{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_abc5cf60b378ffc1b4b6c8ab5c5c91d294b6bf9bc4bfc9ec4cfbff1b9b0beef0","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_abc5cf60b378ffc1b4b6c8ab5c5c91d294b6bf9bc4bfc9ec4cfbff1b9b0beef0","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"94176624e48b0736774897cda06526cd2e4a4d0ce657f13ebed08d0382e336f1","published":"Tue, 26 May 2026 00:00:00 -0400","receipt_hash":"94176624e48b0736774897cda06526cd2e4a4d0ce657f13ebed08d0382e336f1","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"94176624e48b0736774897cda06526cd2e4a4d0ce657f13ebed08d0382e336f1","observed_at":"2026-05-26T04:43:39.018238Z","parent_run_hash":"dca8dedd754ad6a1772113d6b97ee4f4ab9a0afbdeb44aaace5ff2d2446b164b","published":"Tue, 26 May 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2502.10906v2 Announce Type: replace \nAbstract: Reward design plays a pivotal role in the training of game AIs, requiring substantial domain-specific knowledge and human effort. In recent years, several studies have explored reward generation for training game agents and controlling robots using large language models (LLMs). In the content generation literature, there has been early work on generating reward functions for reinforcement learning agent generators. This work introduces PCGRLLM, an extended architecture based on earlier work, which employs a feedback mechanism and several reasoning-based prompt engineering techniques. We evaluate the proposed method on a story-to-reward generation task in a two-dimensional environment using two state-of-the-art LLMs across various reasoning-based prompting methods. Our experiments provide insightful evaluations that demonstrate the capabilities of LLMs essential for content generation tasks. The results demonstrate a substantial perfo","title":"PCGRLLM: Large Language Model-Driven Reward Design for Procedural Content Generation Reinforcement Learning","url":"https://arxiv.org/abs/2502.10906","vendor":"arxiv_cs_ai"},"summary":"arXiv:2502.10906v2 Announce Type: replace \nAbstract: Reward design plays a pivotal role in the training of game AIs, requiring substantial domain-specific knowledge and human effort. In recent years, several studies have explored reward generation for training game agents and controlling robots using large language models (LLMs). In the content generation literature, there has been early work on generating reward functions for reinforcement learning agent generators. This work introduces PCGRLLM, an extended architecture based on earlier work, which employs a feedback mechanism and several reasoning-based prompt engineering techniques. We evaluate the proposed method on a story-to-reward generation task in a two-dimensional environment using two state-of-the-art LLMs across various reasoning-based prompting methods. Our experiments provide insightful evaluations that demonstrate the capabilities of LLMs essential for content generation tasks. The results demonstrate a substantial perfo","title":"PCGRLLM: Large Language Model-Driven Reward Design for Procedural Content Generation Reinforcement Learning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-26T04:43:39Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2502.10906"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:eb02f7e4182c620b51f4b9d345fb9a2e7c8930cb4513c6a9ef81bd35e0cd249f5b72bb32f80317b65a4b5508ccb1d3a0ab5819b1b4fe0546f5b7ab1fdbefac09","signer":"crovia.substrate","subject":{"observed_at":"2026-05-26T04:43:39Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2502.10906"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"c6969dcb483e33e335a590d07cf6630784f38baa8f6dae3ae6d8baaeeb558d4e","leaf_index":151770,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"d514b462abd28d67534f6728d50e833aba1d7af82cc70e0214764e2bb5c0ac6d","side":"right"},{"sibling":"d97c872722d3363c7d4ec3031d97fcbc92e331181d7546f34e01ed66971b5bcc","side":"left"},{"sibling":"aebb6d42d3039f45dd2c6723c16432602f49ec4c0604a8f973d2f2fc5c53c4cc","side":"right"},{"sibling":"00a0172c311351d6228071d01407078281a1a60a72e131c623cd85372cc55a20","side":"left"},{"sibling":"bd5e22c4cec0af076b731c3cb7866ae4bcd8cadb6c3339b71979fe2034716556","side":"left"},{"sibling":"4ae6332358f1845b78ca5df224c5c067ed70893a61ca3ccb6220dbb5118b086b","side":"right"},{"sibling":"995c5183ae35c285c0b1b516f6ec38a4e2ea87b861f4feb17fe9bba32548c97d","side":"left"},{"sibling":"f9db7ff3c5db7011b2738b446bad7b165ec8fd162c800ba3bad08298201edaa3","side":"left"},{"sibling":"aff657821100efc777fe98abc63d25a13c2d813d2a00f85a278e295ee3a166b3","side":"right"},{"sibling":"879666fab72e779ab55d0564eaabd64b00534fd6bba7f18412c7f31f61ffd09f","side":"right"},{"sibling":"f40ccedd90c323817e961adc0a2e2db82b8aabe192b6c9d5a373ff988987b207","side":"right"},{"sibling":"b85ea61ae405eed84392a7b6b1eee5536f5a38d6b04070638e23ec7b71e3443a","side":"right"},{"sibling":"d415e6939aee710631f5062799379b547d2c3e3d9a68f263bbb5a693285ab2ca","side":"left"},{"sibling":"e5893793e3591ed7f5e58ca94ffcfba46bb30f69fb1c25d5ba8ef49eb99f9126","side":"right"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"e3eecaf996dbe7229a7bb1d234c97aea97a252c5f7c89f8547b6d091db0f0e40","side":"right"},{"sibling":"55bcbd4da3e20d93931f7e58673f10232e81a5b1514d7396cb4b71e8f95788d0","side":"right"},{"sibling":"d841ad93efda0869e5eb97678f348f03f5caab4353e05ff4bf18f47fb945b822","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":152106,"merkle_root":"ac5182c6f3dd09931f2a689df5f4be36df7b55e55bcf106e195671f5ed55fd8f","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260526T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-26T05:37:34Z","sig_algorithm":"ed25519","signature":"a401243fbd2c077d29a623c6ef616c78fbd5c8ce1930afa7af7165b2386e5a8cf15d5094983a1c962e71b27b911a3f3ce09c8cfab9393be2ce5ce8ee6513da06","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_abc5cf60b378ffc1b4b6c8ab5c5c91d294b6bf9bc4bfc9ec4cfbff1b9b0beef0"}}