PreAct compiles successful agent executions into verifiable state-machine programs for 8.5-13x faster replay on repeated tasks, with an independent evaluator check before storing each program.
hub Canonical reference
Executable code actions elicit better LLM agents
Canonical reference. 80% of citing Pith papers cite this work as background.
29
Pith papers citing it
9
external citations · external index
Background
80% of classified citations
hub tools
citation-role summary
background 8
method 2
citation-polarity summary
representative citing papers
ADK Arena evaluates 51 Python ADKs by having an LLM learn each framework's API, write and repair agent code, and run on benchmarks, finding 57% success rate, 5.6x cost variation, no dominant framework, and substitutable information sources.
CAI Dataset is presented as the largest described corpus of LLM-driven hacker trajectories, with the claim that operator data concentration in frontier-model providers creates a major security risk best addressed by on-premise specialized LLMs.
RubricRefine is a training-free pre-execution method that creates rubrics to score and fix inter-tool contract violations in agent code, reaching 0.86 average on M3ToolEval across seven models with zero executions and lower latency.
LLM agents reach only 35% average checkpoint completion on ten realistic CTF challenges in a new open benchmark with automated partial-credit scoring.
Structural dependency graphs and staged pre-execution verification raise LLM-based EDA code pass rates to 82.5% (single-step) and 70-84% (multi-step) while halving tool calls by catching dependency violations before runtime.
MatClaw shows a code-first LLM agent autonomously generating and executing workflows for ML force field training, Curie temperature prediction, and parameter search on CuInP2S6, succeeding on code but requiring interventions for tacit domain knowledge.
Proposes Agentic Programming in which programs control execution flow and LLMs act as invoked components (LLM-as-Code) only for reasoning, producing DAG-structured contexts that improve stability in long-horizon computer-use agents.
RAH improves coding performance on Oolong-Synthetic from 71.75% to 81.36% with fixed GPT-5 backbone by spawning subagent harnesses via executable scripts.
Closed-Loop Trace Distillation distills one-line natural-language prompts from labeled training traces to improve VLM accuracy on predicting minimal-success action chains in Exploratory Manipulation Trace QA by 0.38-0.47 across simulator and real-robot tasks.
A meta-skill authors and refines prose-and-code skills for agents by learning from post-deployment failures with an overfit audit, achieving 56.8% accuracy on SkillsBench tasks versus 43.6% for human-curated skills.
SkillLens organizes skills into policies-strategies-procedures-primitives layers, retrieves via degree-corrected random walk, and uses a verifier for local adaptation, yielding up to 6.31 pp gains on MuLocbench and raising ALFWorld success from 45% to 51.31%.
SST V2 introduces parallel-trainable nonlinear recurrence in latent space to let transformers reason continuously across positions, delivering +15 points on GPQA-Diamond and halving remaining GSM8K errors over matched baselines.
MindTrellis enables users and AI to co-create evolving knowledge graphs, outperforming retrieval-only tools in expert-rated content coverage, structural quality, and reduced cognitive load during a study of 12 participants creating slide decks.
GenericAgent outperforms other LLM agents on long-horizon tasks by maximizing context information density with fewer tokens via minimal tools, on-demand memory, trajectory-to-SOP evolution, and compression.
The paper systematizes agentic skills beyond tool use, providing design pattern and representation-scope taxonomies plus security analysis of malicious skill infiltration in agent marketplaces.
AgentProg reframes interaction history as a program with variables and control flow, plus a belief state for partial observability, achieving SOTA success rates on long-horizon GUI benchmarks while baselines degrade.
GenoMAS deploys six specialized LLM agents with guided planning to preprocess transcriptomic data and identify genes, reaching 89.13% composite similarity and 60.48% F1 on the GenoTEX benchmark while outperforming prior methods.
Yuvion LLM applies adversarially aware training and introduces the YLRE benchmark set, claiming superior safety robustness over larger models on multiple tasks.
SkillDisCo distills reusable PFSM subgraphs from successful agent traces and compiles them into callable procedural skills, improving success rates and reducing turns on ALFWorld and WebArena.
SSA harness matches frontier model pass@1 scores on agent benchmarks and 138k trajectory analysis in code state-spaces shows model-specific differences in edit frequency, testing activity, and phase transitions.
A closed-loop workflow using Gaussian process surrogate modeling and Bayesian optimization, updated over ten iterations with 106 wet-lab tests, adapted from literature data to identify a cryoprotectant formulation achieving 95.15% post-thaw viability for cryomicroneedles.
Proposes and tests a constitutive definition of 'agent harness' via conceptual analysis of literature and six real systems.
BCER agent improves end-to-end reliability of long-horizon MRI workflows via compilation, artifact binding, and bounded local recovery, outperforming reactive baselines especially on long-chain tasks across brain, prostate, and cardiac benchmarks.
citing papers explorer
-
RubricRefine: Improving Tool-Use Agent Reliability with Training-Free Pre-Execution Refinement
RubricRefine is a training-free pre-execution method that creates rubrics to score and fix inter-tool contract violations in agent code, reaching 0.86 average on M3ToolEval across seven models with zero executions and lower latency.
-
State Stream Transformer (SST) V2: Parallel Training of Nonlinear Recurrence for Latent Space Reasoning
SST V2 introduces parallel-trainable nonlinear recurrence in latent space to let transformers reason continuously across positions, delivering +15 points on GPQA-Diamond and halving remaining GSM8K errors over matched baselines.