The paper investigates the effectiveness of tool graph memory—a component that records past tool transitions to guide future tool selection—in large language model agents performing multi‑turn tasks. Across nine models and two benchmarks, the authors find that tool graph memory rarely yields significant performance gains, often incurs more than twice the number of LLM calls, and its guidance is frequently incorrect. They observe that random or no guidance can achieve similar improvements, suggesting the benefits arise from additional computation rather than the memory itself, and that storing experiences as textual insights outperforms the graph approach with minimal extra calls.
arXiv:2607. 11126v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on external tools served by shared providers and accessed by heterogeneous downstream agents.
The paper introduces FRESH, a Failure-aware Retrieval framework that uses Experience-Structured Heterogeneous graphs to transform past successes and failures into structured external memory for tool‑using agents. By explicitly modeling dependencies among tasks, actions, errors, repairs, and execution conditions, FRESH enables frozen language models to reuse reliable strategies, avoid recurring failures, and make safer decisions in stateful tool interactions. Experiments on τ‑Bench and AppWorld with multiple open‑source models demonstrate that FRESH consistently improves task success and tool‑use reliability compared to no‑memory agents and other memory‑based baselines.
arXiv:2608. 11248v1 Announce Type: new Abstract: Long-term memory is essential for language agents operating across extended interactions and evolving tasks.
TrawMem redefines agent memory systems as Task‑Oriented Role‑Adaptive Workspaces, selecting and organizing memories by their roles in task solving rather than mere relevance. It structures interaction histories into local threads and jointly selects complementary memories to build task‑specific workspaces. Experiments on LoCoMo and MemGallery show consistent macro‑F1 gains of 2.23–3.14 points and improved LLM‑Judge scores with fewer context tokens.
arXiv:2605. 18421v2 Announce Type: replace-cross Abstract: Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution.
arXiv:2604.23069v2 Announce Type: replace Abstract: Large language model (LLM) agents often struggle in long-context interactions. As the history grows, sliding windows and prompt compression may dro...
UniToolCall introduces a unified framework for tool-use in large language model agents, standardizing toolset construction, dataset generation, and evaluation. The framework aggregates over 22,000 tools and creates a hybrid training corpus of more than 390,000 instances by combining ten public datasets with synthetically generated, structurally controlled trajectories. It models diverse interaction patterns—single‑hop vs. multi‑hop, single‑turn vs. multi‑turn, serial vs. parallel execution—and adds an Anchor Linkage mechanism to enforce cross‑turn dependencies, while converting seven public benchmarks into a common Query–Action–Observation–Answer format for fine‑grained evaluation.
arXiv:2607. 24772v1 Announce Type: new Abstract: Geoscience research requires complex analysis and domain expertise, with remote sensing (RS) observations as a key foundation.
The paper surveys how graphs are increasingly used in large language model systems to support reasoning, knowledge grounding, retrieval, memory, execution, and multi‑agent coordination. It introduces an operation‑level taxonomy that distinguishes the function of each graph operation, the component that computes it, and how its output is subsequently used. The authors compare graph observations with external computations, analyze memory updates, and examine execution dependencies, then propose an evaluation framework that organizes benchmarks, diagnostics, and system costs, concluding with open challenges in adaptive computation, memory maintenance, and dependency‑aware recovery.
The paper introduces Tool Primitives, a design that replaces rigid API schemas with natural language interfaces for tool calling, enabling seamless inter-tool communication. It builds ToolFace, a repository of over 25,000 functions that LLMs can dynamically retrieve, and HEART, a harness engineering framework that orchestrates tool use with planning, routing, and verification. Experiments show HEART outperforms fine‑tuned models and leading commercial LLMs while cutting API costs by up to 85%.
arXiv:2606. 05646v1 Announce Type: cross Abstract: Large language models (LLMs) have enabled powerful software engineering (SE) agents capable of navigating complex codebases and resolving real-world issues.
arXiv:2610.02330v1 Announce Type: new Abstract: Large language models (LLMs) rely on long-horizon tool invocation sequences for complex tasks, where each invocation can alter the task state and condi...