Search: “reasoning”

arXiv:2606.11052v1 Announce Type: new Abstract: Chain-of-thought (CoT) supervised fine-tuning (SFT) is widely adopted to improve reasoning ability, yet we find that it systematically degrades long-con

arXiv:2606.10385v1 Announce Type: cross Abstract: On-policy distillation (OPD) has demonstrated strong empirical gains in enhancing complex reasoning in LLMs by aligning a student model with a teacher

arXiv:2606.08471v1 Announce Type: cross Abstract: Recently, language models have made rapid progress across various domains and applications. However, their capability for self-improvement, i.e., whet

arXiv:2606.07000v1 Announce Type: new Abstract: Recent post-training methods, particularly Reinforcement Learning with Verifiable Rewards (RLVR), have significantly enhanced the reasoning ability of L

arXiv:2606.06836v1 Announce Type: cross Abstract: Language-guided UAV agents must execute long-horizon semantic instructions while producing smooth, physically feasible continuous flight commands, yet

arXiv:2606.05645v1 Announce Type: new Abstract: Autonomous driving requires reasoning about how ego actions shape the evolution of the surrounding world. However, most end-to-end methods rely on direc

arXiv:2606.05749v1 Announce Type: new Abstract: Iterative retrieval-reasoning agents have recently shown promise for multimodal long-document question answering. However, most existing systems maintai

arXiv:2606.04911v1 Announce Type: cross Abstract: Breast cancer remains a leading cause of cancer-related mortality among women. Its clinical management requires multimodal reasoning across a clinical

arXiv:2606.05030v1 Announce Type: new Abstract: Autoregressive chain-of-thought (CoT) reasoning in large language models (LLMs) is fundamentally forward-directed: each step conditions only on prior to

arXiv:2606.03144v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as self-study assistants in technical disciplines, yet their reliability as mathematical reasoning as

arXiv:2606.03762v1 Announce Type: cross Abstract: Agentic reinforcement learning (RL) equips large language models (LLMs) with tool-use capabilities that substantially improve reasoning on complex tas

arXiv:2602.16902v4 Announce Type: replace Abstract: We introduce LLM-Wikirace, a benchmark for evaluating planning, reasoning, and world knowledge in large language models (LLMs). In LLM-Wikirace, mod

arXiv:2606.00820v1 Announce Type: new Abstract: Multi-agent debate (MAD) is a promising strategy for improving LLM reasoning, but when agents converge on a shared answer, it is unclear whether that co

arXiv:2602.02416v2 Announce Type: replace Abstract: Self-correction in language models remains elusive. In this work, we explore whether language models can explicitly localize errors in incorrect rea

arXiv:2606.00029v1 Announce Type: cross Abstract: Retrieval-augmented generation systems struggle with temporal reasoning and evidence fusion when answering complex questions over historical criminal

arXiv:2510.02919v2 Announce Type: replace Abstract: Large language models (LLMs) increasingly solve complex reasoning tasks via long chain-of-thought, but their forward-only autoregressive generation

arXiv:2605.30451v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) is an effective recipe for training reasoning models with verifier-based outcome rewards, but its supervision

arXiv:2605.29116v1 Announce Type: new Abstract: When multiple LLM agents solve the same problem, standard practice compresses each agent's reasoning into a majority vote or layered synthesis, treating

arXiv:2605.29705v1 Announce Type: new Abstract: Trajectory prediction is a fundamental task for autonomous systems, requiring complex reasoning about multi-agent interactions and intents. Large langua

arXiv:2510.11170v2 Announce Type: replace-cross Abstract: With the rise of reasoning language models and test-time scaling methods as a paradigm for improving model performance, substantial computatio

arXiv:2605.28142v1 Announce Type: cross Abstract: Inference-time sampling can elicit strong reasoning abilities from language models without additional training. Existing power-sampling methods do so

arXiv:2605.28741v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) are rapidly evolving toward true multimodal reasoning, with visual search representing a concrete instantiation of

arXiv:2605.28631v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) can yield large reasoning gains from very few training instances, yet its strong sensitivity to wh

