Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2607.28225v2 Announce Type: replace Abstract: Agentic vision-language models (VLMs), which interleave textual reasoning with explicit tool calls such as cropping and code-based image manipulati...
The paper introduces Traverse, an autonomous web‑search agent that manages its search process through three states—Rubric, Answer, and Verify—while using a Seal Memory tool for active context management. Reinforcement learning is employed to train the agent, but a training instability called Seal Collapse is mitigated by training only the final segment after context management. The resulting 35B model achieves state‑of‑the‑art performance on BrowseComp and related benchmarks, outperforming comparable open‑source systems.
ReMem is a new recommendation agent framework that rethinks perception and memory for long-context recommendation tasks. It replaces raw HTML parsing with OCR-based multimodal perception from screenshots, extracting structured information in a platform-agnostic way. The framework also introduces a chunk-wise sequential memory update strategy and a multi-memory GRPO variant to efficiently model evolving user preferences over arbitrarily long interaction histories, achieving a 5.16% average improvement over state-of-the-art baselines on three recommendation agent tasks.
The paper introduces a framework for evaluating large language model agents by attempting to end‑to‑end reproduce published astronomy studies, separating execution from verification and distinguishing computational failures from methodological ambiguities. Applying this to fourteen papers—one from The Astrophysical Journal and thirteen from Nature—revealed that eleven contained ambiguities that prevented a uniquely specified reproduction path. In a controlled case study, twelve different analysis paths produced distance estimates ranging from 2.16 to 3.53 kpc, with only one matching the published value of ~2.70 kpc, demonstrating that matching outcomes does not guarantee that the agent has reconstructed the underlying reasoning. whyItMatters":"The study shows that end‑to‑end reproduction can expose gaps in implicit scientific knowledge within AI systems, highlighting the need for better integration of causal relevance in LLM agents."
The paper introduces Embodied Semantic Communication (ESC), a new paradigm that redefines information transmission for autonomous agents by embedding multimodal perceptual states, hardware capabilities, and collaborative intents into unified, action‑oriented semantic representations. ESC enables heterogeneous agents to parse, align, and ground shared information directly into local motor control, addressing the limitations of traditional communication approaches that focus solely on bit delivery or single‑task optimization. The tutorial outlines ESC’s conceptual boundaries, system characteristics, and technical pathways, mapping relevant mathematical tools such as semantic information theory, world models, and multi‑agent decision theory, and concludes with a roadmap of open challenges like semantic reliability, dynamic interaction, and bandwidth‑adaptive transmission.
The paper introduces Solver Agent, an AI framework that uses large language models to perform calculations and proofs in mathematics and theoretical physics, tracking the solution process via a persistent ledger. It applies this framework to study global F‑theory uplifts of Type IIB orientifolds and S‑folds, establishing conditions for Weierstrass models over projective threefolds with terminal ζ_k quotient singularities to yield Ε-factorial elliptically fibered Calabi‑Yau fourfolds. The authors derive fixed‑point contributions to Hodge data and Euler characteristics, demonstrate how these corrections determine localized D3‑brane charges for tadpole cancellation, and illustrate the results with toric hypersurface constructions and methods for four‑form flux analysis in Δ=1 compactifications.
AerialDojo-200K is a large-scale benchmark suite for open-world aerial object-goal search, featuring 42 simulation scenes across four families and 21 types, including urban, natural, infrastructure, and disaster environments. The dataset contains 205,732 task instances—over 100K semantic-goal and over 100K image-goal tasks—each with a collision-free reference trajectory and multi-view video recordings. A unified evaluation framework splits scenes into 21 in-distribution and 21 out-of-distribution sets, and preliminary tests on multimodal large language models show significant room for improvement in general-purpose aerial agents.
The paper introduces BSC‑R, a deterministic effect‑boundary mechanism that ties a single‑use commit authorization to the specific action and the semantic state that justified it, aiming to close the proposal‑to‑commit gap in tool‑using language‑model agents. Experiments on 2,847 AgentDojo episodes and 10,302 frozen proposals show that BSC‑R preserves the agent’s original behavior while rejecting unauthorized changes, and further tests on a boundary‑drift experiment and the CONTINUITY suite demonstrate high success rates in valid contexts and robust handling of replay and ambiguous cases. However, broader testing reveals that BSC‑R still allows a 25% invalid‑effect commit rate in a larger attack set, indicating that it provides scoped, not universal, safety.
arXiv:2604.21965v2 Announce Type: replace Abstract: Recent work has used LLM agents to reproduce empirical social science results with access to both the data and code. We broaden this scope by askin...
arXiv:2605.29522v2 Announce Type: replace Abstract: As scientific literature grows rapidly and research increasingly involves AI agents, automated survey generation has become a key capability for bo...
arXiv:2609.37635v1 Announce Type: new Abstract: LLMs have been studied in recent linguistics as potential models of humans' linguistic abilities. Here we discuss an entirely different use of AI, name...
arXiv:2605.14563v3 Announce Type: replace-cross Abstract: Automated code documentation is essential for modern software development, providing the contextual grounding that both human developers and...
arXiv:2609.35955v1 Announce Type: new Abstract: Understanding human-entity interactions requires recovering each person-action event's participants, roles, and shared identities. This structure can s...
arXiv:2609.36380v1 Announce Type: new Abstract: A 3D scene reconstructed from a single image is most useful when represented not as a rendering or a fixed 3D output, but as an explicit scene program...
arXiv:2602.09839v2 Announce Type: replace Abstract: Existing multimodal retrieval benchmarks largely emphasize semantic matching on daily-life images and offer limited diagnostics of professional kno...
arXiv:2609.37648v1 Announce Type: new Abstract: Preoperative liver-tumor assessment requires segmentation, physical-space measurement, visual evidence, and resection planning from the same three-dime...
arXiv:2609.36392v1 Announce Type: new Abstract: In diseases where clinical guidelines are incomplete, contested, or mutually contradictory, knowledge completeness and dynamic conflict-aware synthesis...
arXiv:2609.36887v1 Announce Type: new Abstract: Recent efforts to scale tool-use post-training have largely centered on the synthesis of executable environments, which constitute only one component o...
arXiv:2609.36923v1 Announce Type: new Abstract: Existing reactive Graphical User Interface (GUI) agents often fail in long-horizon, dynamic scenarios, where unexpected disturbances trigger attention-...
arXiv:2609.37588v1 Announce Type: new Abstract: Users of language-based assistive agents often make ambiguous requests. In response, an assistant can either directly act on its interpretation of the...