AI agents are playing an increasingly important role in physics research. However, existing physics benchmarks only evaluate fixed questions, isolated sub-tasks, or paper reproduction with given solutions, and rarely check research quality alongside correctness. We introduce FrontierPhysics, an end-to-end benchmark wit...
Bing-Ran You, Wen-Jun Ke, Ria Rosenauer et al.· 0 citations
Language agents read code, tool output, and dialogue in contexts that grow at every step. Dynamic sparse attention lets a small indexer choose the earlier tokens each query attends to, but the indexer still scores the whole prefix at every layer. Cross-layer reuse methods such as IndexCache rerun the indexer at only so...
Multimodal models and agents have emerged to enable AI systems to learn from and interact with the real world more like humans by integrating information across multiple modalities. However, enabling multimodal agents to continually acquire useful information from complex, heterogeneous multimodal data remains a signif...
Ming-Hao Guo, Qing-Yue Jiao, Xiu-Jin Liu et al.· 0 citations
The SciExam for ENSO can evaluate agent research where no answer is known, and the results suggest that agents can already build competitive models whose structures bear on questions that scientists still debate.
Yin-Lin Zhang, Lang-Chen Liu, Dong-Bin Xiu et al.· 0 citations
Robot foundation models provide strong visuomotor control, yet their performance can degrade when object positions or task instructions change. Further improvements often require post-training on substantial robot data, which can be costly to collect through methods such as teleoperation. Agentic harnesses can adapt ar...
Python Song, Zhi-Xuan Liang, Kelsey Fu et al.· 9 citations· ⚡1
LLM-guided evolutionary methods, such as AlphaEvolve, have emerged as powerful approaches for challenging computational optimization problems, such as circle packing. However, prior work typically optimizes performance gain over a fixed number of iterations. We argue that practical optimization should maximize gain per...
This work introduces HarnessEval-W, an agentified evaluation pipeline that brings the harness paradigm from the LLM ecosystem to world model benchmarking, and applies HarnessEval-W to 18 representative world models over 330 evaluation cases.
Wei-Liang Chen, Haowen Sun, Jun Gao et al.· 3 citations
DeepJEPA is introduced, a weight-tied joint-embedding predictive world model that treats transition depth as an inner test-time scaling axis and learns when another recurrent update is worth computing for each candidate and rollout step.
Zi-Jian Jin, Yun-Bei Zhang, Yuan-Zhe Liu et al.· 1 citation
Results show that post-training can substantially improve financial forecasting performance, together with changes in how the model investigates the market, on this outcome-selected benchmark.
Jia-Cheng Guo, Suo-Zhi Huang, Shu-Zhen Li et al.· 0 citations
These results support a state-based view of robot memory: effective memory for control is not simply retained visual history, but compact task-relevant state derived from the interaction history.
Yu-You Zhang, Yun-Bei Zhang, Miao Li et al.· arXiv.org· 1 citation
Extensive experiments demonstrate that AgentsKG outperforms state-of-the-art training-free baselines in both extraction accuracy and structural quality, offering a robust approach to open-domain knowledge graph construction without additional training.
Shi-Long Liu, Yongqiang Liu, Jiye Liu et al.· Proceedings of the 32nd ACM...· 0 citations
This work designs a contrastive study that combines controlled quantitative experiments with paired trajectory analysis and consolidates observations into a taxonomy of three high-level categories and twelve skill-use modes, showing that skills work when noisy trajectories become procedural anchors that stabilize execu...
Zhi-Yuan Jiang, Fan Huang, Hanwen Xing et al.· 4 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.