Papers › REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction

REFLECT: Summarizing Robot Experiences for Failure Explanation and Correction

27 Jun 2023arXiv:2306.15724archive 2025-07-28

Zeyi Liu, Arpit Bahety, Shuran Song

The ability to detect and analyze failed executions automatically is crucial for an explainable and robust robotic system. Recently, Large Language Models (LLMs) have demonstrated strong reasoning abilities on textual inputs. To leverage the power of LLMs for robot failure explanation, we introduce REFLECT, a framework which queries LLM for failure reasoning based on a hierarchical summary of robot past experiences generated from multisensory observations. The failure explanation can further guide a language-based planner to correct the failure and complete the task. To systematically evaluate the framework, we create the RoboFail dataset with a variety of tasks and failure scenarios. We demonstrate that the LLM-based framework is able to generate informative failure explanations that assist successful correction planning.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 19 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 19 samples from 1 repository, 9 ran (9 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

real-stanford/reflect officialmentioned on GitHubpytorchMITSyntology: 19 samples, 9 ran (0 instrument-failed) · 10 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

19 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

9ran
10unverified

Licence: 0 of the 19 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from real-stanford/reflect. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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 label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

real-stanford/reflect official repository 19 samples, 9 ran (0 instrument-failed) · 10 unverified
camera_space_xyz_to_world_xyz main/point_cloud_utils.py ran MIT (permissive) · 4f68169add358db7 · report fixture: signature camera_space_xyzs:Tensor/2/float, camera_world_xyz:Tensor/1/float, rotation:float/0/float, horizon:float/0/float · returned Tensor · level recorded 2026-09-26
flatten_list in 30 papers main/gen_data.py ran fingerprinted MIT (permissive) · cbf146cba6f1e1e4 · report fixture: signature lis:list/1/list · returned list · level recorded 2026-09-26
get_failure_injection_idx main/gen_data.py ran MIT (permissive) · a1beae3860112855 · report fixture: signature taskUtil:TaskUtil/0/?, actions:list/1/str, task:dict/0/?, action_idxs:list/1/int, nav_idxs:list/1/int, interact_cnt:int/0/int, nav_cnt:int/0/int · returned int · level recorded 2026-09-26
get_iou in 34 papers main/scene_graph.py ran fingerprinted MIT (permissive) · 2cc0c2941e7fc49a · report fixture: signature pred_box:ndarray/1/float, gt_box:ndarray/1/float · returned tuple · level recorded 2026-09-26
get_object_list_from_actions main/data.py ran MIT (permissive) · 1422367f717832a4 · report fixture: signature actions:list/1/str · returned list · level recorded 2026-09-26
get_scene_text main/exp.py ran MIT (permissive) · dbea2913a1b8d249 · report fixture: signature scene_graph:SceneGraph/0/? · returned str · level recorded 2026-09-26
load_data in 700 papers main/data.py ran MIT (permissive) · 89a91dfceeb2c26c · report fixture: signature task_path:str/0/str, task:dict/0/? · returned tuple · level recorded 2026-09-26
object_string_to_intid main/constants.py ran fingerprinted MIT (permissive) · c2293cf765f32ac0 · report fixture: signature object_str:str/0/str · returned int · level recorded 2026-09-26
world_space_xyz_to_camera_space_xyz main/point_cloud_utils.py ran MIT (permissive) · ee172cf12ba1e5aa · report fixture: signature world_space_xyzs:Tensor/2/float, camera_world_xyz:Tensor/2/float, rotation:float/0/float, horizon:float/0/float · returned Tensor · level recorded 2026-09-26
execute_correction_plan main/execute_replan.py unverified MIT (permissive) · f3d2917953b42b9d · report
get_2d_bbox_from_3d_pcd main/get_local_sg.py unverified MIT (permissive) · 5c58ab566b34016f · report
get_held_object main/exp.py unverified MIT (permissive) · 28406307196048ee · report
get_img_feats main/clip_utils.py unverified MIT (permissive) · 8e468b70570c5e0e · report
get_nn_text main/clip_utils.py unverified MIT (permissive) · 99feff65213f3359 · report
get_node_dist main/scene_graph.py unverified MIT (permissive) · 0fdc59d8880aa5b9 · report
get_object_state main/scene_graph.py unverified MIT (permissive) · 89b4cacb10231f36 · report
navigate_to_obj main/action_primitives.py unverified MIT (permissive) · b234710abadc6349 · report
object_color_to_intid main/constants.py unverified MIT (permissive) · 97218b66214d3fc3 · report
object_intid_to_color main/constants.py unverified MIT (permissive) · 15b4c4537630e284 · report

Tasks

Common Sense ReasoningLarge Language ModelRobot Task Planning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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