Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2610.35215v1 Announce Type: cross Abstract: Web agents reuse skills whose stored code, selected version, and loaded implementation can diverge across tasks and updates. SkillLifeBench links the...
MiRL is a new reinforcement learning approach that targets specific misbehaviors of terminal agents—models that execute long‑horizon tasks in natural language by interacting with a command shell. The method first profiles a policy to identify recurring wrong steps, then trains the policy by starting rollouts at those misbehaviors and rewarding only successful, misbehavior‑free trajectories. On the Qwen3.5‑4B model, MiRL reduces repeated misbehaviors by 43–57% on unseen prefixes and outperforms or matches baseline agents on Terminal‑Bench benchmarks while using only 35% of the rollouts.
UMAS is a parameter‑free, cost‑neutral framework for system‑level uncertainty quantification in multi‑agent large language model systems. It estimates the credibility of inter‑agent influence using each generation’s intrinsic confidence, modulates uncertainty updates at each node, and aggregates these into a system‑level estimate. Evaluations on Debate and DyLAN show UMAS outperforms state‑of‑the‑art baselines by an average of 10.54 AUROC points and improves hallucination detection and answer selection, boosting MAS accuracy by up to 12.6 points on specific tasks.
arXiv:2610.33465v1 Announce Type: new Abstract: Equation discovery solvers often use different data interfaces, equation representations and evaluation criteria, making their results difficult to com...
arXiv:2610.33845v1 Announce Type: new Abstract: Can LLM agents carry a hard real-world problem from raw data to a system that holds its own against people? We study this in Hearthstone Battlegrounds,...
arXiv:2610.33958v1 Announce Type: cross Abstract: Coding agents are given embedding search and code-graph tools on the premise that a repository's structure is something the model lacks and the tool...
The paper introduces SR‑BEVS, a sparse recovery learning technique that enhances both clean accuracy and robustness to real‑world corruptions for camera‑based bird’s‑eye view (BEV) 3D object detection models. By pruning weights based on magnitude, generating diverse sparse models, retraining them with varied learning rates, and averaging the recovered models into a single dense model, the method achieves up to 33.8% improvement in corruption robustness and a 1.8% gain in clean accuracy over the Fast‑BEV baseline on the nuScenes dataset. The approach adds no inference overhead and preserves a connected low‑loss basin, suggesting applicability to other BEV models.
arXiv:2610.35077v1 Announce Type: cross Abstract: Understanding and operating with scientific charts is a standard approach in data analysis, and while humans are good at interpreting such charts, op...
The paper introduces a sample‑efficient asynchronous Q‑learning algorithm for robust reinforcement learning in infinite‑horizon, discounted robust MDPs with total‑variation uncertainty. It proves that, given a single Markovian trajectory, the algorithm achieves an entrywise ε‑approximation of the optimal Q‑function with a sample complexity bounded by a nearly minimax‑optimal expression involving the discount factor, uncertainty level, mixing time, and occupancy probability. This result improves significantly over prior bounds for robust RL.
arXiv:2601.10418v2 Announce Type: replace-cross Abstract: We study tabular finite-horizon reinforcement learning problems with multiple steps of lookahead information. Before acting, the learner obse...
arXiv:2605.06285v2 Announce Type: replace Abstract: Single-step retrieval-augmented generation (RAG) provides an efficient way to incorporate external information for simple question answering tasks...
arXiv:2605.12718v2 Announce Type: replace Abstract: Multi-agent debate has emerged as a promising approach for improving LLM reasoning on ground-truth tasks, yet current methodologies face certain st...
arXiv:2610.34599v1 Announce Type: new Abstract: Despite advances in automated liver lesion segmentation, a gap remains between image-derived predictions and clinically interpretable radiology reports...
As large language model agents increasingly compile natural-language requirements into repository-level code, requirement-to-test generation grows in importance to provide validation constraints (or h...
Multilingual automatic speech recognition (ASR) has achieved rapid progress with large-scale pretrained models and multilingual speech corpora. Previous studies have proved the pivotal role of data sa...
Recently, LLM-based autonomous agents have shown strong capabilities in iteratively generating, evaluating, and refining executable solutions. In robotic manipulation, Code-as-Policy lets these agents...
Web fashion images support applications such as visual product search and consumer-to-shop matching, yet their visual heterogeneity makes reliable garment segmentation challenging. Despite advances in...
Claims about the cognitive capabilities of large language models are typically tested by translating behavioral paradigms into text prompts, bypassing the visual interfaces and time pressure through w...
Sequential trading agents produce decisions, orders, execution receipts, account states, and reports that need not agree, even when the final portfolio value is correctly computed. We present FIDES-Li...
LLM agents interact with Web services to perform tasks on users' behalf. Errors during these interactions can disrupt execution and prevent task completion, motivating external intervention. However,...