ReDAct: Uncertainty-Aware Deferral for LLM Agents
arXiv:2604.07036v1 Announce Type: cross Abstract: Recently, LLM-based agents have become increasingly popular across many applications, including complex sequential decision-making problems. However,
Knowledge catalogue
arXiv:2604.07036v1 Announce Type: cross Abstract: Recently, LLM-based agents have become increasingly popular across many applications, including complex sequential decision-making problems. However,
arXiv:2604.08243v1 Announce Type: new Abstract: Although Large Language Models (LLMs) demonstrate remarkable reasoning capabilities, inherent social biases often cascade throughout the Chain-of-Though
arXiv:2604.07592v1 Announce Type: new Abstract: Embodied-AI agents must reason about how objects move and interact in 3-D space over time, yet existing smaller frontier Large Language Models (LLMs) st
arXiv:2604.03647v2 Announce Type: replace-cross Abstract: In the unsupervised self-evolution of Multimodal Large Language Models, the quality of feedback signals during post-training is pivotal for st
arXiv:2503.01804v4 Announce Type: replace Abstract: Ensuring both syntactic and semantic correctness in Large Language Model (LLM) outputs remains a significant challenge, despite being critical for r
Vercel's AI Gateway now supports xAI's Grok 4.20 model family, including variants for multi-agent, reasoning (beta), and non-reasoning use cases, accessible without requiring a separate provider ac...
arXiv:2604.08494v1 Announce Type: cross Abstract: Scanpath similarity metrics are central to eye-movement research, yet existing methods predominantly evaluate spatial and temporal alignment while neg
arXiv:2610.21882v1 Announce Type: cross Abstract: Embodied spatial intelligence requires more than visual recognition: models must localize entities, reason about their relations, and express this kno
In production systems today, most AI agents operate as lightweight dispatchers. They parse a prompt, make an API call, retrieve a record, and hand back control. Their execution is fast, stateless and
arXiv:2610.20627v1 Announce Type: new Abstract: Vision-language models are increasingly used for driving-scene understanding, yet their defensive reasoning under weakly structured Global South traffic
arXiv:2511.16221v2 Announce Type: replace-cross Abstract: Despite their advanced reasoning capabilities, state-of-the-art Multimodal Large Language Models (MLLMs) still lack a core component of human
arXiv:2610.21195v1 Announce Type: new Abstract: On-policy distillation (OPD) improves a student language model by training on its own generated trajectories with supervision from a stronger teacher. H
arXiv:2610.21018v1 Announce Type: new Abstract: When every rollout for a problem fails, GRPO receives neither a successful exemplar nor a nonzero group-relative advantage, so it learns nothing from ex
arXiv:2610.22080v1 Announce Type: new Abstract: A language model can generate several solutions to the same problem, some leading to correct answers and others to incorrect ones. Many post-training me
arXiv:2610.22273v1 Announce Type: cross Abstract: Reasoning over long document contexts remains a challenge for large language models (LLMs). Standard retrieval methods are inherently reactive, bottle
arXiv:2610.22155v1 Announce Type: new Abstract: Real-time interaction requires agents to perceive evolving environments and act under temporal constraints, yet existing evaluations of real-time stream
arXiv:2610.14818v1 Announce Type: new Abstract: Agentic AI moves generative AI applications toward systems that coordinate reasoning, enterprise context, model inference, and external actions. Integra
arXiv:2610.14382v1 Announce Type: new Abstract: Agentic AI systems operating over geospatial data require more than autonomous reasoning and tool use; they must also support explicit orchestration, sp
arXiv:2610.19080v1 Announce Type: new Abstract: Reinforcement learning (RL) has substantially improved the reasoning of autoregressive and discrete-diffusion language models. Language models that gene
arXiv:2606.17029v2 Announce Type: replace Abstract: Deep research agents synthesize long-form reports by searching and reasoning over retrieved evidence. Reinforcement learning with rubric-based rewar
arXiv:2506.20642v3 Announce Type: replace Abstract: Chain-of-Thought (CoT) prompting significantly enhances large language models' (LLMs) problem-solving capabilities, but still struggles with complex
arXiv:2610.19899v1 Announce Type: new Abstract: Neural networks operate naturally on finite-dimensional vectors, yet many problems require reasoning about higher-order objects such as distributions, f
arXiv:2610.19611v1 Announce Type: new Abstract: Modern vision-language models can accept multi-image contexts, but aggregate accuracy rarely reveals where a multi-image reasoning pipeline fails. We st
arXiv:2610.15228v1 Announce Type: new Abstract: Words are increasingly becoming an interface for action: large language models (LLMs) can now invoke tools, operate devices, and make decisions that aff
arXiv:2610.14341v1 Announce Type: new Abstract: We present CoPlanVLM, which uses a Vision Language Model (VLM) to translate a single natural-language instruction and image into coordinated paths for a
arXiv:2610.18670v1 Announce Type: cross Abstract: Reliable robot autonomy requires reasoning about the world from partial and noisy observations. However, many perception systems model only visible sc
arXiv:2602.21189v3 Announce Type: replace Abstract: Pass@k is a widely used performance metric for verifiable large language model tasks, including mathematical reasoning, code generation, and short-a
arXiv:2610.13184v1 Announce Type: new Abstract: While reinforcement learning with verifiable reward (RLVR) enhances reasoning in large language models, its efficacy in long-horizon multimodal tasks re
arXiv:2610.12830v1 Announce Type: new Abstract: Reasoning post-training draws on offline demonstrations and policy-generated rollouts, yet conventional supervised fine-tuning (SFT) followed by reinfor
