{"total":691,"items":[{"citing_arxiv_id":"2605.13825","ref_index":53,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"History Anchors: How Prior Behavior Steers LLM Decisions Toward Unsafe Actions","primary_cat":"cs.AI","submitted_at":"2026-05-13T17:50:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A single consistency instruction with harmful prior actions causes aligned frontier LLMs to select unsafe options at 91-98% rates in high-stakes domains, with escalation and inverse scaling by model size.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13751","ref_index":35,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Learning Responsibility-Attributed Adversarial Scenarios for Testing Autonomous Vehicles","primary_cat":"cs.RO","submitted_at":"2026-05-13T16:33:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CARS integrates responsibility attribution into adversarial scenario generation to produce physically feasible collisions with high attribution rates under regulation-prescribed driver models for autonomous vehicle testing.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13638","ref_index":30,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"CO-MAP: A Reinforcement Learning Approach to the Qubit Allocation Problem","primary_cat":"quant-ph","submitted_at":"2026-05-13T15:04:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Reinforcement learning policy for qubit mapping reduces SWAP overhead by 65-85% versus standard quantum compilers on MQTBench and Queko benchmark circuits.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13534","ref_index":47,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Scaling Retrieval-Augmented Reasoning with Parallel Search and Explicit Merging","primary_cat":"cs.AI","submitted_at":"2026-05-13T13:46:35+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"MultiSearch uses parallel multi-query retrieval plus explicit merging inside a reinforcement-learning loop to improve retrieval-augmented reasoning, outperforming baselines on seven QA benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13269","ref_index":132,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Submodular Multi-Agent Policy Learning for Online Distributed Task Allocation in Open Multi-Agent Systems","primary_cat":"eess.SY","submitted_at":"2026-05-13T09:48:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"SubMAPG uses a new Partition Multilinear Extension to derive unbiased policy gradients from submodular difference rewards, delivering 1/2-approximation and sublinear dynamic regret for online distributed task allocation in open multi-agent systems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13131","ref_index":43,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"ERPPO: Entropy Regularization-based Proximal Policy Optimization","primary_cat":"cs.LG","submitted_at":"2026-05-13T08:01:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"ERPPO adds a DSA-based ambiguity estimator to MAPPO and switches between L1 and L2 entropy regularization to improve exploration and stability in non-stationary multi-dimensional observations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13105","ref_index":20,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"What to Ignore, What to React: Visually Robust RL Fine-Tuning of VLA Models","primary_cat":"cs.RO","submitted_at":"2026-05-13T07:15:37+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PAIR-VLA adds invariance and sensitivity objectives over paired visual variants during PPO fine-tuning of VLA models, yielding 9-16% average gains on ManiSkill3 under distractors, textures, poses, viewpoints, and lighting shifts.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13080","ref_index":94,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Learning to See What You Need: Gaze Attention for Multimodal Large Language Models","primary_cat":"cs.CV","submitted_at":"2026-05-13T06:54:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Gaze Attention groups visual embeddings into selectable regions and dynamically restricts attention to task-relevant ones, matching dense baselines with up to 90% fewer visual KV entries via added context tokens.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13058","ref_index":29,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"MUJICA: Multi-skill Unified Joint Integration of Control Architecture for Wheeled-Legged Robots","primary_cat":"cs.RO","submitted_at":"2026-05-13T06:31:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A single reinforcement learning policy jointly trains multiple locomotion skills for wheeled-legged robots with DC-motor constraints and learns a proprioceptive skill selector for adaptive behavior.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12995","ref_index":39,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking","primary_cat":"cs.LG","submitted_at":"2026-05-13T04:52:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"F-GRPO factorizes group-relative policy optimization into generation and ranking phases within one autoregressive sequence, using order-invariant coverage and position-aware utility rewards to improve top-ranked performance on recommendation and multi-hop QA tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12913","ref_index":31,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Revisiting DAgger in the Era of LLM-Agents","primary_cat":"cs.LG","submitted_at":"2026-05-13T02:40:28+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DAgger-style training with turn-level policy interpolation raises 4B and 8B LLM agents to 27.3% and 29.8% on SWE-bench Verified, beating several larger published systems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12771","ref_index":45,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Adaptive Smooth Tchebycheff Attention for Multi-Objective Policy Optimization","primary_cat":"cs.RO","submitted_at":"2026-05-12T21:32:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"An adaptive smooth Tchebycheff controller for multi-objective RL lets agents reach non-convex Pareto regions in robotic tasks while avoiding the instability of static non-linear scalarizations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12748","ref_index":28,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators","primary_cat":"cs.CL","submitted_at":"2026-05-12T20:55:23+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"LLM simulators exhibit near-zero selective response to targeted misconception feedback and behave sycophantically, but SFT and SFS-aligned RL improve this property.