arXiv:2511.11896v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have recently shown strong potential in vulnerability detection (VD). However, accurately detecting vulnerabiliti

arXiv:2601.14702v2 Announce Type: replace Abstract: Autonomous driving requires reliable perception and safe decision-making in complex scenarios. Recent vision-language models (VLMs) demonstrate reas

arXiv:2605.26893v1 Announce Type: cross Abstract: Chain-of-Thought (CoT) reasoning has advanced large language models (LLMs), but outcome-based supervision leads to pervasive post-hoc rationalization,

arXiv:2605.26781v1 Announce Type: new Abstract: Advanced Large Multimodal Models (LMMs) have demonstrated impressive performance in K-12 reasoning tasks, exhibiting great promise as intelligent tutors

arXiv:2605.25188v1 Announce Type: new Abstract: Multi-agent LLM systems improve reasoning by combining outputs from multiple agents, but interaction-heavy methods can introduce error propagation and h

arXiv:2510.06672v3 Announce Type: replace Abstract: Reinforcement learning algorithms such as GRPO have driven recent advances in large language model (LLM) reasoning. While scaling the number of roll

arXiv:2605.23590v1 Announce Type: new Abstract: ReAct-style agents for search-intensive, multi-step reasoning tasks rely largely on their own internal judgment to decide what evidence to seek, which r

arXiv:2605.23861v1 Announce Type: cross Abstract: Causal generative modeling is essential for developing reliable and transparent AI systems capable of counterfactual reasoning. While existing approac

arXiv:2601.23086v2 Announce Type: replace Abstract: Chain-of-thought (CoT) reasoning provides a significant performance uplift to LLMs by enabling planning, exploration, and deliberation of their acti

arXiv:2511.20785v3 Announce Type: replace Abstract: Large multimodal models (LMMs) have shown great potential for video reasoning with textual Chain-of-Thought. However, they remain vulnerable to hall

arXiv:2605.22620v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning ability of LLMs, but often depends on external supervis

arXiv:2605.19859v1 Announce Type: new Abstract: Vision-language models (VLMs) have rapidly evolved into general-purpose multimodal reasoners with strong zero-shot generalization. In this context, VLMs

arXiv:2605.19952v1 Announce Type: new Abstract: To enable reliable long-term interaction, LLM agents require a memory system that can faithfully store, efficiently retrieve, and deeply reason over acc

arXiv:2602.03955v2 Announce Type: replace Abstract: While large language model (LLM) multi-agent systems achieve superior reasoning performance through iterative debate, practical deployment is limite

arXiv:2605.18621v1 Announce Type: cross Abstract: Spatial intelligence requires multimodal large language models (MLLMs) to move beyond single-view perception and reason consistently about objects, vi

arXiv:2605.17037v1 Announce Type: cross Abstract: Reinforcement learning (RL) has demonstrated potential for enhancing reasoning in large language models (LLMs). However, effective RL training, which

arXiv:2605.16999v1 Announce Type: new Abstract: Reinforcement learning post-training has substantially improved the reasoning accuracy of vision-language models, yet the resulting policies remain poor

arXiv:2605.18636v1 Announce Type: new Abstract: Long-horizon multimodal agents in open-world games must stay goal-directed across many low-level interactions under tight token and latency budgets. Exi

arXiv:2605.15710v1 Announce Type: new Abstract: Existing benchmarks for multimodal memory reasoning largely evaluate systems within pre-assembled contexts, but under-evaluate whether agents can use ev

arXiv:2605.15100v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable abilities in reasoning. However, maximizing their potential through inference-time scaling fac

arXiv:2605.15102v1 Announce Type: cross Abstract: Large language model (LLM) based multi-turn dialogue systems often struggle to track dependencies across non-adjacent turns, undermining both consiste

arXiv:2605.14539v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective paradigm for improving the reasoning capabilities of large language mo

arXiv:2605.14389v1 Announce Type: new Abstract: Time series forecasting is not just numerical extrapolation, but often requires reasoning with unstructured contextual data such as news or events. Whil