Tool Use & Agents

Agents can now learn to design and critique 3D scenes like human designers, achieving state-of-the-art quality through complementary learning.

VLM agents can achieve state-of-the-art robotic manipulation by treating failures as coding bugs, with contact precision, not reasoning, proving the primary bottleneck.

Simulating professional organizations with persistent context and delegation unlocks emergent agent capabilities, outperforming single- and multi-agent baselines on complex professional tasks.

Agentic AI inference can be accelerated by 2-6x with history-free speculative decoding that eliminates KV cache overhead and boosts acceptance rates by up to 70%.

A specialized CAD harness drastically improves LLM agent performance, cutting output tokens by up to 88% and boosting F1 scores by 13% through geometry-grounded RL.

Targeted data augmentation and joint RL/OPD training unlock significantly stronger long-horizon multimodal search capabilities for agents.

Synthesizing data environments from explicit world specifications, not just files, unlocks scalable training for data agents and reveals a fundamental computation-insight gap in frontier models.

A strong LLM can review grounded drafts from a weak model, retaining most task performance while halving latency and memory traffic.

Frontier generalist computer-use agents, previously closed-source, are now open for systematic study and community development, with the first release achieving significant performance gains.

Safety guard evaluations can be misleadingly inflated by superficial cues, with simple edits to tool names or command structure significantly altering measured performance and agent behavior.

Agent guards designed for English requests exhibit significant safety failures when faced with multilingual inputs, with smaller models and specialized guards showing the most pronounced language-dependent biases.

Downstream QA metrics hide critical memory failures: agents correctly classify memory operations less than 20% of the time, a flaw invisible to current benchmarks.

Real-world robot demonstrations can now be collected at 66 demos/hour by optimizing TAMP solution quality for behavior cloning.

Hundreds of billions of midtraining tokens on a curated software engineering corpus unlock substantial gains in agentic capabilities, outperforming standard SFT alone.

Agents can now learn reusable knowledge from experience by converting it into ontological axioms, enabling LLMs to dynamically propose and verify hypotheses for complex tasks.

Autonomous ML engineering agents can achieve frontier-model performance by learning from long experimental trajectories using outcome-guided supervision and windowed reinforcement learning.

A single adversarial token can bypass most safety filters.

Sharing LLM internal states is efficient, but only if you augment the KV cache and replace activations, not swap them.

LLM agents can be reliably steered back to task goals with a learned, dual-path intervention mechanism that generalizes across tasks and executors.

LLM agents can learn to proactively build optimized, hierarchical file system workspaces that anticipate future queries, outperforming reactive retrieval by 33 points on BrowseComp-Plus.

Decentralized agent swarms can learn to self-orchestrate their collective behavior and individual capabilities simultaneously, outperforming fixed coordination strategies.

Rational synthesis for multi-agent systems with unknown dynamics and $\mathsf{PLTL}_f$ objectives is achieved by integrating solution concepts like Nash equilibrium with temporal logic satisfaction.

Humanoid robots can now grasp and manipulate bulky objects using their entire bodies, achieving 90% success in complex repositioning tasks.

An adaptive acquisition function learned online via temporal difference learning discovers optimal perturbation experiments 2x more effectively than fixed methods.

A VLM can learn to dynamically "imagine" missing visual evidence to solve complex spatiotemporal reasoning tasks, outperforming direct reasoning and fixed imagination pipelines.

Frontier models can be used sparingly for long-horizon tasks by a weak agent that learns to predict when it needs help, then keeps the strong model on a leash.

Even the best AI agents fail to deliver substantial business value in realistic customer delivery scenarios, struggling to uncover unstated constraints and achieve high impact.

Agentic RL agents can learn to efficiently manage context and subtasks across multiple sessions by estimating the marginal contribution of each session, outperforming naive advantage broadcasting.

Adaptive uncertainty gating and post-crossing correction boost multi-object tracking accuracy by +1.0 HOTA on sports datasets, outperforming existing methods at real-time speeds.

VLMs can learn to actively explore 3D worlds and acquire visual evidence for reasoning, achieving 53.2% accuracy by optimizing for final-answer correctness alone.

GPT-6-Astra achieves unprecedented embodied intelligence performance, yet practical deployment faces significant hurdles in demonstration cost and physical constraints.

Frontier LLM agents fail to recognize superior human-corrected scientific research plans, performing worse than chance even with full project context.

Coding agents fix 40%+ more bugs when they're shown whole files verbatim, not compressed snippets or similar-but-unnecessary code.

Even top LLMs achieve full scientific closure in less than a third of physics research tasks, revealing a critical gap between generating evidence and drawing robust conclusions.

Native desktop automation requires seamless GUI and code integration, a feat previously unachievable with prompt-level tool composition, but OS-Helix now unifies these into a single action space.

LLM agents can be made robust to complex, multi-turn adversarial attacks on tool use through a co-evolutionary game, outperforming prior methods on safety and capability benchmarks.

Frontier LLMs fail to reliably identify and apply domain-specific rules in complex, multi-file scenarios, with top models scoring below 63% on core reasoning tasks.

Scientific agent swarms can achieve state-of-the-art performance and generalize to new tasks by evolving through feedback-guided mutation and complementary recombination of hypotheses and code.

Persistent interactive worlds that evolve with history and agent actions are now possible through a novel coupling of a computable world engine and egocentric audiovisual generation.

Even the best LLM agents fail nearly half of long-horizon coding tasks due to harness engineering flaws, with failures concentrating on how cross-cutting functionality is modularized.

Asynchronous RL training on long-horizon tasks achieves superior performance by leveraging Muon and a novel single-rollout recipe that avoids waiting for complete trajectories.

Agentic markets can achieve near-optimal welfare in first-price auctions, with the price of anarchy driven to zero by competitive floors and approaching $1 - 1/e^2$ under near-independent value distributions.

Most social LLMs fail to achieve verifiable success in coordination tasks, even when rated highly by conversational judges.

LLM agents falter significantly when faced with real-world user emotions, revealing a critical fragility in their long-horizon tool-calling capabilities.

Heterogeneous LLMs can share internal factual states without fine-tuning by exchanging word indices mapped to receiver-local vector directions.

Language agents can achieve superior sample efficiency and performance by jointly learning to act and forecast multi-step action sequences within a single policy backbone.

Distilling LLM agents by supervising semantic actions, not token sequences, unlocks significant performance gains and bypasses tokenization constraints.

Most self-distillation methods for agentic RL fail to consistently outperform a strong baseline, and impressive final scores often hide unstable training dynamics and substantial computational overhead.

Agentic robots are no longer just predicting actions, but actively orchestrating their own learning and execution through goal-directed reasoning.

A novel two-axis framework unifies the study of multimodal agent memory, revealing distinct tiers of memory adaptation from static reuse to self-evolving policies.