Self-Distilled Policy Gradient
On-policy self-distillation, where a language model conditions on privileged context to supervise its own generations, is a promising source of dense supervision for sparse-reward ...
Research Papers
Latest AI/ML research from ArXiv and Papers with Code
RobotValues: Evaluating Household Robots When Human Values Conflict
While household robots are often evaluated based on task completion, everyday domestic environments involve value-conflicting situations in which robots are expected to choose acti...
AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents
Language agents spend substantial inference time solving individual tasks, yet the experience acquired in one episode is often underutilized in future episodes. Continual learning ...
Agent libOS: A Library-OS-Inspired Runtime for Long-Running, Capability-Controlled LLM Agents
Large language model (LLM) agents are evolving from request-response assistants into long-running software actors: they maintain state across model calls, fork subtasks, wait for e...
SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual Misinformation
Recent generative models can now produce visual artifacts with realistic embedded text and layouts, creating a new misinformation threat: synthetic credibility. We introduce SYNCRE...
Training-Free Multi-Concept LoRA Composition with Prompt-Aware Weighting
Low-Rank Adaptation (LoRA) successfully enables personalization in text-to-image generation by adapting pre-trained diffusion models to specific visual concepts and styles. However...
Large Language Models Are Overconfident in Their Own Responses
Prior work has shown that instruction-tuned large language models (LLMs) are less well calibrated than their base pre-trained counterparts. However, little is known about the frequ...
AURA: Action-Gated Memory for Robot Policies at Constant VRAM
The KV-cache is the right memory for datacenters but the wrong memory for robots. Datacenter inference batches many short requests and resets them, amortizing an attention cache ac...
Ψ-Bench: Evaluating Persona-Sensitive Influencing in Persuasive Dialogues
Personalization is a crucial capability of modern language agents. However, current research primarily positions personalized agents as passive responders to user preferences, limi...
MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?
Abundant procedural knowledge on the Web holds great potential for helping agents solve long-horizon tasks. However, such knowledge is often multimodal, heterogeneous, noisy, and i...
HarnessForge: Joint Harness and Policy Evolution for Adaptive Agent Systems
LLM agents are increasingly expected to operate across heterogeneous task regimes that require distinct execution paradigms. This challenges fixed agent systems and motivates syste...
Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams
Auto-harness systems such as A-Evolve, GEPA, and Meta-Harness improve LLM agents by optimizing prompts, skills, tools, memories, and supporting infrastructure from execution feedba...
TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL
Reinforcement learning (RL) for visual reasoning needs scalable, verifiable, and controllable training signals. Existing visual RL post-training trains on static curated datasets, ...
Thinking in Blender: Staged Executable Inverse Graphics with Vision-Language Models
Inverse graphics is a longstanding and highly underconstrained problem that seeks to reconstruct images as editable 3D scenes which can be rendered, relit, and manipulated. In this...
Who Annotates in NLP? A Large-scale Assessment of Human Annotation Reporting between 2018 and 2025
Human annotation is the empirical foundation of much NLP research, from dataset construction to model evaluation, but papers often leave unclear who produced the annotations and ho...
VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization
The recent "Reasoning with Video" paradigm utilizes Video Generation Models (VGMs) to generate temporally coherent visual trajectories to complete reasoning tasks. Although state-o...
K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts
Frontier model evaluations are shifting from foundational capabilities (e.g., instruction following and reasoning) toward compositional, agentic ones, but Korean agentic benchmarks...
On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters
Parameter-efficient fine-tuning (PEFT) is usually treated as a cheaper alternative to full fine-tuning. We study a broader role: small trainable adapters as persistent local state ...
Semantic Motion Anchors: Bridging Motion and Meaning in Co-Speech Gestures
Learning a shared representation between spoken text and gesture is central to co-speech gesture retrieval, synthesis, and understanding, but remains challenging for semantically m...
Geometric Latent Reasoning Induces Shorter Generations in LLMs
Large language models solve complex problems by generating lengthy chains of explicit reasoning tokens. While effective, this makes reasoning expensive, length-sensitive, and const...
Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation
On-Policy distillation (OPD) in large language models is shifting from full-trace KL supervision toward more selective training paradigms. Recent OPD methods increasingly focus on ...
Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses
Search agents are often trained as policies over growing transcripts: the model must decide how to search while also remembering what it has seen, which evidence is useful, which c...
Policy and World Modeling Co-Training for Language Agents
Reinforcement learning (RL) improves large language model (LLM) agents by teaching them which actions lead to high rewards, but provides little supervision on what those actions do...
WALL-WM: Carving World Action Modeling at the Event Joints
WALL-WM is a World Action Model that shifts video-action learning from chunk-centric optimization to event-grounded Vision-Language-Action pretraining, using semantically coherent ...