{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/register-agent","entry":"register_agent","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":6,"n_papers_ran":3,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":5,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":1,"unverified":3},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2605.27621","paper":"/paper/arxiv-2605-27621","title":"Agents that Matter: Optimizing Multi-Agent LLMs via Removal-Based Attribution","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"ybkim95/agent-scaling","path":"agent_scaling/agents/registry.py","file_url":"https://github.com/ybkim95/agent-scaling/blob/HEAD/agent_scaling/agents/registry.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5d4f251c0080a0ac","mcp_get_code":{"code_sha256":"5d4f251c0080a0ac"}},{"arxiv_id":"2411.11188","paper":"/paper/amago-2-breaking-the-multi-task-barrier-in","title":"AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers","date":"2024-11-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ut-austin-rpl/amago","path":"amago/agent.py","file_url":"https://github.com/ut-austin-rpl/amago/blob/HEAD/amago/agent.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cb28542e368fc51b","mcp_get_code":{"code_sha256":"cb28542e368fc51b"}},{"arxiv_id":"2410.06468","paper":"/paper/does-spatial-cognition-emerge-in-frontier","title":"Does Spatial Cognition Emerge in Frontier Models?","date":"2024-10-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apple/ml-space-benchmark","path":"space/registry.py","file_url":"https://github.com/apple/ml-space-benchmark/blob/HEAD/space/registry.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"8bfd6b5a0eb466ef","mcp_get_code":{"code_sha256":"8bfd6b5a0eb466ef"}},{"arxiv_id":"2310.09971","paper":"/paper/amago-scalable-in-context-reinforcement","title":"AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents","date":"2023-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"UT-Austin-RPL/amago","path":"amago/agent.py","file_url":"https://github.com/UT-Austin-RPL/amago/blob/HEAD/amago/agent.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cb28542e368fc51b","mcp_get_code":{"code_sha256":"cb28542e368fc51b"}},{"arxiv_id":"2212.07919","paper":"/paper/roscoe-a-suite-of-metrics-for-scoring-step-by","title":"ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning","date":"2022-12-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/ParlAI","path":"parlai/core/loader.py","file_url":"https://github.com/facebookresearch/ParlAI/blob/HEAD/parlai/core/loader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"60339a7726e86b18","mcp_get_code":{"code_sha256":"60339a7726e86b18"}},{"arxiv_id":"1906.01603","paper":"/paper/do-neural-dialog-systems-use-the-conversation","title":"Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study","date":"2019-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chinnadhurai/ParlAI","path":"parlai/core/loader.py","file_url":"https://github.com/chinnadhurai/ParlAI/blob/HEAD/parlai/core/loader.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"d1c669045b65dcac","mcp_get_code":{"code_sha256":"d1c669045b65dcac"}}]}