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12689","ref_index":28,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"3D RL-DWA: A Hybrid Reinforcement Learning and Dynamic Window Approach for Goal-Directed Local Navigation in Multi-DoF Robots","primary_cat":"cs.RO","submitted_at":"2026-05-12T19:37:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A hybrid RL-DWA controller achieves high deformation and near-perfect path completion for deformable microrobots navigating simulated 3D vascular networks from sparse point clouds.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12652","ref_index":43,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Multi-Rollout On-Policy Distillation via Peer Successes and Failures","primary_cat":"cs.LG","submitted_at":"2026-05-12T18:57:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"MOPD improves on-policy distillation for LLMs by using peer successes for positive patterns and failures for negative examples to create more informative teacher signals.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12645","ref_index":66,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Training LLMs with Reinforcement Learning for Intent-Aware Personalized Question Answering","primary_cat":"cs.CL","submitted_at":"2026-05-12T18:38:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"IAP uses RL to train LLMs to explicitly infer and apply implicit user intent in single-turn personalized QA, achieving ~7.5% average macro-score gains over baselines on LaMP-QA.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12625","ref_index":17,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Driving Intents Amplify Planning-Oriented Reinforcement Learning","primary_cat":"cs.RO","submitted_at":"2026-05-12T18:10:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DIAL uses intent-conditioned CFG and multi-intent GRPO to expand and preserve diverse modes in continuous-action preference RL, lifting RFS to 9.14 and surpassing both prior best (8.5) and human demonstration (8.13).","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12484","ref_index":50,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Learning, Fast and Slow: Towards LLMs That Adapt Continually","primary_cat":"cs.LG","submitted_at":"2026-05-12T17:58:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Fast-Slow Training combines slow parameter updates with fast context optimization to achieve up to 3x better sample efficiency, higher performance, less forgetting, and preserved plasticity in continual LLM learning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12483","ref_index":15,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training","primary_cat":"cs.LG","submitted_at":"2026-05-12T17:57:48+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Sparse RL on a strong teacher followed by dense distillation to the student outperforms direct GRPO on the student for math tasks, with a forward-KL + OPD bridge enabling further gains.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12380","ref_index":25,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training","primary_cat":"cs.LG","submitted_at":"2026-05-12T16:44:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A new RL objective adapts trust-region and off-policy handling automatically via normalized effective sample size of batch policy ratios, matching tuned baselines without new hyperparameters.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12379","ref_index":18,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Discrete Flow Matching for Offline-to-Online Reinforcement Learning","primary_cat":"cs.LG","submitted_at":"2026-05-12T16:44:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DRIFT enables stable offline-to-online fine-tuning of CTMC policies in discrete RL via advantage-weighted discrete flow matching, path-space regularization, and candidate-set approximation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12365","ref_index":57,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"QAP-Router: Tackling Qubit Routing as Dynamic Quadratic Assignment with Reinforcement Learning","primary_cat":"quant-ph","submitted_at":"2026-05-12T16:34:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"QAP-Router models qubit routing as dynamic QAP and applies RL with a solution-aware Transformer to cut CNOT counts by 12-30% versus industry compilers on real circuit benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12288","ref_index":102,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"TokenRatio: Principled Token-Level Preference Optimization via Ratio Matching","primary_cat":"cs.CL","submitted_at":"2026-05-12T15:44:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TBPO derives a token-level preference optimization objective from sequence-level pairwise data via Bregman divergence ratio matching that generalizes DPO and improves alignment quality.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12272","ref_index":17,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"BatchBench: Toward a Workload-Aware Benchmark for Autoscaling Policies in Big Data Batch Processing -- A Proposed Framework","primary_cat":"cs.IR","submitted_at":"2026-05-12T15:36:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"BatchBench is a proposed framework with workload taxonomy, parameterized generator, five-axis evaluation harness, and standardized agent interface to enable fair comparison of autoscaling policies.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12262","ref_index":3,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Missingness-MDPs: Bridging the Theory of Missing Data and POMDPs","primary_cat":"cs.AI","submitted_at":"2026-05-12T15:28:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Miss-MDPs extend POMDPs with missing-data theory to learn observation missingness patterns and compute near-optimal policies with high-probability guarantees.