I was running Qwen3.8-Flash-Next (base and later Swift-1.5 NVFP4) on a paid pod seat for about a month, and it started answering with short strings that echoed its own earlier reasoning. I assumed the
No more excuses for GPU-poor folks not to start LLMing! Full 27B-class reasoning in ternary transformer weights, for llama.cpp (CUDA, Metal, CPU) ~9.3x smaller than FP16 (ideal) | 98.2% of FP16 intell
arXiv:2610.11920v1 Announce Type: new Abstract: For persistent and personalized conversational agents, memory systems can enable them to remember, update, and reason over long histories by storing pas
arXiv:2610.11502v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown strong reasoning capabilities when fine-tuned with reinforcement learning (RL), particularly through Group Relat
arXiv:2610.12391v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) often struggle to identify and use geometric relations in diagrams. Recent methods address this challenge by co
arXiv:2610.11332v1 Announce Type: new Abstract: Structured pruning reduces the deployment cost of reasoning language models, but the resulting capability degradation can hinder subsequent on-policy di
arXiv:2610.10623v1 Announce Type: cross Abstract: Looped Language Models (LoopLMs) offer a parameter efficient approach to scaling reasoning by reusing shared parameters across recurrent computation s
arXiv:2610.11196v1 Announce Type: cross Abstract: Large audio-language models (LALMs) exploit multimodal evidence, yet task-irrelevant audio can alter text-reasoning decisions when listening is unnece
arXiv:2610.11345v1 Announce Type: new Abstract: Self-evolving LLM agents promise to improve autonomously through continual interaction and learning, reducing their dependence on manually curated super
arXiv:2610.10179v1 Announce Type: new Abstract: Search agents enable Large Language Models (LLMs) to iteratively retrieve and use information for complex multi-hop questions. Reinforcement Learning wi
arXiv:2610.09788v1 Announce Type: new Abstract: Reward modeling often requires jointly representing and reasoning over multiple evaluation criteria, yet verbalizing this process token by token can inc
arXiv:2610.07094v1 Announce Type: cross Abstract: LLM deployment is shifting from single-turn completion to agentic trajectories in which a model plans, calls tools, reads results and reasons at test
arXiv:2610.07787v1 Announce Type: new Abstract: Multi-agent systems (MAS) powered by large language models have shown strong performance across code generation, mathematical reasoning, and question an
arXiv:2610.07851v1 Announce Type: new Abstract: Agentic workflows enable large language models (LLMs) to solve complex tasks by coordinating reasoning, tool use, and verification. However, a workflow
arXiv:2610.07954v1 Announce Type: new Abstract: Language-based trajectory predictors represent coordinates as discrete tokens and learn auxiliary tasks such as destination and group reasoning. This fo
arXiv:2606.16193v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language tasks, yet their internal visual representati
arXiv:2610.07533v1 Announce Type: cross Abstract: Audio language models must handle dozens of distinct skills, from pitch comparison and speaker counting to musical tempo estimation and emotion recogn
arXiv:2610.07350v1 Announce Type: new Abstract: Long chain-of-thought reasoning increases sequential decoding cost while creating a growing history of potentially reusable continuations. We investigat
arXiv:2610.05274v1 Announce Type: new Abstract: Roadside traffic reasoning requires every free-form textual claim to be backed by visual evidence. Existing grounded multimodal large language models (M
arXiv:2610.05033v1 Announce Type: new Abstract: Generating a high-quality gaming world from a natural-language game intent requires joint reasoning about scene structure, spatial layout, gameplay obje
arXiv:2610.05048v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) provides dense token-level supervision without a second model: one network acts as teacher with the reference solutio
arXiv:2610.06360v1 Announce Type: cross Abstract: Reinforcement learning post-training for language models relies on two reward designs: human preferences (RLHF, DPO) and binary verifiers (RLVR). Clin
arXiv:2610.04918v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards scales multimodal reasoning, but an outcome reward says how much a trajectory is worth, not how that valu
arXiv:2505.24033v3 Announce Type: replace-cross Abstract: We investigate whether hidden states from Structured State Space Models (SSMs) can be merged post hoc to support downstream reasoning. Inspire
arXiv:2610.06293v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable potential in video understanding, yet their reliance on retrospective summarizatio
arXiv:2610.02549v1 Announce Type: new Abstract: Time and event expression extraction are fundamental temporal reasoning tasks, but the problem remains difficult due to annotation ambiguity, domain sen
arXiv:2610.03123v1 Announce Type: cross Abstract: Existing streaming vision-language models (VLMs) continuously perceive and reason over visual streams, but their computational pathways remain fixed t
arXiv:2610.02391v1 Announce Type: cross Abstract: When a large language model solves a mathematical problem, its reasoning is largely hierarchical, and the solution often branches at a few tokens wher
arXiv:2610.02523v1 Announce Type: new Abstract: Developing cognitive models of algorithmic reasoning from behavioral data is a central problem in cognitive science that challenges current methods. Tra
arXiv:2610.02815v1 Announce Type: new Abstract: Long chain-of-thought reasoning substantially increases KV-cache memory during autoregressive decoding, as every generated token introduces new key and
Let's go https://huggingface.co/reflection! Introducing Beam: a highly efficient agentic open model with 501B total parameters and 23B active. - Frontier reasoning efficiency - Advances the Western op