TRACE is a lightweight learned selector that ranks completed search trajectories by aggregating cross‑rollout evidence, preserving individual query and evidence occurrences while propagating information across shared content or document identity. Trained with answer‑level supervision over frozen text embeddings, TRACE selects an existing answer without additional search or autoregressive aggregation, and a single selector generalizes across rollout policies and agent backbones. Across six WebQA policies, six long‑horizon dataset‑backbone combinations, and multiple WebQA benchmarks, TRACE outperforms majority voting and generative aggregators, achieving higher accuracy and at least tenfold higher processing throughput.
By Qisheng Zhou, Zhen Xiong, Qiaoyu Tan
The paper introduces Richard, a prototype for voice‑first mobile interaction that separates voice sessions, task execution, and result delivery while linking them through persistent request records. It offers visual feedback via conversation and task views, and its backend handles immediate responses, dedicated services, and agent tasks. Evaluation on Android demonstrates controlled lifecycle verification and real‑world programming request execution, highlighting task continuity, user control, and service integration for intermittent user participation.
By Xinyang Chen
Mid‑Harness proposes a test‑time compute strategy that samples and verifies candidate actions before execution, keeping the underlying generator and harness unchanged. Experiments show that with a strong verifier, sampling more actions significantly boosts success rates—e.g., a GPT‑5.6 verifier raises Pass@1 from 50.00 % to 68.03 % on TerminalBench‑Lite using eight samples. The approach also improves performance across various models, benchmarks, and harnesses, demonstrating that action scaling is a promising target for enhancing terminal agent reliability.
By Minki Kang, Ryo Hachiuma, Shaokun Zhang, Subhashree Radhakrishnan, Yonggan Fu, Jindong Jiang, Mingjie Liu, Ehsan Hosseini-Asl, Yi Dong, Yu-Chiang Frank Wang, Byung-Kwan Lee
PhantomEnvironments is a framework that trains large language model agents in synthetic, rule‑generated fictional worlds. By creating multi‑turn reinforcement learning environments where agents search templated articles to answer multi‑hop questions, the approach eliminates the need for costly human data or hallucinated LLM‑generated settings. Agents trained in these zero‑cost, purely rule‑based worlds transfer effectively to real‑world multi‑hop search benchmarks, often surpassing models trained on real data, and demonstrate scalable search behavior that grows linearly with question difficulty.
By Anmol Kabra, Swathi Saravana Selvam, Albert Gong, Chao Wan, Christian Belardi, Dongyoung Go, Katie Z. Luo, Kilian Q. Weinberger
arXiv:2609.40306v1 Announce Type: cross
Abstract: Pretrained robot policies provide useful action priors, but long-horizon manipulation still requires coordination between semantic reasoning and phys...
By Haoyuan Deng, Jiebin Liu, Tengxiao Zhang, Langning Yan, Hongye Cao, Ziwei Wang
arXiv:2609.35561v2 Announce Type: replace
Abstract: Recursive self-improvement (RSI) seeks to enable AI systems to participate in improving their own capabilities. A concrete pathway is autonomous mo...
By Yaxin Du, Xiyuan Yang, Zhifan Zhou, Yujie Ge, Cheng Wang, Jiajun Wang, Sijie Chen, Zehui Liu, Yuxin Zhang, Weicheng Gu, Julian Zhang, Zixing Lei, Siheng Chen
arXiv:2608.24764v2 Announce Type: replace
Abstract: As language-model agents become more capable of iterative search, corpus access is shifting from retrieval toward interaction. Agents can explore t...
By Hongyu Guo, Zhiyu Zheng, Minghao Hu, Shuai Lei, Zhunchen Luo, Chao Ma, Yunbo Cao, Zhao Cao
arXiv:2609.33665v2 Announce Type: replace
Abstract: Automatically generated environments provide a scalable source of interaction data for training general agents. However, existing approaches mainly...
By Xiao-Wen Yang, Weiyi Xu, Wen Da, Hang Xu, Canwei Li, Hong-Jie You, Pusen Dong, Yucheng Zeng, Zhaokai Luo, Yu-Feng Li, Yao Hu, Mu Chuan
arXiv:2609.34211v2 Announce Type: replace
Abstract: In financial fraud detection, rich semantic context can provide important evidence for transaction behavior modeling and fraud reasoning. However,...
