it matters: This paper presents a concrete, recent AI development with strong experimental validation, including real-world deployment, offering practical value for autonomous traffic management.

arxiv13h agoScore 85

Traffic signal controlVision-language modelsReinforcement learning

Research

GIST: Gibbs-Targeted Hierarchical Data Selection for Offline RLVR

This paper introduces GIST, a two-level data selection method for offline reinforcement learning with verifiable rewards (RLVR). It derives a factorization of the KL divergence between the current policy and the Gibbs-optimal target, identifying which responses and tokens are most informative. GIST selects correct responses on-policy and incorrect responses near the policy's mode, and supervises only the tokens where the mismatch lies. Experiments show accuracy gains across GSM8K, MATH-500, and MBPP for three models, with 66.6% fewer supervised tokens in a controlled comparison.

arxiv13h agoScore 78

Reinforcement LearningData SelectionToken Efficiency

Research Editor selected

Online Rubric Self-Distillation for Token-Level Credit Assignment in RL

The paper introduces ORSD, a method that generates natural-language process rubrics from on-policy trajectories to provide dense token-level supervision for reinforcement learning. A frozen verifier selects the best rubric bundle based on alignment with task success, and the likelihood gap with and without the rubric yields token-specific credit added to trajectory-level advantages. Experiments on ALFWorld and WebShop show faster policy improvement and higher final performance for Qwen3-1.7B and Qwen3-4B.

Why it matters: This is a novel, concrete AI research contribution with empirical results, addressing a key challenge in RL credit assignment.

arxiv13h agoScore 85

reinforcement learningtoken-level credit assignmentprocess rubrics

Research

CANDO: Conservative Action-Noise Directional Optimization for Residual Reinforcement Learning

This paper introduces CANDO, a residual reinforcement learning method that improves frozen generative policies by combining noise-space and action-space residual optimization. CANDO removes fixed latent feasible regions and uses conservative value estimation with gated execution to regulate adaptation. Experiments show CANDO achieves 76.1 NAUC and 91.4% final success rate, surpassing single-space baselines by 6.6 NAUC and 4.1%.

arxiv1d agoScore 78

Reinforcement LearningRobot ControlPolicy Adaptation

Research

ReSI-Math: Recoverable Capability Frontiers for Efficient Reasoning Improvement

ReSI-Math is a framework that identifies recoverable reasoning failures in LLMs—cases where direct decoding fails but trajectory-level search can elicit correct solutions—and converts them into efficient RLVR supervision. Using self-judge-guided evolutionary search, it selects frontier problems for sequential RLVR stages. On Qwen3-VL-8B, it improved MATH500 and WE-MATH averages from 78.71 to 80.16 after three stages, and frontier-guided selection outperformed random selection in matched single-problem RLVR.

arxiv1d agoScore 78

reinforcement learningLLM reasoningdata efficiency

Research

Density-Aware Reward Scaling for Diverse High-Reward Outcomes in RL

DARS is a lightweight reward-processing method that inversely scales rewards by local outcome density to promote reward-proportional sampling in continuous spaces. It requires no learned density model or auxiliary objective)Skip, and works with standard policy-gradient training. In multimodal navigation and text-to-image prompt adaptation, DARS-GRPO avoids mode collapse and improves diversity while maintaining semantic alignment.

arxiv1d agoScore 78

Reinforcement LearningReward DesignDiversity in AI

Research

FourSight: Stable FP4 RL Post-Training via Sequence Filtering and Sparse Channel Compensation

FourSight addresses instability when applying NVFP4 W4A4 quantization to reinforcement learning post-training. It identifies that failures concentrate in outlier sequences and high-variance activation channels, then applies TIM-aware sequence filtering and sparse BF16 channel compensation. The method sustains near-BF16 accuracy and improves step-to-accuracy by 1.76-2.60x while staying within 2.3% of FP4 step time up to 120B-scale models.

arxiv1d agoScore 78

quantizationreinforcement learningmodel deployment

Research Editor selected

Artifact-to-Capability: Diagnosing Breaks in Capability Formation of Self-Evolving Agents

This paper introduces a formal definition of capability formation from artifacts in self-evolving agents, proposing five sequentially dependent properties and a three-scale diagnosis method. In freestyle Gomoku, Reflexion, Voyager, and DGM all show standard proxy signals but exhibit distinct capability-formation breaks, such as legalization gain, compositional override, and loss-only drift. The findings demonstrate that signal-based evaluation cannot reliably determine whether a capability has formed.

Why it matters: Provides a concrete diagnostic framework and counterexamples that challenge common evaluation practices in self-evolving AI agents, offering practical value for researchers and developers.

arxiv1d agoScore 85

self-evolving agentscapability evaluationagent diagnostics

Research Editor selected

WebCatalyst: High-Fidelity RL for Interactive HTML Generation

WebCatalyst is a reinforcement learning framework that improves interactive HTML generation from natural-language specs, using a game-level GUI assessor, Visual Anchor to prevent reward hacking, and Action-Trace Credit for token-level credit assignment. Trained on under 1K requests, it raises Cookie-Bench Mini Games from 68.8 to 75.3 and WebGen-Bench accuracy from 48.8 to 56.9 on Qwen3.6-35B-A3B, outperforming Claude Opus 4.7 in average rank. The work highlights feedback fidelity as key to advancing interactive HTML generation.

