Papers › Skill Expansion and Composition in Parameter Space

Skill Expansion and Composition in Parameter Space

9 Feb 2025arXiv:2502.05932archive 2025-07-28

Tenglong Liu, Jianxiong Li, Yinan Zheng, Haoyi Niu, Yixing Lan, Xin Xu, Xianyuan Zhan

Humans excel at reusing prior knowledge to address new challenges and developing skills while solving problems. This paradigm becomes increasingly popular in the development of autonomous agents, as it develops systems that can self-evolve in response to new challenges like human beings. However, previous methods suffer from limited training efficiency when expanding new skills and fail to fully leverage prior knowledge to facilitate new task learning. In this paper, we propose Parametric Skill Expansion and Composition (PSEC), a new framework designed to iteratively evolve the agents' capabilities and efficiently address new challenges by maintaining a manageable skill library. This library can progressively integrate skill primitives as plug-and-play Low-Rank Adaptation (LoRA) modules in parameter-efficient finetuning, facilitating efficient and flexible skill expansion. This structure also enables the direct skill compositions in parameter space by merging LoRA modules that encode different skills, leveraging shared information across skills to effectively program new skills. Based on this, we propose a context-aware module to dynamically activate different skills to collaboratively handle new tasks. Empowering diverse applications including multi-objective composition, dynamics shift, and continual policy shift, the results on D4RL, DSRL benchmarks, and the DeepMind Control Suite show that PSEC exhibits superior capacity to leverage prior knowledge to efficiently tackle new challenges, as well as expand its skill libraries to evolve the capabilities. Project website: https://ltlhuuu.github.io/PSEC/.

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 12 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 2 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 10 ran (8 with no instrument failure; 2 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 10 samples that ran have no recorded date.

ltlhuuu/PSEC officialmentioned on GitHubjaxMITSyntology: 12 samples, 10 ran (2 instrument-failed) · 2 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

12 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 2 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · honoured contract
2ran · violated contract
1ran · our draft was wrong
1ran; the contract check could not run
2ran
2unverified

Licence: 9 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. For 9 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ltlhuuu/PSEC. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

ltlhuuu/PSEC official repository 12 samples, 10 ran (2 instrument-failed) · 2 unverified
compute_q jaxrl5/agents/psec/psec_finetune.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) here; the stored copy is pointer only · efbad980c5e8e094 · report fixture: signature critic_fn:callable/0/?, critic_params:dict/0/?, observations:ArrayImpl/2/float, actions:ArrayImpl/2/float · returned ArrayImpl · level recorded, date not recorded
cosine_beta_schedule in 76 papers jaxrl5/networks/diffusion.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 87d1bc442d93916d · report fixture: signature timesteps:int/0/int, s:float/0/float · returned ArrayImpl · level recorded 2026-09-22
evaluate1 jaxrl5/evaluation_dsrl.py ran MIT (permissive) · 74b0ae56402911be · report fixture: signature agent:MinimalAgent/0/?, env:MinimalEnv/0/?, num_episodes:int/0/int, save_video:bool/0/bool, render:bool/0/bool, train_lora:bool/0/bool, eval_maxq_weight:float/0/float, eval_minqc_weight:float/0/float · returned dict · level recorded 2026-09-24
evaluate2 jaxrl5/evaluation_dsrl.py ran MIT (permissive) · c7143d30af7311f2 · report fixture: signature agent:MinimalAgent/0/?, env:MinimalEnv/0/?, num_episodes:int/0/int, save_video:bool/0/bool, render:bool/0/bool, train_lora:bool/0/bool, eval_maxq_weight:float/0/float, eval_minqc_weight:float/0/float · returned dict · level recorded 2026-09-24
expectile_loss in 13 papers
census: 5 implementations from 6 papers, 4 distinct outputs on one shared input
jaxrl5/agents/psec/psec_finetune.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · ad221b0896e1bcd0 · report fixture: signature diff:ArrayImpl/1/float, expectile:float/0/float · returned ArrayImpl · level recorded, date not recorded
get_weight_decay_mask jaxrl5/networks/mlp.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 1049990078a4b0f2 · report fixture: signature params:FrozenDict/0/? · returned FrozenDict · level recorded 2026-09-24
linear_beta_schedule in 42 papers jaxrl5/networks/diffusion.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · 0cd44ae2231fcb3b · report fixture: signature timesteps:int/0/int, beta_start:float/0/float, beta_end:float/0/float · returned ArrayImpl · level recorded 2026-09-24
mish in 95 papers
census: 5 implementations from 8 papers, 1 distinct output on one shared input
jaxrl5/agents/psec/psec_pretrain.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 7fc1d127bf81537f · report fixture: signature x:ArrayImpl/2/float · returned ArrayImpl · level recorded 2026-09-22
safe_expectile_loss jaxrl5/agents/psec/psec_finetune.py ran · violated contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 7e821a429b5ff00e · report fixture: signature diff:ArrayImpl/2/float, expectile:float/0/float · returned ArrayImpl · level recorded, date not recorded
vp_beta_schedule in 10 papers jaxrl5/networks/diffusion.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 539aaf559a17a19a · report fixture: signature timesteps:int/0/int · returned ArrayImpl · level recorded 2026-09-22
evaluate in 514 papers jaxrl5/evaluation_dsrl.py unverified MIT (permissive) · 27b1370715ab6f72 · report
subsample_ensemble in 5 papers jaxrl5/networks/ensemble.py unverified MIT (permissive) here; the stored copy is pointer only · c021b9fd8bb7677d · report

Tasks

D4RL

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