Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
The paper proposes a method that mimics human cognition to train reinforcement learning agents to generate explainable strategies and policies as executable procedures derived from sequences of gameplay actions. It demonstrates automatic learning of such programs for chess and a grid‑based environment, showing that the resulting strategies produce effective actions and can be learned from gameplay data.
The paper presents a symbolic sub‑policy model for chess that incorporates domain knowledge to improve interpretability. By adapting patterns learned through inductive logic programming (PAL), the authors evaluate the model using a divergence metric against a random baseline and show that it can suggest moves comparable to a human beginner. They also propose a computational evaluation scheme that augments an existing engine with their model.
ST-Bench is a new benchmark that tests whether multi‑agent systems (MAS) outperform single agents on complex scientific data analysis tasks. It includes 100 Earth‑science data‑science tasks expanded into 2,067 queries, validated by domain experts. Evaluations show that most MAS configurations beat the cheapest single‑agent baseline, with the best reaching nearly three times its score, though at higher inference cost.
Attacca is a new approach for training visual goal‑conditioned policies that can handle continuous long‑horizon task execution in embodied agents. It decouples goal images from the execution environment by sampling class‑compatible masked goals from other worlds, enabling the policy to ground targets in the current view via a target‑mask prediction head. The method also introduces behavioral‑phase conditioning to distinguish Search, Approach, and Interact stages, and achieves significant performance gains on Minecraft tasks, outperforming baselines by up to 7× on long‑horizon scenarios.
OOPMAS introduces a training‑free framework that generates both the agent set and the coordination workflow at the granularity of individual queries. Agents are defined as object‑oriented class definitions with dedicated roles, tools, and persistent state, while workflows are expressed as executable main functions over these agent objects. A dynamic skill library accumulates structured lessons from execution feedback across optimization rounds, enabling in‑context improvement without any gradient updates or fine‑tuning, and achieves 89.6% accuracy on a mixed‑task benchmark, outperforming the strongest baseline by 18.1 percentage points.
The paper introduces Agentic Semantic Sensing (Agentic SemS), a closed‑loop framework for AI‑enabled radio access networks that dynamically adjusts sensing configurations within a communication‑feasible profile set. A profile‑conditioned causal Transformer updates semantic beliefs from streaming data, while a semantic utility network guides the selection of the next sensing profile and determines when to exit early, balancing task benefit against sensing cost. Experiments on Widar3.0 demonstrate that Agentic SemS reduces cumulative sensing cost by 25.33% compared to a full‑sequence baseline while maintaining 85.79% Macro‑F1, and that semantic early exit yields an additional 12.35% cost savings with minimal performance loss.
The paper introduces DHCG, a framework that dynamically constructs hierarchical collaboration graphs for large language model–based multi‑agent systems. DHCG coordinates Planner, Worker, and Generator modules to adaptively determine the composition and scale of agents during execution, guided by feedback and action‑aware preference optimization. Experiments on code generation, mathematical reasoning, and domain‑specific tasks show DHCG surpasses static and dynamic baselines, improving performance by 2.77–8.02 points and achieving a 13.06‑point gain over single‑agent baselines.
ShanLiangRen is a nutrition agent designed to generate personalized daily meal plans that satisfy both user constraints and multidimensional nutritional goals. It transforms dietary specifications, nutrient data, user attributes, and natural language requirements into a constrained planning instance, then uses a retrieval‑augmented generation approach to narrow the candidate set from a large ingredient and recipe space. Finally, it refines plans via Pareto‑guided iterative revisions with an LLM, producing fully quantified meal plans with explicit ingredients, portion sizes, and compliance reports.
The paper introduces Confidence Reasoning Graphs (CRGs), an inference-time framework that estimates the probability an LLM agent has successfully completed its task using a single trajectory without requiring privileged model access or training data. CRGs decompose the agent’s overall claim of success into contextualized sub-claims, estimate confidence for each terminal claim based on trajectory evidence, and aggregate these into an overall confidence estimate. Experiments across multiple benchmarks, models, and agent frameworks show that CRGs produce better-calibrated confidence and more effective risk-aware decision making than existing verbalized, sampling-based, and white-box surrogate methods, while also providing transparent, auditable evidence for each estimate.
DAEDALUS is a method that builds reusable memory for large‑language‑model agents by having an explorer agent generate self‑created tasks and a solver agent attempt them. When the solver fails, a heuristic is extracted and only accepted after repeated successful use, then added to a memory bank for future test‑time use. Experiments on AppWorld, τ²‑bench, and AutomationBench show that DAEDALUS raises mean success rates by up to 15.9 points and pass⁵ by up to 2.2× compared to a no‑memory baseline, while also providing a cost‑effective alternative to training‑task or oracle‑verifier approaches.
arXiv:2610.08102v1 Announce Type: new Abstract: Conversational MLLM agents are increasingly expected to assist in professional workflows, from AI research and engineering design to product management...
arXiv:2610.08106v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) advance rapidly, while conventional benchmark development lags behind, delaying investigation of newly observe...
arXiv:2610.08138v1 Announce Type: new Abstract: Legal intelligence aims to support reliable decision-making across long-horizon legal processes involving evolving case states and multiple roles. Howe...
The paper introduces Predicting Intention of Partner (PIP), a method for zero‑shot coordination in partially observable settings. PIP employs a Joint‑view VAE to create a partner representation from local observations and uses Partner‑State Belief networks to infer hidden partner states from interaction history. Experiments on Burrito‑PO, Overcooked‑PO, and Melting Pot, along with human evaluation, show that PIP outperforms other methods and demonstrates effective coordination with unseen partners under occlusion.
arXiv:2610.08246v1 Announce Type: new Abstract: Frontier large language models (LLMs) can generate heuristic functions that guide search to achieve state-of-the-art performance in satisficing plannin...
arXiv:2610.08250v1 Announce Type: new Abstract: Large language models are increasingly used to simulate clients for counselor training and psychological counseling research, but reliable simulation r...
arXiv:2610.08363v1 Announce Type: new Abstract: Maritime systems operate in highly dynamic environments where unexpected equipment failures can compromise safety, reliability, and operational efficie...
arXiv:2610.08432v1 Announce Type: new Abstract: Improving embodied agents often focuses on optimizing the underlying model through training, while the surrounding agent harness that controls planning...
arXiv:2610.08586v1 Announce Type: new Abstract: Long conversational agents have become essential in our daily lives. They must remember what was said long back in order to help us efficiently complet...
arXiv:2610.08647v1 Announce Type: new Abstract: LLM-based agents solve complex multi-step tasks, but sequential execution incurs substantial latency. In principle, parallelizing work across multiple...