Home › Code › parse_action

parse_action

Syntologyentry name in harvested coderead from the graph 2026-09-24

parse_action appears in the code Syntology harvested for 33 papers, as 27 distinct code bodies found in 38 places (a place is one code body under one paper). At least one of them ran in 22 of the papers; 11 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named parse_action do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 17 of the 27 distinct code bodies named parse_action; 10 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
3ran · our draft was wrong
0ran · fixture could not drive it
14ran
10unverified
11fingerprinted

Licence is a property of each copy, so it is counted per place: 8 of the 38 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

33 papers shown of 33, newest first; 38 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 3 papers added by Syntology; 3 papers have no page here and are shown by arXiv id only. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
Selective Rollout: Mid-Trajectory Termination for Multi-Sample Agent RL added by Syntology 2026-05 (from id) zhiyuanZhai20/selective-rollout/src/prompts.py 17942fd27330ceb9 ran no licence file found · pointer only
VenusBench-Mobile: A Challenging and User-Centric Benchmark for Mobile GUI Agents with Capability Diagnostics added by Syntology 2026-04 (from id) inclusionAI/UI-Venus/models/browser/venus_browser.py df341ba22d2a7a95 unverified no licence file found · pointer only
BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models added by Syntology 2025-10 (from id) thierry123454/tool-selection-bias/5_bias_investigation/continued_pretraining/plot_compare_base_vs_adapted.py 98bbe08b08d7a02b unverified no licence file found · pointer only
RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments 28 May 2025 osu-nlp-group/redteamcua/mm_agents/uitars_agent.py c242cf8145d74b19 unverified Apache-2.0 (permissive)
WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning 22 May 2025 weizhepei/webagent-r1/WebAgent-R1/Eval/browser_env/envs.py 1829c408a278c974 ran Apache-2.0 (permissive)
ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replay 22 May 2025 dvlab-research/arpo/verl/trainer/gui_agent.py c242cf8145d74b19 unverified Apache-2.0 (permissive)
arXiv:2505.03792 2025-05 (from id) langfengQ/CoSo/digirl/algorithms/causal_digirl/trainer.py fcc406534c37c490 ran Apache-2.0 (permissive)
UI-TARS: Pioneering Automated GUI Interaction with Native Agents 21 Jan 2025 bytedance/ui-tars/codes/ui_tars/action_parser.py c242cf8145d74b19 unverified Apache-2.0 (permissive)
Game-theoretic LLM: Agent Workflow for Negotiation Games 8 Nov 2024 wenyueh/game_theory/src/sequential_game_agent.py 24b0c7cadb707386 unverified Apache-2.0 (permissive)
Learning Evolving Tools for Large Language Models 9 Oct 2024 Chen-GX/ToolEVO/MCTS/src/toolqa.py 53f099b3ef83420f ran fingerprinted no licence file found · pointer only
NNetscape Navigator: Complex Demonstrations for Web Agents Without a Demonstrator 3 Oct 2024 MurtyShikhar/NNetnav/src/postprocess_trajectories_agentlab.py 1e0ac88be6fda037 unverified Apache-2.0 (permissive)
DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects 3 Oct 2024 zhaowei-wang-nlp/divscene/agent_inference/hf_idefics2_gpt4o.py b6552010f6d8a287 ran fingerprinted MIT (permissive)
DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects 3 Oct 2024 zhaowei-wang-nlp/divscene/agent_inference/hf_idefics2_online_client.py 7a16f1f9f950f857 ran fingerprinted MIT (permissive)
DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects 3 Oct 2024 zhaowei-wang-nlp/divscene/agent_inference/hf_idefics2_server.py a24d87222eb1a622 ran fingerprinted MIT (permissive)
Infer Human's Intentions Before Following Natural Language Instructions 26 Sep 2024 simon-wan/fiser/dataloaders/data_utils.py 7a7525f5ae8ab255 ran Apache-2.0 (permissive)
Tree Search for Language Model Agents 1 Jul 2024 kohjingyu/search-agents/browser_env/envs.py 1829c408a278c974 ran MIT (permissive)
