The paper introduces a benchmark for evaluating whether off‑the‑shelf small language models (SLMs) can reliably perform microtasks that support a large language model (LLM) planner, such as auto‑approving shell commands, writing memory, selecting tools, and ranking past turns. Using fixed prompts and confidence‑interval‑aware eligibility thresholds, the authors test several Qwen3 models (0.6/1.7/4/8 B) in FP16 with no tuning and find that none of the 16 configurations meet the eligibility criteria. Quantization to 4‑bit precision further degrades performance, with the eligibility gap tracking model size rather than precision, and the issue persists across different models (e.g., Llama‑3.x) and prompt variations.
By Jundong Hu, Shekar Ramachandran
The paper introduces a claim‑anchored execution contract that binds a tool‑using agent’s emitted claim to its exact source span, the ordered execution prefix that produced it, and the source version and access state observed. Each receipt contains deterministic anchors, source identifiers, offsets, hashes, quotes, and a domain‑separated execution commitment, allowing a verifier to reconstruct these bindings before semantic or task labels are joined. The contract defines seven independently testable properties and demonstrates high detection rates against cross‑object attacks, with strong performance on conflict‑aware support guard evaluations.
By Miaobo Hu, Shuhao Hu, Xiaobo Guo, Xin Wang, Bokun Wang, Yina Sa, Daren Zha, Jun Xiao
Agent evaluations increasingly benchmark LLMs, but rankings can be swayed by evaluation conditions such as scaffolds or tasks, making reliability claim‑dependent. A Bayesian variance‑decomposition framework applied to 22 benchmarks shows that reliability varies with the measurement goal: fixed model‑scaffold systems rank reliably, while underlying‑model rankings are less stable. Scaffold choice can alter conclusions, and adding more tasks only modestly improves reliability when scaffold coverage is limited; however, pooling diverse benchmarks can substantially raise cross‑task ranking reliability and reduce cost.
By Michael Hardy, Ruhana Azam, Anka Reuel, Mykel Kochenderfer, Sanmi Koyejo
The paper investigates how reinforcement learning post‑training of large language models (LLMs) tends to sharpen existing behaviors, improving single‑shot accuracy but reducing solution coverage. It shows that pre‑trained LLMs, when paired with a lightweight inference harness, can outperform post‑trained models in coverage for agentic tasks that require multi‑turn tool use. The authors introduce the Sharpening Tax metric to quantify this trade‑off, analyze its prevalence across 14 model pairs and 42 benchmark cases, and propose a Bayesian sampler, PTGS, that mitigates the tax by adapting sampling temperature to prompt difficulty.
By Changdae Oh, Qi Zeng, Qi Qi, Andrey Zhmoginov, Deren Lei, Yun He, Hoang Phan, Hangoo Kang, Azalia Mirhoseini, Sharon Li
arXiv:2610.01569v1 Announce Type: cross
Abstract: Unmanned aerial vehicle (UAV) swarms increasingly rely on language-model agents to provide adaptive mission-level reasoning in uncertain environments...
By Andrea Iannoli, Ivan Zyrianoff, Angelo Trotta, Lorenzo Gigli, Marco Di Felice
arXiv:2610.01746v1 Announce Type: cross
Abstract: Autonomous driving systems have become a central focus of intelligent transportation research, with End-to-End Learning and Modular Architectures off...
By Kartik B. Kapse
arXiv:2610. 01834v1 Announce Type: new Abstract: Judgment models such as \jev{} return, in a single call and without reasoning text, a probability for each described option.
By Yaodong Yang, Hongyao Tang, Yi Ma, Xingyu Fan, Weixun Wang, Jinpeng Li, Tianpei Yang
arXiv:2610.02000v1 Announce Type: new
Abstract: Adverse conditions such as rain, snow, fog, and dust remain challenging for camera-based perception in autonomous driving. We study multi-class weather...
By Hossein Maghsoumi, George Atia, Yaser P. Fallah
arXiv:2610.02150v1 Announce Type: cross
Abstract: Large language model (LLM) agents increasingly rely on persistent external sources to solve sequences of knowledge-intensive tasks. Existing methods...
