{"total":15,"items":[{"citing_arxiv_id":"2605.10426","ref_index":24,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving","primary_cat":"cs.CV","submitted_at":"2026-05-11T12:01:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CoWorld-VLA extracts semantic, geometric, dynamic, and trajectory expert tokens from multi-source supervision and feeds them into a diffusion-based hierarchical planner, achieving competitive collision avoidance and trajectory accuracy on the NAVSIM v1 benchmark.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09104","ref_index":43,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Token Economics for LLM Agents: A Dual-View Study from Computing and Economics","primary_cat":"cs.AI","submitted_at":"2026-05-09T18:18:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"The paper delivers a unified survey of token economics for LLM agents, conceptualizing tokens as production factors, exchange mediums, and units of account across micro, meso, macro, and security dimensions using established economic theories.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Single Agent [28]→The Neoclassical Theory of the Firm [29], Factor Substitution [30]. Multi-Agent System [3]→Transaction Costs [31], Principal-agent Theory [32]. Agent Ecosystem [33]→Mechanism Design Theory [34], Congestion Externalities [35]. T oken Economics ofthe Single Agent (§3) Problem Modeling: Single-Agent Token Economics(§3.1) Computation andInference Efficiency(§3.2) T oken Density [36,37,38,39,40,41,42], T oken Quantity [43,44,45,46,47,48,49],Per-T oken Computation and Memory Cost [50,51,52,53,54,55,56],MoE architectures [57,58], Speculative decoding [59,60]. Memory Architecture andContext Management(§3.3) Context Window as Working Memory [61,62,63,64,65],Long-T erm and Episodic Memory [2,66,67,68,69,70]. Tooling andInformation Retrieval(§3.4) T ool Calling and Function Invocation [28,71,72,73,74,75],Retrieval-Augmented Generation [76,77,78,79,80,81,82]."},{"citing_arxiv_id":"2605.06285","ref_index":28,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LatentRAG: Latent Reasoning and Retrieval for Efficient Agentic RAG","primary_cat":"cs.CL","submitted_at":"2026-05-07T13:56:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"LatentRAG performs agentic RAG by generating latent tokens for thoughts and subqueries in one forward pass, matching explicit methods' accuracy on seven benchmarks while reducing latency by ~90%.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.06165","ref_index":78,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost","primary_cat":"cs.AI","submitted_at":"2026-05-07T12:51:49+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Post-Reasoning boosts LLM accuracy by reversing the usual answer-after-reasoning order, delivering mean relative gains of 17.37% across 117 model-benchmark pairs with zero extra cost.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.22709","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Thinking Without Words: Efficient Latent Reasoning with Abstract Chain-of-Thought","primary_cat":"cs.CL","submitted_at":"2026-04-24T16:45:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Abstract-CoT lets models reason with short discrete latent token sequences from a reserved vocabulary, using warm-up training and RL to match verbal CoT performance with up to 11.6x fewer tokens.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.21027","ref_index":93,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering","primary_cat":"cs.AI","submitted_at":"2026-04-22T19:18:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"HypEHR is a hyperbolic embedding model for EHR data that uses Lorentzian geometry and hierarchy-aware pretraining to answer clinical questions nearly as well as large language models but with much smaller size.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.18486","ref_index":16,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Xiaomi OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation","primary_cat":"cs.CV","submitted_at":"2026-04-20T16:37:22+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"OneVL achieves superior accuracy to explicit chain-of-thought reasoning at answer-only latency by supervising latent tokens with a visual world model decoder that predicts future frames.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.17892","ref_index":32,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LEPO: Latent Reasoning Policy Optimization for Large Language Models","primary_cat":"cs.LG","submitted_at":"2026-04-20T07:05:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"LEPO applies RL to continuous latent representations in LLMs by injecting Gumbel-Softmax stochasticity for diverse trajectory sampling and unified gradient estimation, outperforming existing discrete and latent RL methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.10500","ref_index":7,"ref_count":3,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Visual Enhanced Depth Scaling for Multimodal Latent Reasoning","primary_cat":"cs.CV","submitted_at":"2026-04-12T07:14:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Visual replay module and adaptive depth scaling improve multimodal latent reasoning, reaching SOTA benchmarks with faster inference than explicit chain-of-thought methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.09757","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MedLVR: Latent Visual Reasoning for Reliable Medical Visual Question Answering","primary_cat":"cs.CV","submitted_at":"2026-04-10T16:03:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"MedLVR interleaves latent visual reasoning segments in autoregressive decoding and uses two-stage training to raise average medical VQA accuracy from 48.3% to 53.4% over a Qwen2.5-VL-7B backbone on OmniMedVQA and five other benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.08299","ref_index":6,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SeLaR: Selective Latent Reasoning in Large Language Models","primary_cat":"cs.CL","submitted_at":"2026-04-09T14:32:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"SeLaR selectively applies latent soft reasoning in LLMs via entropy gating and contrastive regularization, outperforming standard CoT on five benchmarks without training.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.03679","ref_index":18,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"LightThinker++: From Reasoning Compression to Memory Management","primary_cat":"cs.CL","submitted_at":"2026-04-04T10:46:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LightThinker++ adds explicit adaptive memory management and a trajectory synthesis pipeline to LLM reasoning, cutting peak token use by ~70% while gaining accuracy in standard and long-horizon agent tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.03307","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"V-Reflection: Transforming MLLMs from Passive Observers to Active Interrogators","primary_cat":"cs.CV","submitted_at":"2026-03-31T03:57:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"V-Reflection introduces a think-then-look mechanism where MLLM latent states actively interrogate visual features via two-stage distillation from a box-guided teacher to a dynamic autoregressive student, narrowing the fine-grained perception gap on benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2503.16419","ref_index":20,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","primary_cat":"cs.CL","submitted_at":"2025-03-20T17:59:38+00:00","verdict":"ACCEPT","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A survey organizing techniques to achieve efficient reasoning in LLMs by shortening chain-of-thought outputs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2502.05171","ref_index":31,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach","primary_cat":"cs.LG","submitted_at":"2025-02-07T18:55:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A recurrent-depth architecture enables language models to improve reasoning performance by iterating computation in latent space, achieving gains equivalent to much larger models on benchmarks.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"adapters on top of weight-shared layers (Bae et al., 2024), or (dynamic) weight-tying of trained models (Hay and Wolf, 2023; Liu et al., 2024b). As mentioned in Section 6, while we consider the proposed recurrent depth approach to be a very natural way to learn to reason in continuous latent space from the ground up, the works of Hao et al. (2024); Cheng and Durme (2024) and Liu et al. (2024a) discuss how to finetune existing fixed- depth transformers with this capability. These works have a similar aim to ours, enabling reasoning in latent space, but approach this goal from separate directions. For additional discussions related to the idea of construct- ing a prior that incentivizes reasoning and algorithm learn-"}],"limit":50,"offset":0}