By Linbo Shao, Huilin He, Yating Lou, Dawei Cheng
arXiv:2602.14049v2 Announce Type: replace-cross
Abstract: Spatio-temporal traffic forecasting is a core component of intelligent transportation systems, supporting various downstream tasks such as si...
By Yue Wang, Areg Karapetyan, Djellel Difallah, Samer Madanat
arXiv:2605.29307v2 Announce Type: replace-cross
Abstract: Large Language Model (LLM) search agents have shown strong promise on knowledge-intensive tasks through iterative reasoning and retrieval. Mo...
By Alireza Salemi, Chang Zeng, Atharva Nijasure, Jui-Hui Chung, Razieh Rahimi, Fernando Diaz, Hamed Zamani
arXiv:2609.34422v2 Announce Type: replace-cross
Abstract: Language-model agents increasingly tackle long-horizon tasks whose interaction histories exceed the model's active context. Recent work has b...
By Lirui Luo, Kelong Mao, Heming Xia, Rongqing Li, Xinwei Yang, Luyu Chen, Kieran Wong, Yudong Guo, Xinrui Wang, Jiayin Zhu, Simiu Gu, Sulong Xu, Cong Fang
arXiv:2609.35596v2 Announce Type: replace-cross
Abstract: Self-evolving LLM agents have gained prominence for their ability to improve after deployment by modifying their harness, including their con...
By Saswat Das, Parvati Viswanathan, Daniel Donnelly, Chang Huang, Sahar Abdelnabi, Ferdinando Fioretto
arXiv:2609.38334v1 Announce Type: new
Abstract: Large language models (LLMs) are increasingly deployed as agents for multi-step decision-making, yet transfer poorly to unseen environments. World-mode...
By Yuhan Guo, Jinming Liu, Liang Xu, Ziqiang Li, Jianguo Huang, Zhicheng Wang, Hu Zhu, Qiuyu Chen, Yuntao Wei, Xin Jin, Wenjun Zeng
arXiv:2609.39238v1 Announce Type: new
Abstract: An agent that moves must recognise a place from a viewpoint it has never seen. We introduce 4MT-VLM, a dataset of procedurally generated landscapes, ea...
By Markus Frey
arXiv:2609.40118v1 Announce Type: new
Abstract: As LLM capabilities advance, agents are tackling increasingly complex tasks over longer horizons. Their growing interaction histories make memory compa...
By Jingbo Yang, Kwei-Herng Lai, Xiaowen Wang, Zhaoxuan Tan, Pei Zhou, Mengting Wan, Yaar Harari, Evgeniy Gabrilovich, Shiyu Chang
arXiv:2609.38291v1 Announce Type: cross
Abstract: Large language model (LLM) agents are vulnerable to safety risks such as injected malicious instructions or misleading information, motivating runtim...
By Zhuo Liu, Moxin Li, Zhixin Ma, Wentao Shi, Wenjie Wang, Fuli Feng
arXiv:2609.38641v1 Announce Type: new
Abstract: Vision-Language-Action (VLA) foundation models have recently emerged as one of the prevailing solutions for autonomous driving, as they can utilize kno...
By Kai Yan, Xiangyu Chen, Yulong Cao, Alex Naumann, Peter Karkus, Yan Wang, Jef Packer, Alex Schwing, Yuxiong Wang, Boris Ivanovic, Wenjie Luo, Marco Pavone
arXiv:2609.39066v1 Announce Type: new
Abstract: Conventional image forgery detection methods produce binary scores or pixel-level masks without interpretable evidence, while recent multimodal large l...
By Zhiya Tan, Jing Huang, Changtao Miao, Lin Tan, Xin Zhang, Weiwei Feng, Jianshu Li, Joey Tianyi Zhou
arXiv:2609.39135v1 Announce Type: new
Abstract: Physical reasoning from video requires inferring latent physical properties and dynamics beyond direct observation. Direct VLM inference remains unreli...
By Shenxiang Zeng, Chen Yang, Peiyao Chen, Guohui Zhang, Jiansheng Fan, Chen Wang