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12261","ref_index":38,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Delay-Empowered Causal Hierarchical Reinforcement Learning","primary_cat":"cs.LG","submitted_at":"2026-05-12T15:28:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"DECHRL models causal structures and stochastic delay distributions within hierarchical RL and incorporates them into a delay-aware empowerment objective to improve performance under temporal uncertainty.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12236","ref_index":63,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning","primary_cat":"cs.RO","submitted_at":"2026-05-12T15:07:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TMRL bridges behavioral cloning pretraining and RL finetuning via diffusion noise and timestep modulation to enable controlled exploration, improving sample efficiency and enabling real-world robot training in under one hour.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12227","ref_index":55,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Combining On-Policy Optimization and Distillation for Long-Context Reasoning in Large Language Models","primary_cat":"cs.CL","submitted_at":"2026-05-12T15:04:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"dGRPO merges outcome-based policy optimization with dense teacher guidance from on-policy distillation, yielding more stable long-context reasoning on the new LongBlocks synthetic dataset.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12206","ref_index":32,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"On the Importance of Multistability for Horizon Generalization in Reinforcement Learning","primary_cat":"cs.LG","submitted_at":"2026-05-12T14:45:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Multistability is necessary for temporal horizon generalization in POMDPs, sufficient in simple tasks along with transient dynamics in complex ones, while monostable parallelizable RNNs like SSMs and gated linear RNNs fail by construction.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12112","ref_index":52,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy","primary_cat":"cs.CV","submitted_at":"2026-05-12T13:29:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Policy entropy remains constant in flow-matching models during RLHF due to fixed noise schedules while perceptual diversity collapses from mode-seeking policy gradients, so perceptual entropy constraints are introduced to preserve diversity and improve quality.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12084","ref_index":53,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Learning What Matters: Adaptive Information-Theoretic Objectives for Robot Exploration","primary_cat":"cs.RO","submitted_at":"2026-05-12T13:07:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"QOED selects identifiable parameter directions via Fisher matrix eigenspace analysis and modifies exploration objectives to approximate ideal information gain under bounded nuisance assumptions, yielding 21-35% performance gains in robotic tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12070","ref_index":17,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction","primary_cat":"cs.LG","submitted_at":"2026-05-12T12:57:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Missing old logits in async agentic RL entangle discrepancy and staleness terms in PPO off-policy correction; exact acquisition methods and revised PPO-EWMA restore decoupled updates with reported gains in speed and performance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12061","ref_index":258,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory","primary_cat":"cs.AI","submitted_at":"2026-05-12T12:47:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SAGE is a self-evolving agentic graph-memory engine that dynamically constructs and refines structured memory graphs via writer-reader feedback, yielding performance gains on multi-hop QA, open-domain retrieval, and long-term agent benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12058","ref_index":5,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"H\\\"older Policy Optimisation","primary_cat":"cs.LG","submitted_at":"2026-05-12T12:45:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"HölderPO unifies token aggregation in GRPO via the Hölder mean with dynamic p annealing, reporting 54.9% average math-benchmark accuracy and 93.8% ALFWorld success.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12034","ref_index":35,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation","primary_cat":"cs.MM","submitted_at":"2026-05-12T12:16:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Staged post-training with self-distillation lets a 3B omni-modal model match or slightly exceed a 30B model on a visually debiased benchmark.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12022","ref_index":20,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"SAGE: Scalable Automated Robustness Augmentation for LLM Knowledge Evaluation","primary_cat":"cs.CL","submitted_at":"2026-05-12T12:09:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"UNKNOWN","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SAGE trains a rubric-based verifier and an RL-optimized generator on seed human data to scalably augment LLM knowledge benchmarks, matching human-annotated quality on HellaSwag at lower cost and generalizing to MMLU.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12004","ref_index":48,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Learning Agentic Policy from Action Guidance","primary_cat":"cs.CL","submitted_at":"2026-05-12T11:54:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"ActGuide-RL uses human action data as plan-style guidance in mixed-policy RL to overcome exploration barriers in LLM agents, matching SFT+RL performance on search benchmarks without cold-start training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11981","ref_index":36,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"High-lift Wing Separation Control via Bayesian Optimization and Deep Reinforcement Learning","primary_cat":"physics.flu-dyn","submitted_at":"2026-05-12T11:34:46+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Bayesian optimization improved the aerodynamic efficiency of a 30P30N high-lift wing by 10.9% using synthetic jets, while deep reinforcement learning achieved negligible gains due to a penalty-heavy reward function.