Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2609.37105v1 Announce Type: cross Abstract: Language model agents can be improved by updating their model weights or refining the harness that guides task execution. These components are couple...
The paper introduces STRAT, an auxiliary task for deep reinforcement learning that trains agents to generate a short textual trace describing their state. This trace, produced online by environment rules, includes landmark, route, and survey information such as position, inventory, goals, and progress. Adding a single auxiliary head to a standard policy, STRAT improves performance on 60 sparse-reward XLand-MiniGrid tasks, compacting state representations, preventing rank collapse, and offering a readable account of agent beliefs at no extra cost.
arXiv:2609.32490v2 Announce Type: replace Abstract: LLM-based multi-agent systems (MASs) have shown strong potential for solving complex tasks, but most assume that task requirements are sufficiently...
CAR‑VLA is a Vision‑Language‑Action model for autonomous driving that jointly considers scene complexity and dynamic risk to determine reasoning depth, urgency, and focus. It maps four complexity‑risk categories to three reasoning modes—Fast Intuition, Slow Thinking, and Reflex Response—each tailored to different driving scenarios. The model is trained via progressive supervised learning and reinforcement learning, achieving competitive performance on NAVSIM and Navhard benchmarks and demonstrating risk‑aware reasoning in high‑risk scenarios.
arXiv:2609.33772v2 Announce Type: replace Abstract: Executable environments are critical for post-training agents on tasks that require tool use and multi-step interaction, but constructing executabl...
Beacon is a new agentic visual reasoning model that improves multimodal large language models (MLLMs) by better deciding when to use tools and how to use them. It introduces two key concepts—Mode Adaptiveness, which ensures tools are invoked only when necessary, and Tool Effect, which measures the net benefit of tool use— and trains the model with supervised fine‑tuning and reinforcement learning that rewards necessity-aware decisions and expands capability through expert hints. Across 13 benchmarks, Beacon outperforms other open‑source models, achieving the highest average score and the largest net tool‑gain on diagnostic tests.
PhysWAM is a unified world-action model for autonomous driving that jointly denoises multiview video, metric depth, and ego motion using a flow‑matching transformer. It introduces Coupled Point Projection (CPP), a geometric constraint that aligns generated depth points with LiDAR data after applying the predicted SE(3) ego motion, thereby enforcing physical consistency. At inference, trajectory selection uses a simple label‑free consensus rule, and the model demonstrates strong planning performance, zero‑shot transfer to unseen environments, and accurate, temporally coherent depth and video predictions.
StateTape introduces a new framework for long‑horizon coding agents that rewrites the agent’s context as the code repository changes, rather than letting the context grow with every observation. It models the repository as a symbol‑level code graph, using a tape to mark symbols altered by each write and a manager model to resolve stale records. The authors provide theoretical analysis, a new benchmark called TraceBench, and empirical results showing higher resolve rates across six agents and three edit‑heavy benchmarks with minimal computational overhead.
The paper introduces a Lagrangian framework for managing a regenerative commons, framing the problem as a constrained Markov game with a specified depletion budget. It constructs policy sequences from unconstrained solutions, extending time‑average concepts to reset episodes with discounted rewards and terminal costs, and provides theoretical guarantees such as reward‑independent feasibility, cooperative feasibility, and approximate optimality. Experiments on a fishery model using constrained IPPO and MAPPO illustrate how depletion budgets influence stock retention, harvest rewards, and price adaptation.
OmniVCBench is a figure‑centric, source‑traceable benchmark designed to evaluate the interpretation component of Artificial Intelligence Virtual Cells (AIVCs). It comprises 6,077 curated question–answer pairs drawn from scientific figures and experimental contexts, organized into three scientific reasoning tasks that mirror the AIVC Predict–Explain–Discover agenda. The benchmark also introduces AIVC‑Judge, a task‑conditioned MLLM‑as‑a‑judge framework with reference‑aware rubrics, and a Model‑Derived Hard‑Negative Mining strategy to generate multiple‑choice distractors for efficient evaluation.
The paper introduces ProgressCompass, a framework that enhances Embodied Progress Reward Models (PRMs) by providing the necessary contextual information for accurate progress estimation in long manipulation tasks. It presents ContextProgress-Bench, a benchmark with 24 tasks that tests PRMs under three context-dependent scenarios—State Recall, Sequence Tracking, and Recurrence Disambiguation—showing that even history-aware PRMs struggle without proper context. By integrating a context-aware loop that leverages general-purpose vision‑language models, ProgressCompass reduces PRM progress error by up to 82% and improves rank agreement by 76%.
VISTA is a method for active multimodal agents that internalizes collective visual experience via on‑policy distillation. It turns observations from multiple rollouts of the same input into shared supervision, using Collective Visual Experience Distillation (CVED) to organize observations with context and Heterogeneity‑Aware Policy Improvement (HAPI) to reinforce successful trajectories and guide learning from unsuccessful ones. The approach lets an experience‑conditioned teacher evaluate a student’s partial responses, enabling discoveries from one trajectory to inform others without altering the student’s original history, and achieves superior performance on fine‑grained perception and general reasoning tasks compared to comparable agents.
LongCat-DeepResearch is a deep research system that merges an enhanced LongCat model with a multi‑agent workflow to produce comprehensive, evidence‑grounded reports. The workflow separates global planning from detailed investigation, using planning agents to create a ResearchSpec and research agents to draft sections in parallel, followed by targeted local revisions guided by global review. The system achieves strong benchmark scores, including 55.25 on DeepResearchBench and 79.83 on ResearchRubrics, and shows benefits from combining planning perspectives and additional editing for readability.
arXiv:2609.34879v2 Announce Type: replace Abstract: Tool agents use large language models to act through external tools, yet successfully executed calls can still leave user requests unfulfilled. Too...
The paper introduces Dually Regularized AIL, a model‑free algorithm for adversarial imitation learning that jointly applies KL policy regularization and a quadratic reward penalty based on expert and learner occupancies. It proves fast convergence rates, achieving a ×O(1/K+1/N) bound on the regularized imitation gap in finite‑horizon MDPs with general function approximation, and establishes the first algorithm to attain ×O(1/ε) sample complexity in both expert demonstrations and online interactions for this regularized objective.
arXiv:2609.37834v1 Announce Type: new Abstract: Harness optimization provides a practical setting for recursive self-improvement (RSI), where agent-generated modifications inform subsequent changes t...
arXiv:2609.35808v1 Announce Type: cross Abstract: Experience reuse can reduce repeated exploration in embodied agents, but a trajectory that succeeded previously may be unsuitable for the current exe...
arXiv:2609. 37968v1 Announce Type: new Abstract: Advances in the coding capabilities of LLM agents allow them to inspect and modify their own instructions, tools, and execution procedures.
arXiv:2609.35953v1 Announce Type: new Abstract: Young people increasingly turn to General-Purpose Conversational Agents (GPCAs), such as ChatGPT, in moments of distress. We examine young adults' (age...
arXiv:2609.35750v2 Announce Type: replace-cross Abstract: Scaling the horizon of agentic LLMs is bottlenecked by the need to fit ever longer context traces in GPU memory. Context compaction has been...