Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2610.16133v1 Announce Type: cross Abstract: Puzzles offer a natural testbed for Large Language Models (LLMs) reasoning because they pose verifiable goals under partial information and require m...
arXiv:2610.16172v1 Announce Type: cross Abstract: Recent multimodal large language models (MLLMs) achieve strong results on video question answering, yet often fail to recover the temporal structure...
arXiv:2610.16784v1 Announce Type: cross Abstract: Generating and editing presentation slides requires models to combine accurate text rendering, instruction following, visual grounding, aesthetic des...
The paper introduces ProAS, a Progress‑Aware Advantage Shaping framework designed to improve critic‑free reinforcement learning for large language model agents. ProAS uses a dynamic Agentic Reference Graph to provide fine‑grained credit assignment through Masking Unreasonable Incentives and Asymmetric Penalty Redistribution, avoiding the uniform advantage broadcast that can reinforce invalid actions. Experiments on Qwen2.5‑1.5B‑Instruct and Qwen2.5‑7B‑Instruct show that ProAS raises baseline success rates to 91.9% and 94.3% on ALFWorld and 66.7% and 70.8% on WebShop, while speeding up training convergence up to 2.44× and remaining robust to imperfect reference graphs.
arXiv:2610.16067v1 Announce Type: cross Abstract: Agent evaluation harnesses are software systems that run test suites, generate inputs, and decide outcomes with test oracles. This paper audits such...
Large language models increasingly rely on external memory to answer queries grounded in long-horizon histories such as multi-session dialogues and lengthy documents. However, existing memory methods...
LLM-agent evaluation reports behavioral scores but leaves the identity of the deployed runtime stack unreported. A tampered deployment that preserves evaluated outputs passes every output-only evaluat...
We present RoboCloth, a dataset of 500 real cloth materials captured under flexible, calibrated camera and lighting configurations, where both are robotically controlled during acquisition. Each mater...
To address sparse terminal rewards in LLM arithmetic reasoning, we propose a Bellman-consistent trajectory RL method. Our framework introduces Trajectory Bellman Residual Minimization (TBRM) to transf...
We present CommerceGen-Studio, an end-to-end framework for generating commercial-grade main images for e-commerce Stock Keeping Units (SKUs). Our framework is organized along a three-stage pipeline of...
Achieving general spatial intelligence requires a unified understanding of both static 3D and dynamic 4D. However, we find that existing models struggle to excel at both: 3D post-training can weaken d...
Understanding the social intelligence of large language models (LLMs) is increasingly important for applications involving human-AI interaction and multi-agent environments. Social intelligence compri...
Agents driven by large language models are increasingly deployed on long-horizon tasks, where they use tools and modify real workspaces. How well they perform depends as much on the harness around the...
Document understanding systems are typically evaluated as separate components via layout analysis, optical text recognition, reading-order prediction, and image captioning. This separation leaves scie...
A ReAct-style agent accumulates observations, intermediate results, and failed attempts in a single context. As this context grows, stale and off-path information consumes its limited capacity and obs...
Large language models (LLMs) have demonstrated multilingual capabilities across diverse language generation and understanding tasks. Yet effective code-switching requires more than multilingual profic...
Autoregressive generation underlies real-time, causal video synthesis and is the backbone of video world models. Today's dominant approach distills a bidirectional diffusion model into a causal few-st...
Effective social interaction requires more than fluent responses: agents must reach plans that fit the participants' needs and circumstances. Existing evaluations of social agents mainly rely on LLM j...
Batch black-box optimization is important for expensive systems where many candidates can be evaluated in parallel, yet only a few rounds of evaluation are affordable. In this regime, effective batch...
Current video object removal methods suffer from prohibitive latency (minutes per video) and non-causal processing that prevents real-time interaction. We present StreamErase, enabling sub-second late...