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11975","ref_index":9,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Stochastic Minimum-Cost Reach-Avoid Reinforcement Learning","primary_cat":"cs.LG","submitted_at":"2026-05-12T11:31:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Introduces RAPCs and a contraction Bellman operator that jointly enforce probabilistic reach-avoid constraints while minimizing expected costs in stochastic RL, with almost-sure convergence to local optima.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11974","ref_index":40,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Towards Order Fairness: Mitigating LLMs Order Sensitivity through Dual Group Advantage Optimization","primary_cat":"cs.LG","submitted_at":"2026-05-12T11:31:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"DGAO uses reinforcement learning to optimize LLMs for both accuracy and order stability by balancing intra-group accuracy advantages and inter-group stability advantages.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11922","ref_index":20,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"StepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement Learning","primary_cat":"cs.SE","submitted_at":"2026-05-12T10:36:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"StepCodeReasoner aligns code reasoning with verifiable stepwise execution traces via print anchors and bi-level GRPO reinforcement learning, reaching SOTA results on CRUXEval (91.1%) and LiveCodeBench (86.5%) for a 7B model.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11908","ref_index":19,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Delightful Gradients Accelerate Corner Escape","primary_cat":"cs.LG","submitted_at":"2026-05-12T10:21:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Delightful Policy Gradient removes exponential corner trapping in softmax policy optimization for bandits and tabular MDPs, achieving logarithmic escape times and global O(1/t) convergence.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11906","ref_index":33,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"YFPO: A Preliminary Study of Yoked Feature Preference Optimization with Neuron-Guided Rewards for Mathematical Reasoning","primary_cat":"cs.CL","submitted_at":"2026-05-12T10:18:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"YFPO augments standard preference optimization with neuron-level activation margins from math-related features to improve LLM reasoning on math tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.12569","ref_index":21,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Active Sensing with Meta-Reinforcement Learning for Emitter Localization from RF Observations","primary_cat":"eess.SP","submitted_at":"2026-05-12T10:03:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A meta-reinforcement learning agent achieves 80.1% success in localizing RF emitters by sequentially sensing the environment with a 2x2 patch antenna in Sionna ray-tracing simulations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11882","ref_index":35,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment","primary_cat":"cs.AI","submitted_at":"2026-05-12T09:56:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FATE lets LLM agents self-evolve safer behaviors by generating and filtering repairs from their own failure trajectories using verifiers and Pareto optimization.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11865","ref_index":41,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Variance-aware Reward Modeling with Anchor Guidance","primary_cat":"stat.ML","submitted_at":"2026-05-12T09:46:26+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Anchor-guided variance-aware reward modeling uses two response-level anchors to resolve non-identifiability in Gaussian models of pluralistic preferences, yielding provable identification, a joint training objective, and improved RLHF performance.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11726","ref_index":48,"ref_count":2,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models","primary_cat":"cs.LG","submitted_at":"2026-05-12T08:09:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Introduces Block-R1 benchmark, Block-R1-41K dataset, and a conflict score to handle domain-specific optimal block sizes in RL post-training of diffusion LLMs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11723","ref_index":34,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating","primary_cat":"cs.CV","submitted_at":"2026-05-12T08:08:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"CaC is a hierarchical spatiotemporal concentrating reward model for video anomalies that reports 25.7% accuracy gains on fine-grained benchmarks and 11.7% anomaly reduction in generated videos via a new dataset and GRPO training with temporal/spatial IoU rewards.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11706","ref_index":25,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"GRAFT: Graph-Tokenized LLMs for Tool Planning","primary_cat":"cs.LG","submitted_at":"2026-05-12T07:59:41+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"GRAFT internalizes tool dependency graphs via dedicated special tokens in LLMs and applies on-policy context distillation to achieve higher exact sequence matching and dependency legality than prior external-graph methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11694","ref_index":14,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Augmented Lagrangian Method for Last-Iterate Convergence for Constrained MDPs","primary_cat":"cs.LG","submitted_at":"2026-05-12T07:51:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"An inexact augmented Lagrangian method with projected Q-ascent yields global last-iterate convergence guarantees for constrained MDP policy optimization, extending from tabular to log-linear and non-linear policies.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}