Why it matters: Provides a concrete, novel RL method with measurable benchmark gains and analysis, valuable for AI researchers and practitioners in code generation.

arxiv1d agoScore 82

WebCatalystinteractive HTML generationreinforcement learning

Research Editor selected

JHiMA-WebRL: Joint Hierarchical Multi-Agent RL for Long-Horizon Web Tasks

JHiMA-WebRL introduces a hierarchical multi-agent reinforcement learning framework for web agents, coupling a task decomposer with an actor and jointly training them. Using teacher-generated subtask supervision and an extension of GRPO, the framework achieves 37.2% success on WebArena-Lite-v2 with a 14B model, outperforming a 32B monolithic RL agent. Ablations confirm that joint updating of the decomposer is key.

Why it matters: This paper presents a concrete, recent AI development with clear performance gains and a novel joint training method, offering practical value for long-horizon web automation.

arxiv1d agoScore 85

Reinforcement LearningWeb NavigationMulti-Agent Systems

Research Editor selected

PEARL: A Durable Method for Suppressing Misaligned Behaviors in Language Models

This paper introduces PEARL, a GRPO-based reinforcement learning variant that suppresses undesired model behaviors more durably than standard methods. It tests on two deliberately misaligned model organisms with narrow and broad triggers, showing strong immediate suppression, preserved task accuracy, and durability under further fine-tuning. The method is most beneficial for broad misalignments that resist targeted SFT.

Why it matters: Provides a concrete, novel method with empirical results on durability, a key challenge in AI safety.

arxiv1d agoScore 85

AI alignmentbehavioral suppressionreinforcement learning

Research Editor selected

What Drives the Zero-to-One Jump? Diagnosing and Steering Hard-Prompt Learning in RLVR

The paper investigates the abrupt transition from unsolved to solved states in reinforcement learning with verifiable rewards (RLVR) for mathematical reasoning. The authors identify that negative rollouts preceding successful transitions retain higher early-stage generation entropy, motivating a new method called NAPO (Negative-Augmented Policy Optimization). Integrated with GRPO, NAPO injects informative gradients from negative examples and achieves significant improvements on AIME24 and AIME2025 benchmarks under fixed rollout budgets.

Why it matters: Provides a concrete diagnosis and steerable method for the zero-to-one jump phenomenon in RLVR, offering practical gains on hard math benchmarks.

arxiv2d agoScore 88

reinforcement learningmathematical reasoningpolicy optimization

Research Editor selected

Offline Approximate Value Iteration: A Reinforcement Learning Approach for Satellite Constellation Deployment

Researchers introduce a reinforcement learning-based approximate dynamic programming method to optimize Walker-type satellite constellation deployment under uncertainties like launch failures and satellite malfunctions. The approach uses offline approximate value iteration with linear function approximation and action pruning to reduce computational demands. Preliminary results show lower expected costs and deployment times compared to a rolling-horizon baseline, demonstrating a novel application of approximate dynamic programming in space logistics.

Why it matters: Presents a concrete, novel RL application to a real-world space logistics problem with measurable improvements over baselines.

arxiv2d agoScore 85

reinforcement learningspace logisticssatellite deployment

Research Editor selected

BLPO: Beyond-Local Policy Optimization for Long-Horizon LLM Agents

BLPO is a new reinforcement learning method for long-horizon LLM agents that estimates task-progress advantages from shared experience across tasks and updates, avoiding the need for a learned critic or extra rollouts. It summarizes trajectory prefixes into task-progress states and abstracts actions by function, using a global memory with balanced aggregation to control bias. Experiments on ALFWorld and WebShop with 1.5B and 7B policies show improved task success and faster learning under matched training budgets.

Why it matters: This paper introduces a concrete algorithmic improvement for training LLM agents on long-horizon tasks, with empirical gains on standard benchmarks, making it valuable for researchers and practitioners.

arxiv2d agoScore 85

LLM agentsreinforcement learninglong-horizon tasks

Research

MIRA: Reinforcing Multimodal Reasoning via Deceptive Contextual Augmentation

MIRA is a training framework that improves multimodal reasoning robustness by injecting deceptive visual contexts during training, creating 'hard traps' that stress-test models against misleading information. It also introduces a group-wise reflection-triggering mechanism for autonomous error detection and correction. Experiments show an average 7% improvement on in-domain benchmarks without human annotations.

arxiv2d agoScore 78

multimodal reasoningreinforcement learningrobustness

Research Editor selected

Axiomatic Framework for RL in Open Multi-Agent Systems

This paper proposes an axiomatic framework for reinforcement learning in open multi-agent systems, deriving value function learning from Shapley axioms. It introduces Shapley Machines and Banzhaf Machines, which improve learning efficiency and generalization over base algorithms like IPPO and POAM in NAHT benchmarks.

Why it matters: Provides a principled game-theoretic foundation and practical algorithmic templates for a challenging RL setting, with demonstrated improvements.

arxiv2d agoScore 85

Reinforcement LearningMulti-Agent SystemsCooperative Game Theory