Ask-before-Plan: Proactive Language Agents for Real-World Planning 18 Jun 2024 magicgh/ask-before-plan/common/chat.py 4be69b5d38ffb46e ran fingerprinted MIT (permissive)
PDDLEGO: Iterative Planning in Textual Environments 30 May 2024 zharry29/nl-to-pddl/source/pddl_evaluation/src/compare_plan.py 9fc0305b3d6abb02 ran MIT (permissive)
WorkBench: a Benchmark Dataset for Agents in a Realistic Workplace Setting 1 May 2024 olly-styles/workbench/src/evals/agent.py a3db7ab2f37601d6 ran fingerprinted MIT (permissive)
KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents 5 Mar 2024 zjunlp/knowagent/Path_Generation/hotpotqa_run/agent_arch.py 9f8148d447f9ea0c ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
Large Language Models are Learnable Planners for Long-Term Recommendation 29 Feb 2024 jizhi-zhang/billp/Agents/agent_base.py 215250417118aa19 ran MIT (permissive)
AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System 23 Feb 2024 salesforceairesearch/agentlite/agentlite/agents/agent_utils.py 8cbdbfe07b3e0678 ran fingerprinted Apache-2.0 (permissive)
Mirror: A Multiple-perspective Self-Reflection Method for Knowledge-rich Reasoning 22 Feb 2024 hanqi-qi/mirror/agents_module.py a236bd96b70f98f1 ran fingerprinted no licence file found · pointer only
Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents 17 Feb 2024 lancopku/agent-backdoor-attacks/AgentTuning/AgentTuning/AgentBench.old/src/tasks/webshop/web_agent_site/engine/engine.py f482598cf447f335 ran · our draft was wrong fingerprinted no licence file found · pointer only
TravelPlanner: A Benchmark for Real-World Planning with Language Agents 2 Feb 2024 llv22/travelplanner_forward/agents/tool_agents.py 744db5623472fa82 ran · our draft was wrong fingerprinted no licence file found · pointer only
VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks 24 Jan 2024 web-arena-x/visualwebarena/browser_env/envs.py 1829c408a278c974 ran MIT (permissive)
AutoAct: Automatic Agent Learning from Scratch for QA via Self-Planning 10 Jan 2024 zjunlp/autoact/Self_Plan/Group_Planning/benchmark_run/Meta_agent_arch.py 9f8148d447f9ea0c ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
LASER: LLM Agent with State-Space Exploration for Web Navigation 15 Sep 2023 mayer123/laser/web_agent_site/engine/engine.py f482598cf447f335 ran · our draft was wrong fingerprinted GPL-3.0 (copyleft) · pointer only
BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents 11 Aug 2023 salesforce/bolaa/hotpotqa_run/agent_arch.py 9f8148d447f9ea0c ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
WebArena: A Realistic Web Environment for Building Autonomous Agents 25 Jul 2023 web-arena-x/webarena/browser_env/envs.py 1829c408a278c974 ran Apache-2.0 (permissive)
ToolQA: A Dataset for LLM Question Answering with External Tools 23 Jun 2023 night-chen/toolqa/benchmark/chameleon/run_toolqa/run-v2.py f71b690030237706 unverified Apache-2.0 (permissive)
ToolQA: A Dataset for LLM Question Answering with External Tools 23 Jun 2023 night-chen/toolqa/benchmark/ReAct/code/agents.py 0cd0094dec049291 unverified Apache-2.0 (permissive)
ToolQA: A Dataset for LLM Question Answering with External Tools 23 Jun 2023 night-chen/toolqa/benchmark/ReAct/code/environment.py 23aab7577a21a4cf unverified Apache-2.0 (permissive)
Hierarchical Prompting Assists Large Language Model on Web Navigation 23 May 2023 oootttyyy/webarena/browser_env/envs.py 1829c408a278c974 ran Apache-2.0 (permissive)
Reflexion: Language Agents with Verbal Reinforcement Learning 20 Mar 2023 noahshinn/reflexion/hotpotqa_runs/agents.py 0cd0094dec049291 unverified MIT (permissive)
Reflexion: Language Agents with Verbal Reinforcement Learning 20 Mar 2023 noahshinn/reflexion/hotpotqa_runs/environment.py 23aab7577a21a4cf unverified MIT (permissive)
arXiv:openreview_krRRnq3E1w zhangSchnee/BoG/bog/actions.py 5383ad4e44568f23 unverified Apache-2.0 (permissive)
arXiv:openreview_9aU4vrHPKD Octobrist/CoPE/src/world/extract_plan_from_golden.py cea54f4f2666afeb unverified Apache-2.0 (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections