Category

ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL

Trains LLM agents to proactively edit and manage their working context for long-horizon tasks using an expanded toolset (planning, long-term memory, soft offloading) and a fine-grained RL algorithm that identifies critical edits and assigns action-level credit. Improves accuracy while keeping contexts compact on long-context QA and deep search.

PaperGym: Rubric-Centered Evolution for Research-Plan Generation

Turns each research paper into a training environment to generate verifiable research plans by synthesizing questions from goals/background and deriving evaluation criteria from methods/experiments. Key features: four-stage extraction that reduces criterion leakage to 3.7%, a two-stage rubric-centered training (self-distillation then GRPO), and the PaperGym-20k corpus with two held-out benchmarks.

EmbodiedSkills: A Unified Framework for Orchestrating, Training, and Deploying VLA Agents

Wraps vision–language–action policies into executable skills that are runtime-validated, executed as bounded low-level action chunks, outcome-verified, and logged as structured trajectories. A fixed skill interface enables swapping or adapting low-level VLA policies and provides component-level supervision for training and optional online adaptation.

Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills

Distills operational know‑how from ML GitHub repositories into compact, verified 'skills' that research agents can load and reuse. Produces a skill format (SKILL.md, references, scripts), the AREX‑Skill Library (5,000+ skills from 1,000 repos), and demonstrates sizable benchmark gains when agents use skills.

EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction

Predicts an LLM agent's final success or failure from partial execution traces and halts runs when outcomes are confident to save per-task compute. Uses LightGBM success/failure classifiers on behavioral, textual, and reference features; cuts 13–26% steps and up to 44% input tokens on benchmarks.

Iris: Climbing to the Search Frontier

Presents two LLM-based search agents (Iris-mini and Iris-pro) trained by alternating supervised fine-tuning and reinforcement learning against live web search. Key features: web-graph-derived multi-hop tasks with entity abstraction, SFT–RL climbing, inference-time context management, and state-of-the-art open-source benchmark results.

Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments

Reconstructs executable terminal workspaces from recorded agent trajectories and synthesizes verifiable single- and multi-round coding tasks for agent training; it replays file operations, uses an LLM completion agent to fill missing files/dependencies, and verifies tasks with autogenerated test suites.

Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization

Studies when and how an assistant should ask clarification questions before converting natural-language problem descriptions into optimization models. Introduces OR-Clarify, a benchmark for pre-formulation clarification, and InterOPT, a two-stage framework that diagnoses formulation-critical gaps and guides targeted questioning and stopping decisions.

Grounded Skill Synthesis from Code at Scale for Agentic Intelligence

Transforms source code into verifiable, reusable agent skills by extracting atomic operations, workflows, and recurring patterns and validating them via source-body-blind reconstruction. Produces CodeSkillBank (1,006,822 accepted records from 19,769 GitHub repos) and yields ~11.7% average downstream improvement.

EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents

Synthesizes a deployment-specific safety harness (natural-language policy plus executable logic) for a frozen LLM in a target domain, using model behavior, domain specs, and adversarial review to optimize safety–utility trade-offs and transfer across agent benchmarks.

Scores Alone Do Not Prove Discovery: The Discovery Certification Protocol for Auditing AI Research Agents

Defines the Discovery Certification Protocol (DCP) to audit claims of discovery by AI research agents, converting claims into executable recovery and feedback tests. Specifies multi-gate certification, Core control requirements, and a deterministic offline verifier; validated in two controlled audits.

SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?

Evaluates whether AI agents can autonomously use Sparse Autoencoders (SAEs) to discover interpretable features and causally steer model behavior. Introduces a 20-task benchmark that has agents design contrastive probes to search a 131K+ feature dictionary in Gemma-2-9B-IT and evaluates activation rank, selectivity, and causal steering against expert references.