Agents

Pandora simulates psychotherapy clients by separating psychological state and content planning from an individual expression planner, improving expression similarity and reducing perceived AI-like judgments in the reported evaluation.

Axion 1.0 is a fully open agent foundation model trained with two SFT stages plus RL, without dedicated mid-training, DPO, or OPD, and is competitive across a broad agentic benchmark suite.

ToolSpace reverses data-centric environment synthesis by mining tool-composition graphs from real execution traces and synthesizing replay-verified cross-environment tasks, lifting long-horizon tool-use scores and producing harder Pro benchmark splits.

VidUEU-Agent is an automated agent pipeline that converts raw videos into 100K multimodal instruction samples and improves understanding, editing, and unified benchmark scores after fine-tuning.

EvoTeam is a collaboration-centric evolution framework that maintains reusable agent teams and jointly evolves team organization, team-specific interaction rules, and individual agent skills to improve LLM multi-agent systems across heterogeneous tasks.

WebHarbor is a suite of 153 dockerized, executable reconstructions of real websites, built through task-driven human-agent collaboration, providing 3,518 tasks for evaluating and RL-training GUI web agents under deterministic control.

SpecPilot is an autonomous agentic loop that uses a ceiling-based cost model, parallel coding agents, stock-calibrated token forcing and a structured memory to discover lossless algorithms and systems optimizations for speculative decoding deployments, raising speedup over AR from 4.46× to 10.87× with one request and from 1.94× to 3.93× with batching.

MolRSI is an AI agent that combines experience-guided workflow search with persistent cross-task memory to recursively improve molecular discovery workflows, and it is experimentally validated in antibiotic screening and pMHC binder design.

ParetoSaddler separates intermediate Pareto-aware promotion from final deployment selection, improving quality and reducing cost on ClawMark and GAIA2.

Caper pre-executes each proposed shell command in a snapshotted sandbox, gives an LLM approver a bounded effects report, commits allowed commands, and rolls back blocked ones with a reason.

Mage-VL-Cowork is a 4B hybrid computer-use agent trained through a five-stage curriculum on 318,837 trajectories generated by evolved GUI and terminal harnesses and reusable workflows, reaching 66.0% on OSWorld-Verified with a 50-step budget.

Recursa adapts a foundation model system to a new domain without human experts or a stronger teacher model by bootstrapping a knowledge repository of instructions, skills, and memory from domain materials, then refining it through parallel multi-agent recursive self-improvement, raising all-pass rate on Harvey LAB's Firm Knowledge benchmark from 30.0% to 55.0% with DeepSeek-V4.1-Flash and from 35.0% to 46.0% with Qwen3.8-Flash.

This report proposes a four-dimension taxonomy for LLM-agent systems that perform computer graphics tasks and builds an agentic literature survey system that applies the taxonomy at scale to 350 papers, revealing design trends and open challenges.

CUA-Master is a nested double-loop recursive framework that couples open-world seeding and primitive-based task synthesis with iterative model training to improve computer-use agents.

CoworkOS is a cowork-agent harness that separates model-chosen task strategy from runtime execution management and supports long-horizon, human-in-the-loop work across benchmarks, real applications, and automated post-training.

The paper frames video generation through an agent harness that coordinates production, world-model interaction, and development toward recursive self-improvement.

uni-robot-agent is a unified, modular harness that lets open-weight models perform competitive robot use in simulation and the real world, and the paper links effective robot use to four general capabilities.

SWE-Trail uses prior attempts as collector-side history to choose where to compare candidate actions during coding-agent rollouts, then trains students on the resulting trajectories.

NorthCUA is an integrated harness, experience-production flywheel, and staged-learning pipeline that trains Nano, Mini, and Pro computer-use agents and reports strong GUI grounding, desktop, web, and latency results.

ReTrace is a scalable evaluation framework that formalizes transition-consistent recovery and uses goal-oriented action replay after controlled error injection to systematically study model-based recovery in computer-use agents.

Reviso is an agentic video captioning framework that learns a Context-Focus-Points observation plan and uses verification-guided SFT plus GRPO rewards to gather prioritized visual evidence with tools.

The paper proposes Avatar Intelligence: persistent personal agents that represent a user's goals, values, and constraints, with a user-centric architecture, an L0-L3 delegation roadmap, and the Agentic Oversight Index for evaluating delivered value against human oversight burden.

R2Orch nests self-play orchestration with a learnability-based Proposer and randomized skill-withdrawal tests, improving a Director toward zero-skill deployment across twelve benchmarks.

REA is a routed embodied agent runtime that coordinates a slow System 2 brain, a router and fast System 0 policies so that no running policy waits on the brain.

Apriel Voice 27B Preview is an open speech-language model built on Gemma 4 26B-A4B that uses a two-stage speech-adaptation recipe to unify speech understanding, reasoning, conversation, and tool calls while retaining text and image inputs.

CEPO is a framework that splits multi-agent prompts into a shared coordinator prompt and agent-specific executor prompts, and gives the underlying prompt optimizer role-specific meta-instructions for each layer, improving four existing optimizers across 11 benchmarks in four domains.

CodeSpecWeave synthesizes coding tasks with interdependent specifications and reliable executable tests, producing 4,670 training tasks and a 100-task benchmark.

WorkFactory constructs executable professional tasks by planning information support and repairing environments through probe execution, then uses teacher trajectories to train the WorkPilot models.

Co-Design Bench evaluates coding agents on 273 real-user application revisions with hidden acceptance criteria, finding that strong models satisfy many criteria per task but fully complete only a minority of tasks.

VibeGame couples an AI-native 2D game engine with an eight-agent adversarial team and training-free experience distillation to turn natural-language prompts into playable game projects.

WeVisCut connects a stateful script-to-video agent harness, a four-stage pipeline that recovers executable supervision from finished videos, and a single 9B policy trained through SFT, runtime-verified RFT, Guided-OPD, and RCF-DAPO, evaluated on a 100-task benchmark with five metrics.

WebAnything automatically reconstructs source-grounded executable web environments from real URLs using an Explorer–Builder and independent verifier, yielding 244 artifacts and 12,984 accepted tasks and improving agent benchmarks after SFT.

TAO jointly evaluates tool-return readiness, time-decayed KV-cache credit, and token footprint, then uses dynamic programming to select and place waiting agent sessions on GPU nodes.

RealCLI is a paired CLI benchmark that evaluates autonomous execution and scripted human-agent collaboration on matched tasks, revealing low joint task-collaboration performance among frontier agents.

PersonaCUABench holds 74 tasks fixed while varying the requesting user across 44 personas, and across nine backbones persona requests lower mean task completion from 0.689 to 0.441 while user satisfaction and completion diverge.

TauIndianBankBench is a 1,000-task Indian retail-banking benchmark that scores both required procedure steps and final records for tool-using conversational agents.

CausGround distills interaction trajectories into reusable action-centered causal knowledge over a factorized world state, then grounds task-relevant preconditions and effects to guide frozen MLLM planners without parameter updates.

PreView is a trained auxiliary preprocessor that supplies center-guided cropped and enlarged views plus candidate-specific visual and textual cues to a frozen GUI grounding model, improving accuracy without retraining that model.