By Lucheng Fu, Kejing Xia, Yiyang Wang, Yiqiao Jin, Jinjin He, Xiyuan Yang, Haoxin Liu, Ye Yu, Haibo Jin, Yijia Xiao, Wenke Lee, B. Aditya Prakash, Haohan Wang
arXiv:2606.00341v2 Announce Type: replace-cross
Abstract: As AI agents are increasingly deployed in real personal and corporate settings (email accounts, development workflows, company databases, etc...
By Jeremy Tien, Abishek Anand, Yu-Rou Tuan, Yuchen Shen, J. Zico Kolter, Aran Nayebi
arXiv:2609.39995v2 Announce Type: new
Abstract: Diffusion planners exhibit strong capabilities in generating multimodal trajectories. However, existing methods primarily rely on expert demonstrations...
By Jiaxi Ye, Chunji Lv, Guoren Wang, Changsheng Li
arXiv:2604.12102v3 Announce Type: replace
Abstract: We describe compute-grounded reasoning (CGR), a design pattern in which code computes selected sub-problems from explicit intermediate representati...
By Arun Sharma
arXiv:2605.22875v2 Announce Type: replace
Abstract: Long-horizon mathematical reasoning fails less often because a model cannot produce a valid next step than because an agent fails to maintain and e...
By Zelin Zhao, Bo Yuan, Yuchen Zhu, Jaemoo Choi, Yongxin Chen
Selection-Based Structured Reasoning (SSR) is a framework that replaces free-form reasoning with the selection of pre-specified natural‑language reasoning candidates, allowing multimodal agents to choose from a set of reusable high‑level reasoning traces. By scoring these candidates in parallel using a shared context KV cache, SSR eliminates the need for an auxiliary task head and reduces inference cost. Experiments on seven multimodal search benchmarks with 2B and 4B models show that SSR maintains competitive success rates while cutting per‑turn reasoning latency by over 90% and overall inference latency by 28–54%.
By Feiyu Gavin Zhu, Xiaoyu Zhu, Jiqi Yang, Rui Yang, Arnab Kumar Mondal, Yancheng Wang, Xinke Deng, Jean Oh, Reid Simmons, Joerg Liebelt, Xiang Kong, Zhongyu Jiang
arXiv:2609.40245v2 Announce Type: cross
Abstract: Robot navigation in dynamic, human-centered environments requires socially-compliant decisions grounded in robust scene understanding. Recent Vision-...
By Nathan Tsoi, Michael J. Munje, Tejas Oberoi, Rishab Maheshwari, Pengen Zheng, Tanush Chauhan, Peter Stone, Joydeep Biswas
The paper introduces FedCausalCompose, a causal world‑model framework designed for modular large‑language‑model agents that interact with distinct services such as order, payment, inventory, and shipment. It demonstrates that standard observational world models suffer from irreducible interventional errors when unblocked back‑door paths exist, whereas incorporating intervention‑response evidence improves interface recovery and can outperform non‑causal baselines when coverage and local mechanism errors are controlled. Experiments show that causal interfaces are most beneficial in structured tool environments with clear API signatures, while they provide little advantage in dialogue or narrative settings unless the causal information becomes directly relevant to the agent’s decision making.
By Xinyuan Song, Zekun Cai
DashVMC is a system that learns a compact, action‑conditioned world model from about two hours of recorded Geometry Dash gameplay. The model is used to train a controller via behavioural cloning and Proximal Policy Optimization entirely in frozen‑model rollouts, achieving longer survival than the initial policy on all tested levels. At deployment, the system runs a 60‑Hz capture‑to‑action loop on a consumer GPU, demonstrating real‑time control despite imperfect long‑horizon fidelity.
By Florent Tariolle, Florian Yger
arXiv:2604.01151v3 Announce Type: replace
Abstract: As LLM agents are increasingly deployed in multi-agent systems, they introduce risks of covert coordination that may evade standard forms of human...
By Aaron Rose, Carissa Cullen, Sahar Abdelnabi, Philip Torr, Brandon Gary Kaplowitz, Christian Schroeder de Witt
Dynamic resource assignment, the real-time allocation of task streams to heterogeneous processing nodes, is the backbone of modern computing infrastructure. While learning-based schedulers excel in re...
Urban environments are shaped by design choices with long-term implications for health, safety, and quality of life, yet evaluating proposed interventions remains costly, time-consuming, and often imp...